Not in the top 1,000 by GitHub stars

domattioli/structured-gist

Structured outline output for LLM prose — nested lecture-note format instead of paragraphs

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

`skills/structured-gist/SKILL.md`

Week of Nov 2, 2026 · +119 / −124 lines

Before Not checked yet → After Network or broad shell

df2dc317b860 → 5a0abbd32edf

Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.

This preview is limited. See the complete change on GitHub.

Compare on GitHub

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Not checked yet

First observation → df2dc317b860

No earlier version was observed for comparison.

Compare on GitHub

View on GitHub Add to my skills

Verified commit 5a0abbd32edfbdcddb4fa5fba04c8f6041f2b8fe

Version-pinned installation · Claude Code

git clone --filter=blob:none --no-checkout https://github.com/domattioli/structured-gist.git .hotskills/domattioli-structured-gist && git -C .hotskills/domattioli-structured-gist checkout --detach 5a0abbd32edfbdcddb4fa5fba04c8f6041f2b8fe
# Copy each selected skill directory from .hotskills/domattioli-structured-gist into .claude/skills/<skill-name>/

Version-pinned installation · Codex

git clone --filter=blob:none --no-checkout https://github.com/domattioli/structured-gist.git .hotskills/domattioli-structured-gist && git -C .hotskills/domattioli-structured-gist checkout --detach 5a0abbd32edfbdcddb4fa5fba04c8f6041f2b8fe
# Copy each selected skill directory from .hotskills/domattioli-structured-gist into .agents/skills/<skill-name>/

2GitHub stars

0stars in 7 days

1skill in this repository

4commits in 30 days

Heat

1.3

Star growth, last 7 daysNot available
Star growth, last 24 hoursNot available
Rank movement, last 7 daysNot available
Commits, last 30 daysNot available
Accounts asking about it through MCP, last 7 daysNot available
Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

30-day change not yet available: not enough history.

Individual skills in this repository

structured-gist skills/structured-gist

How it works

structured-gist

When your agent uses it

Rewrite explanatory or process-recap prose as a nested lecture-note outline on a fixed marker ladder (concept → attribute → enumerator → `↪` explanation; no plain bullets). Use for agent "what I did and why" recaps, concept / trade-off / cause-chain explanations, session handoffs (`/structured-gist summary`), and finding-first reports (`/structured-gist report`, alias `findings`). Triggers: "structured-gist", "sg", "gist this", "outline this", "notes mode", "sg report", "sg summary", or any request to restructure explanatory text into a skimmable hierarchy. Do NOT use for code, commit messages, bot-template fields or footers, single-fact answers, security or irreversible-action warnings, or when plain prose is requested. Changes structure only, never wording (independent of caveman).

What it loads into context

Frontmatter

202 tokens

Always available to the agent

SKILL.md

5,466 tokens

When the skill is activated

Reference documents

833,389 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

Activation
When — primary target
Marker taxonomy
Length gradient
Hook-arrow `↪` — the explanatory node
Nest by dependency
Pre-emit check
Granularity
Spacing
Emphasis taxonomy
Leaf preservation
Hedge preservation
Carve-outs
Render modes
Worked example
Caveman coexistence
Limitations
Install

Scripts executed separately

benchmarks/compare_corpus.py
benchmarks/content_units.py
benchmarks/controlled/bench/__init__.py
benchmarks/controlled/bench/agents_inc_isolated.py
benchmarks/controlled/bench/baselines.py
benchmarks/controlled/bench/cache.py
benchmarks/controlled/bench/estimate.py
benchmarks/controlled/bench/generate.py
benchmarks/controlled/bench/items.py
benchmarks/controlled/bench/judge.py
benchmarks/controlled/bench/pacing.py
benchmarks/controlled/bench/pipeline.py
benchmarks/controlled/bench/prereg.py
benchmarks/controlled/bench/records.py
benchmarks/controlled/bench/score.py
benchmarks/controlled/bench/words.py
benchmarks/controlled/run.py
benchmarks/controlled/tests/__init__.py
benchmarks/controlled/tests/conftest.py
benchmarks/controlled/tests/fakes.py
benchmarks/controlled/tests/prereg_fixture.py
benchmarks/controlled/tests/test_cache.py
benchmarks/controlled/tests/test_items.py
benchmarks/controlled/tests/test_prereg.py
benchmarks/controlled/tests/test_prompts.py
benchmarks/controlled/tests/test_records.py
benchmarks/controlled/tests/test_run_cli.py
benchmarks/controlled/tests/test_runner.py
benchmarks/controlled/tests/test_words.py
benchmarks/cost_report.py
benchmarks/score_outline.py
benchmarks/semantic-compression/cache_key.py
benchmarks/semantic-compression/external-validation/adapters/build_derived_manifest.py
benchmarks/semantic-compression/external-validation/adapters/common.py
benchmarks/semantic-compression/external-validation/adapters/hotpotqa.py
benchmarks/semantic-compression/external-validation/adapters/qasper.py
benchmarks/semantic-compression/external-validation/adapters/qmsum.py
benchmarks/semantic-compression/external-validation/adapters/test_adapters.py
benchmarks/semantic-compression/external-validation/adapters/validate_derived_gold.py
benchmarks/semantic-compression/external-validation/calibration/compare_calibration.py
benchmarks/semantic-compression/external-validation/evaluation/replication/analyze.py
benchmarks/semantic-compression/external-validation/evaluation/score_deterministic.py
benchmarks/semantic-compression/external-validation/evaluation/score_semantic.py
benchmarks/semantic-compression/external-validation/scripts/build_cases.py
benchmarks/semantic-compression/external-validation/scripts/corpus_lib.py
benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py
benchmarks/semantic-compression/external-validation/scripts/select_hotpotqa.py
benchmarks/semantic-compression/external-validation/scripts/select_qasper.py
benchmarks/semantic-compression/external-validation/scripts/select_qmsum.py
benchmarks/semantic-compression/external-validation/scripts/test_corpus.py
benchmarks/semantic-compression/external-validation/scripts/verify_corpus.py
benchmarks/semantic-compression/run.py
benchmarks/semantic-compression/run_deterministic.sh
benchmarks/semantic-compression/run_judged.sh
benchmarks/semantic-compression/scoring/combine.py
benchmarks/semantic-compression/scoring/deterministic.py
benchmarks/semantic-compression/scoring/findability.py
benchmarks/semantic-compression/scoring/migrate_gold_schema.py
benchmarks/semantic-compression/scoring/outline_nodes.py
benchmarks/semantic-compression/scoring/spr.py
benchmarks/semantic-compression/scoring/structural_linkage.py
benchmarks/semantic-compression/scoring/test_combine.py
benchmarks/semantic-compression/scoring/test_findability.py
benchmarks/semantic-compression/scoring/test_spr.py
benchmarks/semantic-compression/scoring/test_structural_linkage.py
benchmarks/semantic-compression/scoring/test_wording_fidelity.py
benchmarks/semantic-compression/scoring/text_norm.py
benchmarks/semantic-compression/scoring/wording_fidelity.py
benchmarks/semantic-compression/test_cache.py
benchmarks/weight_sweep.py
render/__init__.py
render/claim_list.py
render/test_claim_list.py
scripts/kg.py
scripts/kg_render.py
scripts/validate_plugin.sh
tests/fidelity_check.py
tests/lint_outline.py
tests/smoke.sh
tests/test_benchmark.py
tests/test_claim_list_cli.py
tests/test_kg.py
tests/test_lint.py

Files

../../.claude-plugin/marketplace.jsonasset847 bytes
../../plugins/structured-gist/.claude-plugin/plugin.jsonasset300 bytes
CHANGELOG.mddoc36,100 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
SKILL.mdcore21,981 bytes
benchmarks/compare_corpus.pyruns29,977 bytes
benchmarks/content_units.pyruns9,766 bytes
benchmarks/controlled/PREREGISTRATION.mddoc18,726 bytes
benchmarks/controlled/README.mddoc7,774 bytes
benchmarks/controlled/bench/__init__.pyruns0 bytes
benchmarks/controlled/bench/agents_inc_isolated.pyruns1,663 bytes
benchmarks/controlled/bench/baselines.pyruns4,405 bytes
benchmarks/controlled/bench/cache.pyruns4,430 bytes
benchmarks/controlled/bench/estimate.pyruns5,512 bytes
benchmarks/controlled/bench/generate.pyruns10,595 bytes
benchmarks/controlled/bench/items.pyruns7,192 bytes
benchmarks/controlled/bench/judge.pyruns9,138 bytes
benchmarks/controlled/bench/pacing.pyruns2,897 bytes
benchmarks/controlled/bench/pipeline.pyruns14,071 bytes
benchmarks/controlled/bench/prereg.pyruns24,062 bytes
benchmarks/controlled/bench/records.pyruns9,234 bytes
benchmarks/controlled/bench/score.pyruns19,947 bytes
benchmarks/controlled/bench/stopwords.txtdoc667 bytes
benchmarks/controlled/bench/words.pyruns2,329 bytes
benchmarks/controlled/launchd/.gitkeepasset0 bytes
benchmarks/controlled/prereg.jsonasset12,939 bytes
benchmarks/controlled/prompts/bullets_instruction.mddoc241 bytes
benchmarks/controlled/prompts/judge.mddoc1,733 bytes
benchmarks/controlled/prompts/plain_system.mddoc85 bytes
benchmarks/controlled/prompts/prose_instruction.mddoc226 bytes
benchmarks/controlled/prompts/provider_notice.txtdoc850 bytes
benchmarks/controlled/prompts/shared_user.mddoc200 bytes
benchmarks/controlled/prompts/skill_instruction.mddoc129 bytes
benchmarks/controlled/run.pyruns19,604 bytes
benchmarks/controlled/schemas/judge-output.schema.jsonasset1,266 bytes
benchmarks/controlled/schemas/records.schema.jsonasset13,258 bytes
benchmarks/controlled/slop/cases/.gitkeepasset0 bytes
benchmarks/controlled/tests/__init__.pyruns0 bytes
benchmarks/controlled/tests/conftest.pyruns6,933 bytes
benchmarks/controlled/tests/fakes.pyruns3,363 bytes
benchmarks/controlled/tests/fixtures/cli/agents_inc_help.txtdoc212 bytes
benchmarks/controlled/tests/fixtures/cli/agents_inc_run_help.txtdoc176 bytes
benchmarks/controlled/tests/fixtures/cli/claude_help.txtdoc22,178 bytes
benchmarks/controlled/tests/fixtures/cli/claude_version.txtdoc22 bytes
benchmarks/controlled/tests/fixtures/cli/gask_usage.txtdoc639 bytes
benchmarks/controlled/tests/fixtures/cli/mask_usage.txtdoc719 bytes
benchmarks/controlled/tests/fixtures/cli/oask_usage.txtdoc610 bytes
benchmarks/controlled/tests/fixtures/prompt_hashes.jsonasset639 bytes
benchmarks/controlled/tests/prereg_fixture.pyruns12,939 bytes
benchmarks/controlled/tests/test_cache.pyruns5,979 bytes
benchmarks/controlled/tests/test_items.pyruns4,866 bytes
benchmarks/controlled/tests/test_prereg.pyruns21,067 bytes
benchmarks/controlled/tests/test_prompts.pyruns7,271 bytes
benchmarks/controlled/tests/test_records.pyruns8,099 bytes
benchmarks/controlled/tests/test_run_cli.pyruns7,966 bytes
benchmarks/controlled/tests/test_runner.pyruns18,731 bytes
benchmarks/controlled/tests/test_words.pyruns2,189 bytes
benchmarks/corpus/corpus.jsonasset3,234 bytes
benchmarks/corpus/sources/agentic-harness-explain.mddoc580 bytes
benchmarks/corpus/sources/boundary-formalization.mddoc570 bytes
benchmarks/corpus/sources/cause-chain-root-cause.mddoc477 bytes
benchmarks/corpus/sources/ff-metric-glossary.mddoc1,129 bytes
benchmarks/corpus/sources/ff-release-checklist.mddoc935 bytes
benchmarks/corpus/sources/ff-server-inventory.mddoc824 bytes
benchmarks/corpus/sources/ff-team-conventions.mddoc1,016 bytes
benchmarks/corpus/sources/hook-fix-recap.mddoc514 bytes
benchmarks/corpus/sources/ld-arch-decision.mddoc3,850 bytes
benchmarks/corpus/sources/ld-incident-timeline.mddoc3,456 bytes
benchmarks/corpus/sources/ld-migration-guide.mddoc3,834 bytes
benchmarks/corpus/sources/ld-onboarding-doc.mddoc3,818 bytes
benchmarks/corpus/sources/mx-api-overview.mddoc1,593 bytes
benchmarks/corpus/sources/mx-postmortem-actions.mddoc1,449 bytes
benchmarks/corpus/sources/mx-quarterly-review.mddoc1,594 bytes
benchmarks/corpus/sources/mx-tooling-survey.mddoc1,838 bytes
benchmarks/corpus/sources/pr-collision-postmortem.mddoc602 bytes
benchmarks/corpus/sources/quality-gate-design.mddoc455 bytes
benchmarks/corpus/sources/rebase-conflict-recap.mddoc474 bytes
benchmarks/corpus/sources/trade-off-model-tiering.mddoc590 bytes
benchmarks/cost_report.pyruns10,017 bytes
benchmarks/prompts.jsonasset5,372 bytes
benchmarks/renderings/agentic-harness-explain/direct.mddoc658 bytes
benchmarks/renderings/agentic-harness-explain/kg.jsonasset3,685 bytes
benchmarks/renderings/agentic-harness-explain/kg.mddoc672 bytes
benchmarks/renderings/agentic-harness-explain/kg.meta.jsonasset19 bytes
benchmarks/renderings/boundary-formalization/direct.mddoc583 bytes
benchmarks/renderings/boundary-formalization/kg.jsonasset1,985 bytes
benchmarks/renderings/boundary-formalization/kg.mddoc530 bytes
benchmarks/renderings/boundary-formalization/kg.meta.jsonasset19 bytes
benchmarks/renderings/cause-chain-root-cause/direct.mddoc355 bytes
benchmarks/renderings/cause-chain-root-cause/kg.jsonasset1,451 bytes
benchmarks/renderings/cause-chain-root-cause/kg.mddoc337 bytes
benchmarks/renderings/cause-chain-root-cause/kg.meta.jsonasset19 bytes
benchmarks/renderings/ff-metric-glossary/direct.mddoc1,012 bytes
benchmarks/renderings/ff-metric-glossary/kg.jsonasset3,679 bytes
benchmarks/renderings/ff-metric-glossary/kg.mddoc796 bytes
benchmarks/renderings/ff-metric-glossary/kg.meta.jsonasset19 bytes
benchmarks/renderings/ff-release-checklist/direct.mddoc481 bytes
benchmarks/renderings/ff-release-checklist/kg.jsonasset3,093 bytes
benchmarks/renderings/ff-release-checklist/kg.mddoc573 bytes
benchmarks/renderings/ff-release-checklist/kg.meta.jsonasset19 bytes
benchmarks/renderings/ff-server-inventory/direct.mddoc593 bytes
benchmarks/renderings/ff-server-inventory/kg.jsonasset3,128 bytes
benchmarks/renderings/ff-server-inventory/kg.mddoc632 bytes
benchmarks/renderings/ff-server-inventory/kg.meta.jsonasset19 bytes
benchmarks/renderings/ff-team-conventions/direct.mddoc772 bytes
benchmarks/renderings/ff-team-conventions/kg.jsonasset3,486 bytes
benchmarks/renderings/ff-team-conventions/kg.mddoc707 bytes
benchmarks/renderings/ff-team-conventions/kg.meta.jsonasset19 bytes
benchmarks/renderings/hook-fix-recap/direct.mddoc504 bytes
benchmarks/renderings/hook-fix-recap/kg.jsonasset1,921 bytes
benchmarks/renderings/hook-fix-recap/kg.mddoc504 bytes
benchmarks/renderings/hook-fix-recap/kg.meta.jsonasset19 bytes
benchmarks/renderings/ld-arch-decision/direct.mddoc1,161 bytes
benchmarks/renderings/ld-arch-decision/kg.jsonasset4,588 bytes
benchmarks/renderings/ld-arch-decision/kg.mddoc1,283 bytes
benchmarks/renderings/ld-arch-decision/kg.meta.jsonasset19 bytes
benchmarks/renderings/ld-incident-timeline/direct.mddoc1,159 bytes
benchmarks/renderings/ld-incident-timeline/kg.jsonasset4,164 bytes
benchmarks/renderings/ld-incident-timeline/kg.mddoc1,128 bytes
benchmarks/renderings/ld-incident-timeline/kg.meta.jsonasset19 bytes
benchmarks/renderings/ld-migration-guide/direct.mddoc1,161 bytes
benchmarks/renderings/ld-migration-guide/kg.jsonasset3,857 bytes
benchmarks/renderings/ld-migration-guide/kg.mddoc1,077 bytes
benchmarks/renderings/ld-migration-guide/kg.meta.jsonasset19 bytes
benchmarks/renderings/ld-onboarding-doc/direct.mddoc1,135 bytes
benchmarks/renderings/ld-onboarding-doc/kg.jsonasset3,786 bytes
benchmarks/renderings/ld-onboarding-doc/kg.mddoc959 bytes
benchmarks/renderings/ld-onboarding-doc/kg.meta.jsonasset19 bytes
benchmarks/renderings/mx-api-overview/direct.mddoc1,095 bytes
benchmarks/renderings/mx-api-overview/kg.jsonasset3,880 bytes
benchmarks/renderings/mx-api-overview/kg.mddoc1,031 bytes
benchmarks/renderings/mx-api-overview/kg.meta.jsonasset19 bytes
benchmarks/renderings/mx-postmortem-actions/direct.mddoc1,051 bytes
benchmarks/renderings/mx-postmortem-actions/kg.jsonasset3,325 bytes
benchmarks/renderings/mx-postmortem-actions/kg.mddoc892 bytes
benchmarks/renderings/mx-postmortem-actions/kg.meta.jsonasset19 bytes
benchmarks/renderings/mx-quarterly-review/direct.mddoc998 bytes
benchmarks/renderings/mx-quarterly-review/kg.jsonasset3,987 bytes
benchmarks/renderings/mx-quarterly-review/kg.mddoc956 bytes
benchmarks/renderings/mx-quarterly-review/kg.meta.jsonasset19 bytes
benchmarks/renderings/mx-tooling-survey/direct.mddoc1,124 bytes
benchmarks/renderings/mx-tooling-survey/kg.jsonasset3,582 bytes
benchmarks/renderings/mx-tooling-survey/kg.mddoc1,119 bytes
benchmarks/renderings/mx-tooling-survey/kg.meta.jsonasset19 bytes
benchmarks/renderings/pr-collision-postmortem/direct.mddoc540 bytes
benchmarks/renderings/pr-collision-postmortem/kg.jsonasset1,916 bytes
benchmarks/renderings/pr-collision-postmortem/kg.mddoc557 bytes
benchmarks/renderings/pr-collision-postmortem/kg.meta.jsonasset19 bytes
benchmarks/renderings/quality-gate-design/direct.mddoc412 bytes
benchmarks/renderings/quality-gate-design/kg.jsonasset1,714 bytes
benchmarks/renderings/quality-gate-design/kg.mddoc397 bytes
benchmarks/renderings/quality-gate-design/kg.meta.jsonasset19 bytes
benchmarks/renderings/rebase-conflict-recap/direct.mddoc416 bytes
benchmarks/renderings/rebase-conflict-recap/kg.jsonasset1,871 bytes
benchmarks/renderings/rebase-conflict-recap/kg.mddoc439 bytes
benchmarks/renderings/rebase-conflict-recap/kg.meta.jsonasset19 bytes
benchmarks/renderings/trade-off-model-tiering/direct.mddoc566 bytes
benchmarks/renderings/trade-off-model-tiering/kg.jsonasset1,784 bytes
benchmarks/renderings/trade-off-model-tiering/kg.mddoc497 bytes
benchmarks/renderings/trade-off-model-tiering/kg.meta.jsonasset19 bytes
benchmarks/reports/ab-reads-v0.4.0.mddoc4,320 bytes
benchmarks/reports/comparison-v0.4.0.jsonasset44,918 bytes
benchmarks/reports/comparison-v0.4.0.mddoc5,267 bytes
benchmarks/reports/comparison-v0.5.0b1.jsonasset44,118 bytes
benchmarks/reports/comparison-v0.5.0b1.mddoc5,645 bytes
benchmarks/requirements.txtdoc18 bytes
benchmarks/results/.gitkeepasset0 bytes
benchmarks/score_outline.pyruns21,144 bytes
benchmarks/scoring.mddoc5,563 bytes
benchmarks/semantic-compression/.cache/judged/.gitignoreasset14 bytes
benchmarks/semantic-compression/FINDABILITY_FINDINGS.mddoc25,788 bytes
benchmarks/semantic-compression/README.mddoc22,060 bytes
benchmarks/semantic-compression/RESULTS.mddoc14,907 bytes
benchmarks/semantic-compression/SPR_FINDINGS.mddoc25,828 bytes
benchmarks/semantic-compression/WORDING_FIDELITY_FINDINGS.mddoc17,227 bytes
benchmarks/semantic-compression/cache_key.pyruns1,171 bytes
benchmarks/semantic-compression/external-validation/.gitignoreasset347 bytes
benchmarks/semantic-compression/external-validation/DERIVED_MANIFEST.jsonasset39,212 bytes
benchmarks/semantic-compression/external-validation/HANDOFF.mddoc4,955 bytes
benchmarks/semantic-compression/external-validation/MANIFEST.jsonasset20,901 bytes
benchmarks/semantic-compression/external-validation/README.mddoc20,130 bytes
benchmarks/semantic-compression/external-validation/THIRD_PARTY_NOTICES.mddoc8,164 bytes
benchmarks/semantic-compression/external-validation/adapters/ADAPTER_DESIGN.mddoc14,504 bytes
benchmarks/semantic-compression/external-validation/adapters/ADJUDICATION_PROTOCOL.mddoc3,386 bytes
benchmarks/semantic-compression/external-validation/adapters/ANNOTATION_PROTOCOL.mddoc11,419 bytes
benchmarks/semantic-compression/external-validation/adapters/FINDINGS.mddoc15,224 bytes
benchmarks/semantic-compression/external-validation/adapters/HANDOFF_FULL_EVAL.mddoc5,822 bytes
benchmarks/semantic-compression/external-validation/adapters/NATIVE_SNAPSHOT.jsonasset14,609 bytes
benchmarks/semantic-compression/external-validation/adapters/build_derived_manifest.pyruns4,327 bytes
benchmarks/semantic-compression/external-validation/adapters/common.pyruns9,639 bytes
benchmarks/semantic-compression/external-validation/adapters/hotpotqa.pyruns957 bytes
benchmarks/semantic-compression/external-validation/adapters/qasper.pyruns848 bytes
benchmarks/semantic-compression/external-validation/adapters/qmsum.pyruns845 bytes
benchmarks/semantic-compression/external-validation/adapters/test_adapters.pyruns13,571 bytes
benchmarks/semantic-compression/external-validation/adapters/validate_derived_gold.pyruns8,486 bytes
benchmarks/semantic-compression/external-validation/calibration/calibration_comparison.jsonasset2,508 bytes
benchmarks/semantic-compression/external-validation/calibration/compare_calibration.pyruns4,879 bytes
benchmarks/semantic-compression/external-validation/calibration/hotpotqa-01/annotator_a.jsonasset2,717 bytes
benchmarks/semantic-compression/external-validation/calibration/hotpotqa-01/annotator_b.jsonasset2,399 bytes
benchmarks/semantic-compression/external-validation/calibration/hotpotqa-02/annotator_a.jsonasset2,330 bytes
benchmarks/semantic-compression/external-validation/calibration/hotpotqa-02/annotator_b.jsonasset2,833 bytes
benchmarks/semantic-compression/external-validation/calibration/qasper-01/annotator_a.jsonasset4,526 bytes
benchmarks/semantic-compression/external-validation/calibration/qasper-01/annotator_b.jsonasset4,020 bytes
benchmarks/semantic-compression/external-validation/calibration/qasper-02/annotator_a.jsonasset1,273 bytes
benchmarks/semantic-compression/external-validation/calibration/qasper-02/annotator_b.jsonasset1,236 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-01/annotator_a.jsonasset6,164 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-01/annotator_b.jsonasset8,024 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-02/annotator_a.jsonasset5,561 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-02/annotator_b.jsonasset6,989 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-03/annotator_a.jsonasset10,114 bytes
benchmarks/semantic-compression/external-validation/calibration/qmsum-03/annotator_b.jsonasset15,002 bytes
benchmarks/semantic-compression/external-validation/evaluation/GENERATION_PROTOCOL.mddoc2,448 bytes
benchmarks/semantic-compression/external-validation/evaluation/JUDGE_PROTOCOL.mddoc4,923 bytes
benchmarks/semantic-compression/external-validation/evaluation/RESULTS.mddoc24,567 bytes
benchmarks/semantic-compression/external-validation/evaluation/RUN_MANIFEST.jsonasset3,319 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/deterministic_scores.jsonasset339,193 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-01.jsonasset7,688 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-02.jsonasset7,309 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-03.jsonasset6,392 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-04.jsonasset5,918 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-05.jsonasset9,543 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-06.jsonasset8,700 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-07.jsonasset6,923 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/judgments/hotpotqa-08.jsonasset8,266 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-01/deep.mddoc5,548 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-01/skim.mddoc1,058 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-01/standard.mddoc3,959 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-02/deep.mddoc5,838 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-02/skim.mddoc929 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-02/standard.mddoc4,844 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-03/deep.mddoc6,676 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-03/skim.mddoc956 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-03/standard.mddoc4,573 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-04/deep.mddoc3,368 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-04/skim.mddoc874 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-04/standard.mddoc2,854 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-05/deep.mddoc5,346 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-05/skim.mddoc1,275 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-05/standard.mddoc4,580 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-06/deep.mddoc8,790 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-06/skim.mddoc1,281 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-06/standard.mddoc6,847 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/deep.mddoc6,136 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/skim.mddoc1,338 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/standard.mddoc5,286 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-08/deep.mddoc6,073 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-08/skim.mddoc1,174 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-08/standard.mddoc5,283 bytes
benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/scores.jsonasset60,253 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/deterministic_scores.jsonasset563,479 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-01.jsonasset11,225 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-02.jsonasset13,176 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-03.jsonasset11,199 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-04.jsonasset13,710 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-05.jsonasset10,248 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-06.jsonasset4,446 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-07.jsonasset3,214 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-08.jsonasset4,503 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-09.jsonasset3,603 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/judgments/qasper-10.jsonasset4,548 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-01/deep.mddoc6,074 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-01/skim.mddoc581 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-01/standard.mddoc2,697 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-02/deep.mddoc7,144 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-02/skim.mddoc852 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-02/standard.mddoc3,703 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-03/deep.mddoc5,897 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-03/skim.mddoc603 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-03/standard.mddoc3,089 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-04/deep.mddoc7,941 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-04/skim.mddoc752 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-04/standard.mddoc4,060 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-05/deep.mddoc5,125 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-05/skim.mddoc470 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-05/standard.mddoc2,304 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-06/deep.mddoc12,728 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-06/skim.mddoc1,266 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-06/standard.mddoc5,426 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-07/deep.mddoc15,498 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-07/skim.mddoc1,832 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-07/standard.mddoc7,807 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-08/deep.mddoc18,116 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-08/skim.mddoc1,708 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-08/standard.mddoc8,441 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-09/deep.mddoc16,323 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-09/skim.mddoc2,034 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-09/standard.mddoc8,828 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-10/deep.mddoc21,021 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-10/skim.mddoc2,654 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/renderings/qasper-10/standard.mddoc10,963 bytes
benchmarks/semantic-compression/external-validation/evaluation/qasper/scores.jsonasset79,955 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/deterministic_scores.jsonasset1,554,670 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-01.jsonasset13,439 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-02.jsonasset16,939 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-03.jsonasset20,111 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-04.jsonasset19,308 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-05.jsonasset10,100 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-06.jsonasset14,977 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-07.jsonasset7,903 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-08.jsonasset10,710 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-09.jsonasset9,686 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-10.jsonasset13,963 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-11.jsonasset13,391 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-12.jsonasset8,614 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-13.jsonasset20,474 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-14.jsonasset9,790 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-15.jsonasset10,912 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-16.jsonasset5,298 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-17.jsonasset7,918 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-18.jsonasset8,170 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-19.jsonasset12,094 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-20.jsonasset10,543 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-21.jsonasset10,663 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-22.jsonasset9,224 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-23.jsonasset15,469 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-24.jsonasset13,144 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-01/deep.mddoc4,839 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-01/skim.mddoc984 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-01/standard.mddoc3,270 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-02/deep.mddoc6,040 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-02/skim.mddoc1,165 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-02/standard.mddoc4,836 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-03/deep.mddoc7,132 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-03/skim.mddoc1,279 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-03/standard.mddoc6,060 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-04/deep.mddoc8,599 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-04/skim.mddoc1,778 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-04/standard.mddoc5,497 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-05/deep.mddoc6,040 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-05/skim.mddoc1,165 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-05/standard.mddoc4,836 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-06/deep.mddoc8,599 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-06/skim.mddoc1,778 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-06/standard.mddoc5,497 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-07/deep.mddoc19,080 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-07/skim.mddoc2,021 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-07/standard.mddoc9,699 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-08/deep.mddoc16,333 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-08/skim.mddoc1,733 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-08/standard.mddoc8,353 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-09/deep.mddoc29,257 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-09/skim.mddoc3,060 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-09/standard.mddoc10,437 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-10/deep.mddoc49,865 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-10/skim.mddoc3,634 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-10/standard.mddoc19,655 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-11/deep.mddoc49,847 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-11/skim.mddoc3,634 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-11/standard.mddoc19,655 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-12/deep.mddoc40,623 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-12/skim.mddoc2,951 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-12/standard.mddoc11,887 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-13/deep.mddoc11,452 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-13/skim.mddoc938 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-13/standard.mddoc6,333 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-14/deep.mddoc14,239 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-14/skim.mddoc622 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-14/standard.mddoc8,162 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-15/deep.mddoc14,239 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-15/skim.mddoc622 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-15/standard.mddoc8,162 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-16/deep.mddoc11,452 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-16/skim.mddoc938 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-16/standard.mddoc6,333 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-17/deep.mddoc6,349 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-17/skim.mddoc668 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-17/standard.mddoc3,609 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-18/deep.mddoc9,387 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-18/skim.mddoc819 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-18/standard.mddoc4,373 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-19/deep.mddoc5,443 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-19/skim.mddoc876 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-19/standard.mddoc3,473 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-20/deep.mddoc3,930 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-20/skim.mddoc703 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-20/standard.mddoc2,629 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-21/deep.mddoc3,930 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-21/skim.mddoc703 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-21/standard.mddoc2,629 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-22/deep.mddoc4,088 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-22/skim.mddoc893 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-22/standard.mddoc3,225 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-23/deep.mddoc4,807 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-23/skim.mddoc1,034 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-23/standard.mddoc3,560 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/deep.mddoc5,206 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/skim.mddoc879 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/standard.mddoc3,470 bytes
benchmarks/semantic-compression/external-validation/evaluation/qmsum/scores.jsonasset363,716 bytes
benchmarks/semantic-compression/external-validation/evaluation/replication/CROSS_METRIC_CASES.mddoc5,152 bytes
benchmarks/semantic-compression/external-validation/evaluation/replication/analyze.pyruns10,156 bytes
benchmarks/semantic-compression/external-validation/evaluation/replication/hypothesis_results.jsonasset46,023 bytes
benchmarks/semantic-compression/external-validation/evaluation/score_deterministic.pyruns3,348 bytes
benchmarks/semantic-compression/external-validation/evaluation/score_semantic.pyruns7,616 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/coverage_audit.jsonasset993 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/derived_blind_weights.jsonasset885 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/derived_gold.jsonasset3,274 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/external_gold.jsonasset1,417 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/source.mddoc6,006 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/coverage_audit.jsonasset720 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/derived_blind_weights.jsonasset901 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/derived_gold.jsonasset3,185 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/external_gold.jsonasset1,362 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/source.mddoc5,865 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/coverage_audit.jsonasset642 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/derived_blind_weights.jsonasset828 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/derived_gold.jsonasset1,510 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/external_gold.jsonasset1,558 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/source.mddoc6,635 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/coverage_audit.jsonasset553 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/derived_blind_weights.jsonasset853 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/derived_gold.jsonasset1,575 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/external_gold.jsonasset1,293 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/source.mddoc3,496 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/coverage_audit.jsonasset617 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/derived_blind_weights.jsonasset933 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/derived_gold.jsonasset1,740 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/external_gold.jsonasset1,363 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/source.mddoc5,451 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/coverage_audit.jsonasset640 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/derived_blind_weights.jsonasset861 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/derived_gold.jsonasset1,586 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/external_gold.jsonasset1,209 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/source.mddoc8,934 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/coverage_audit.jsonasset3,425 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/derived_blind_weights.jsonasset657 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/derived_gold.jsonasset2,938 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/external_gold.jsonasset1,514 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/source.mddoc6,188 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/coverage_audit.jsonasset1,586 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/derived_blind_weights.jsonasset1,139 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/derived_gold.jsonasset2,723 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/external_gold.jsonasset1,378 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/provenance.jsonasset1,184 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/source.mddoc5,365 bytes
benchmarks/semantic-compression/external-validation/hotpotqa/selection.jsonasset65,170 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/coverage_audit.jsonasset541 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/derived_blind_weights.jsonasset1,531 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/derived_gold.jsonasset4,752 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/external_gold.jsonasset2,786 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/source.mddoc30,786 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/coverage_audit.jsonasset562 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/derived_blind_weights.jsonasset786 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/derived_gold.jsonasset1,667 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/external_gold.jsonasset1,649 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/source.mddoc25,146 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/coverage_audit.jsonasset745 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/derived_blind_weights.jsonasset988 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/derived_gold.jsonasset2,200 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/external_gold.jsonasset3,035 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/source.mddoc25,272 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/coverage_audit.jsonasset741 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/derived_blind_weights.jsonasset979 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/derived_gold.jsonasset2,040 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/external_gold.jsonasset4,707 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/source.mddoc28,241 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/coverage_audit.jsonasset1,273 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/derived_blind_weights.jsonasset1,393 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/derived_gold.jsonasset3,632 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/external_gold.jsonasset4,976 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/source.mddoc15,336 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/coverage_audit.jsonasset835 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/derived_blind_weights.jsonasset873 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/derived_gold.jsonasset3,656 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/external_gold.jsonasset3,177 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/source.mddoc13,123 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/coverage_audit.jsonasset671 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/derived_blind_weights.jsonasset484 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/derived_gold.jsonasset1,130 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/external_gold.jsonasset2,923 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/source.mddoc22,582 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/coverage_audit.jsonasset906 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/derived_blind_weights.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/derived_gold.jsonasset3,109 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/external_gold.jsonasset4,105 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/source.mddoc24,761 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/coverage_audit.jsonasset501 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/derived_blind_weights.jsonasset754 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/derived_gold.jsonasset1,797 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/external_gold.jsonasset2,117 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/source.mddoc18,428 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/coverage_audit.jsonasset1,363 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/derived_blind_weights.jsonasset1,102 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/derived_gold.jsonasset3,906 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/external_gold.jsonasset3,165 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/provenance.jsonasset1,069 bytes
benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/source.mddoc24,666 bytes
benchmarks/semantic-compression/external-validation/qasper/selection.jsonasset25,099 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/coverage_audit.jsonasset2,592 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/derived_blind_weights.jsonasset2,688 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/derived_gold.jsonasset10,220 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/external_gold.jsonasset6,847 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/source.mddoc50,820 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/coverage_audit.jsonasset1,466 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/derived_blind_weights.jsonasset2,394 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/derived_gold.jsonasset9,171 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/external_gold.jsonasset4,504 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/source.mddoc80,561 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/coverage_audit.jsonasset3,240 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/derived_blind_weights.jsonasset4,083 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/derived_gold.jsonasset23,636 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/external_gold.jsonasset20,763 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/source.mddoc75,670 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/coverage_audit.jsonasset2,361 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/derived_blind_weights.jsonasset3,676 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/derived_gold.jsonasset12,462 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/external_gold.jsonasset14,477 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/source.mddoc77,551 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/coverage_audit.jsonasset749 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/derived_blind_weights.jsonasset1,619 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/derived_gold.jsonasset5,275 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/external_gold.jsonasset5,445 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/source.mddoc80,561 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/coverage_audit.jsonasset653 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/derived_blind_weights.jsonasset1,698 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/derived_gold.jsonasset5,066 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/external_gold.jsonasset3,366 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/source.mddoc77,551 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/coverage_audit.jsonasset624 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/derived_blind_weights.jsonasset1,372 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/derived_gold.jsonasset3,838 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/external_gold.jsonasset5,315 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/source.mddoc77,551 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/coverage_audit.jsonasset1,808 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/derived_blind_weights.jsonasset2,099 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/derived_gold.jsonasset9,063 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/external_gold.jsonasset10,090 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/source.mddoc70,957 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/coverage_audit.jsonasset2,258 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/derived_blind_weights.jsonasset2,172 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/derived_gold.jsonasset8,766 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/external_gold.jsonasset5,855 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/provenance.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/source.mddoc128,374 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/coverage_audit.jsonasset2,825 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/derived_blind_weights.jsonasset3,246 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/derived_gold.jsonasset15,613 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/external_gold.jsonasset14,608 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/provenance.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/source.mddoc104,880 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/coverage_audit.jsonasset1,694 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/derived_blind_weights.jsonasset2,192 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/derived_gold.jsonasset9,516 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/external_gold.jsonasset18,490 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/provenance.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/source.mddoc104,880 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/coverage_audit.jsonasset3,379 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/derived_blind_weights.jsonasset1,869 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/derived_gold.jsonasset9,711 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/external_gold.jsonasset10,386 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/provenance.jsonasset980 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/source.mddoc90,685 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/coverage_audit.jsonasset2,325 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/derived_blind_weights.jsonasset3,136 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/derived_gold.jsonasset14,684 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/external_gold.jsonasset52,741 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/provenance.jsonasset980 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/source.mddoc90,685 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/coverage_audit.jsonasset1,507 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/derived_blind_weights.jsonasset2,304 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/derived_gold.jsonasset10,039 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/external_gold.jsonasset16,545 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/provenance.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/source.mddoc104,880 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/coverage_audit.jsonasset1,489 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/derived_blind_weights.jsonasset2,384 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/derived_gold.jsonasset11,224 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/external_gold.jsonasset20,324 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/provenance.jsonasset968 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/source.mddoc104,880 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/coverage_audit.jsonasset1,143 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/derived_blind_weights.jsonasset807 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/derived_gold.jsonasset3,654 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/external_gold.jsonasset3,037 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/provenance.jsonasset980 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/source.mddoc90,685 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/coverage_audit.jsonasset932 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/derived_blind_weights.jsonasset971 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/derived_gold.jsonasset3,363 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/external_gold.jsonasset2,610 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/source.mddoc41,125 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/coverage_audit.jsonasset878 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/derived_blind_weights.jsonasset1,091 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/derived_gold.jsonasset2,900 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/external_gold.jsonasset3,303 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/source.mddoc58,648 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/coverage_audit.jsonasset688 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/derived_blind_weights.jsonasset1,817 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/derived_gold.jsonasset5,343 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/external_gold.jsonasset4,324 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/source.mddoc41,125 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/coverage_audit.jsonasset1,271 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/derived_blind_weights.jsonasset1,673 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/derived_gold.jsonasset5,525 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/external_gold.jsonasset4,581 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/source.mddoc44,080 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/coverage_audit.jsonasset1,092 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/derived_blind_weights.jsonasset2,234 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/derived_gold.jsonasset5,927 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/external_gold.jsonasset7,978 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/source.mddoc44,080 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/coverage_audit.jsonasset934 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/derived_blind_weights.jsonasset1,369 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/derived_gold.jsonasset3,485 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/external_gold.jsonasset5,552 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/source.mddoc31,404 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/coverage_audit.jsonasset2,018 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/derived_blind_weights.jsonasset4,340 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/derived_gold.jsonasset14,238 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/external_gold.jsonasset34,720 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/source.mddoc49,117 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/coverage_audit.jsonasset2,848 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/derived_blind_weights.jsonasset4,219 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/derived_gold.jsonasset12,546 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/external_gold.jsonasset21,181 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/provenance.jsonasset962 bytes
benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/source.mddoc53,252 bytes
benchmarks/semantic-compression/external-validation/qmsum/selection.jsonasset28,770 bytes
benchmarks/semantic-compression/external-validation/scripts/build_cases.pyruns15,948 bytes
benchmarks/semantic-compression/external-validation/scripts/corpus_lib.pyruns3,917 bytes
benchmarks/semantic-compression/external-validation/scripts/fetch_sources.pyruns12,794 bytes
benchmarks/semantic-compression/external-validation/scripts/select_hotpotqa.pyruns7,211 bytes
benchmarks/semantic-compression/external-validation/scripts/select_qasper.pyruns12,322 bytes
benchmarks/semantic-compression/external-validation/scripts/select_qmsum.pyruns10,731 bytes
benchmarks/semantic-compression/external-validation/scripts/test_corpus.pyruns12,939 bytes
benchmarks/semantic-compression/external-validation/scripts/verify_corpus.pyruns8,973 bytes
benchmarks/semantic-compression/harness-verification.mddoc6,205 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/gold.jsonasset13,422 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/judged/sonnet-v0.10.0.jsonasset8,587 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/judged/sonnet.jsonasset18,871 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/renderings/sonnet-v0.10.0/standard.mddoc2,423 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/renderings/sonnet/deep.mddoc2,601 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/renderings/sonnet/skim.mddoc362 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/renderings/sonnet/standard.mddoc1,258 bytes
benchmarks/semantic-compression/pressure-tests/causality-heavy-explain/source.mddoc2,282 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/gold.jsonasset10,528 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/judged/haiku.jsonasset18,284 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/judged/sonnet-v0.10.0.jsonasset7,721 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/judged/sonnet.jsonasset24,274 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/haiku/deep.mddoc1,072 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/haiku/skim.mddoc123 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/haiku/standard.mddoc553 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/sonnet-v0.10.0/standard.mddoc2,097 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/sonnet/deep.mddoc2,957 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/sonnet/skim.mddoc614 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/renderings/sonnet/standard.mddoc2,553 bytes
benchmarks/semantic-compression/pressure-tests/cause-chain-reversal/source.mddoc2,153 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/gold.jsonasset11,453 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/judged/haiku.jsonasset22,361 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/judged/sonnet-v0.10.0.jsonasset6,721 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/judged/sonnet.jsonasset21,142 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/haiku/deep.mddoc2,441 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/haiku/skim.mddoc265 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/haiku/standard.mddoc1,148 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/sonnet-v0.10.0/standard.mddoc1,931 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/sonnet/deep.mddoc1,558 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/sonnet/skim.mddoc236 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/renderings/sonnet/standard.mddoc1,162 bytes
benchmarks/semantic-compression/pressure-tests/migration-tristate/source.mddoc1,838 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/gold.jsonasset9,548 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/judged/sonnet-v0.10.0.jsonasset7,074 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/judged/sonnet.jsonasset16,470 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/renderings/sonnet-v0.10.0/standard.mddoc1,621 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/renderings/sonnet/deep.mddoc1,878 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/renderings/sonnet/skim.mddoc349 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/renderings/sonnet/standard.mddoc1,687 bytes
benchmarks/semantic-compression/pressure-tests/negation-and-true-peers/source.mddoc1,657 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/gold.jsonasset10,562 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.10.0-nolint.jsonasset7,746 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.10.0.jsonasset8,026 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.4.12.jsonasset24,474 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.5.0b1.jsonasset23,305 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/sonnet-v0.10.0-nolint.jsonasset7,903 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/sonnet-v0.10.0.jsonasset6,649 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/sonnet.jsonasset19,418 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/haiku/deep.mddoc2,697 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/haiku/skim.mddoc333 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/haiku/standard.mddoc1,605 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.10.0-nolint/standard.mddoc2,866 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.10.0/standard.mddoc2,760 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.4.12/deep.mddoc4,900 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.4.12/skim.mddoc1,693 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.4.12/standard.mddoc3,463 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.5.0b1/deep.mddoc4,296 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.5.0b1/skim.mddoc738 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.5.0b1/standard.mddoc2,042 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet-v0.10.0-nolint/standard.mddoc3,032 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet-v0.10.0/standard.mddoc3,083 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet/deep.mddoc2,697 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet/skim.mddoc333 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet/standard.mddoc1,605 bytes
benchmarks/semantic-compression/pressure-tests/registrar-hedge/source.mddoc2,568 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/gold.jsonasset30,231 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/judged/haiku.jsonasset49,535 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/judged/sonnet-v0.10.0.jsonasset16,121 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/judged/sonnet.jsonasset62,336 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/haiku/deep.mddoc6,539 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/haiku/skim.mddoc471 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/haiku/standard.mddoc2,140 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/sonnet-v0.10.0/standard.mddoc7,245 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/sonnet/deep.mddoc7,199 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/sonnet/skim.mddoc593 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/renderings/sonnet/standard.mddoc3,550 bytes
benchmarks/semantic-compression/pressure-tests/synthetic-scale-verylarge/source.mddoc8,251 bytes
benchmarks/semantic-compression/provenance.jsonasset156 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/gold.jsonasset8,137 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/judged/opus-v0.10.0-nolint.jsonasset5,615 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/judged/opus-v0.10.0.jsonasset5,657 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/judged/sonnet-v0.10.0-nolint.jsonasset6,544 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/judged/sonnet-v0.10.0.jsonasset5,655 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/judged/sonnet.jsonasset17,385 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/opus-v0.10.0-nolint/standard.mddoc2,112 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/opus-v0.10.0/standard.mddoc2,094 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/sonnet-v0.10.0-nolint/standard.mddoc2,038 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/sonnet-v0.10.0/standard.mddoc2,143 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/sonnet/deep.mddoc1,940 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/sonnet/skim.mddoc330 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/renderings/sonnet/standard.mddoc1,187 bytes
benchmarks/semantic-compression/regression/near-identical-numbers/source.mddoc1,776 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/gold.jsonasset14,356 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/judged/sonnet-v0.10.0.jsonasset8,328 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/judged/sonnet.jsonasset26,416 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/renderings/sonnet-v0.10.0/standard.mddoc2,991 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/renderings/sonnet/deep.mddoc2,817 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/renderings/sonnet/skim.mddoc597 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/renderings/sonnet/standard.mddoc1,551 bytes
benchmarks/semantic-compression/regression/real-benchmark-archaeology/source.mddoc3,144 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/gold.jsonasset8,132 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/judged/opus-v0.10.0-nolint.jsonasset5,770 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/judged/opus-v0.10.0.jsonasset6,497 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/judged/sonnet-v0.10.0-nolint.jsonasset5,768 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/judged/sonnet-v0.10.0.jsonasset6,609 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/judged/sonnet.jsonasset15,159 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/opus-v0.10.0-nolint/standard.mddoc1,723 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/opus-v0.10.0/standard.mddoc1,415 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/sonnet-v0.10.0-nolint/standard.mddoc1,498 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/sonnet-v0.10.0/standard.mddoc1,717 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/sonnet/deep.mddoc1,375 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/sonnet/skim.mddoc356 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/renderings/sonnet/standard.mddoc1,072 bytes
benchmarks/semantic-compression/regression/real-hook-discovery/source.mddoc1,474 bytes
benchmarks/semantic-compression/results/FINDABILITY_SCORES.mddoc45,604 bytes
benchmarks/semantic-compression/results/SCORES.mddoc9,749 bytes
benchmarks/semantic-compression/results/SPR_SCORES.mddoc6,362 bytes
benchmarks/semantic-compression/results/WORDING_FIDELITY_SCORES.mddoc4,803 bytes
benchmarks/semantic-compression/results/combined.jsonasset79,043 bytes
benchmarks/semantic-compression/results/deterministic.jsonasset66,181 bytes
benchmarks/semantic-compression/results/findability.jsonasset664,145 bytes
benchmarks/semantic-compression/results/judged.jsonasset2 bytes
benchmarks/semantic-compression/results/readme_example.mddoc5,279 bytes
benchmarks/semantic-compression/results/spr.jsonasset25,838 bytes
benchmarks/semantic-compression/results/weight_comparison.jsonasset4,443 bytes
benchmarks/semantic-compression/results/wording_fidelity.jsonasset294,092 bytes
benchmarks/semantic-compression/run.pyruns11,946 bytes
benchmarks/semantic-compression/run_deterministic.shruns510 bytes
benchmarks/semantic-compression/run_judged.shruns571 bytes
benchmarks/semantic-compression/scoring/STRUCTURAL_LINKAGE.mddoc3,100 bytes
benchmarks/semantic-compression/scoring/blind_weights/causality-heavy-explain.jsonasset3,143 bytes
benchmarks/semantic-compression/scoring/blind_weights/cause-chain-reversal.jsonasset1,466 bytes
benchmarks/semantic-compression/scoring/blind_weights/migration-tristate.jsonasset1,572 bytes
benchmarks/semantic-compression/scoring/blind_weights/near-identical-numbers.jsonasset2,413 bytes
benchmarks/semantic-compression/scoring/blind_weights/negation-and-true-peers.jsonasset2,453 bytes
benchmarks/semantic-compression/scoring/blind_weights/real-benchmark-archaeology.jsonasset2,210 bytes
benchmarks/semantic-compression/scoring/blind_weights/real-hook-discovery.jsonasset1,431 bytes
benchmarks/semantic-compression/scoring/blind_weights/synthetic-scale-verylarge.jsonasset2,553 bytes
benchmarks/semantic-compression/scoring/combine.pyruns12,393 bytes
benchmarks/semantic-compression/scoring/deterministic.pyruns4,460 bytes
benchmarks/semantic-compression/scoring/findability.pyruns38,466 bytes
benchmarks/semantic-compression/scoring/hedge_lexicon.jsonasset5,347 bytes
benchmarks/semantic-compression/scoring/migrate_gold_schema.pyruns6,021 bytes
benchmarks/semantic-compression/scoring/outline_nodes.pyruns4,660 bytes
benchmarks/semantic-compression/scoring/spr.pyruns15,999 bytes
benchmarks/semantic-compression/scoring/structural_linkage.jsonasset115,155 bytes
benchmarks/semantic-compression/scoring/structural_linkage.pyruns22,643 bytes
benchmarks/semantic-compression/scoring/test_combine.pyruns7,070 bytes
benchmarks/semantic-compression/scoring/test_findability.pyruns26,429 bytes
benchmarks/semantic-compression/scoring/test_spr.pyruns10,714 bytes
benchmarks/semantic-compression/scoring/test_structural_linkage.pyruns1,595 bytes
benchmarks/semantic-compression/scoring/test_wording_fidelity.pyruns5,088 bytes
benchmarks/semantic-compression/scoring/text_norm.pyruns6,997 bytes
benchmarks/semantic-compression/scoring/wording_fidelity.pyruns14,396 bytes
benchmarks/semantic-compression/suite.jsonasset600 bytes
benchmarks/semantic-compression/test_cache.pyruns5,921 bytes
benchmarks/weight_sweep.pyruns10,853 bytes
examples/attribute.mddoc1,396 bytes
examples/caveman-combo.mddoc730 bytes
examples/report.mddoc1,911 bytes
examples/self-explain.mddoc1,560 bytes
examples/splice-to-subtree.mddoc1,581 bytes
examples/standard.mddoc730 bytes
reference/activation-hooks.mddoc1,689 bytes
reference/composition.mddoc1,829 bytes
reference/install.mddoc659 bytes
reference/kg-mode.mddoc4,804 bytes
reference/render-modes.mddoc12,046 bytes
reference/self-explain-notes.mddoc2,799 bytes
render/README.mddoc4,000 bytes
render/__init__.pyruns0 bytes
render/claim_list.pyruns14,853 bytes
render/claim_list.schema.jsonasset2,027 bytes
render/test_claim_list.pyruns19,135 bytes
scripts/kg.pyruns15,730 bytes
scripts/kg_render.pyruns23,264 bytes
scripts/validate_plugin.shruns3,556 bytes
tests/RESULTS.mddoc4,603 bytes
tests/benchmark.mddoc39,973 bytes
tests/fidelity_check.pyruns5,917 bytes
tests/fixtures/bad_attr_self_nest.mddoc144 bytes
tests/fixtures/bad_bullet.mddoc133 bytes
tests/fixtures/bad_connective_because.mddoc58 bytes
tests/fixtures/bad_ladder.mddoc133 bytes
tests/fixtures/bad_mixed_siblings.mddoc171 bytes
tests/fixtures/bad_nonleaf_arrow_not_first.mddoc189 bytes
tests/fixtures/bad_r10_arrow_multi.mddoc63 bytes
tests/fixtures/bad_r11_indent.mddoc322 bytes
tests/fixtures/bad_r11_long.mddoc225 bytes
tests/fixtures/bad_r13.mddoc172 bytes
tests/fixtures/bad_r14.mddoc228 bytes
tests/fixtures/bad_r15.mddoc244 bytes
tests/fixtures/bad_r16_depth_indent.mddoc158 bytes
tests/fixtures/bad_r16_depth_indent_arrow.mddoc151 bytes
tests/fixtures/bad_r2_skip_rung.mddoc177 bytes
tests/fixtures/bad_r5_arrow_two_facts.mddoc77 bytes
tests/fixtures/bad_r7_enum_depth4_overlong.mddoc132 bytes
tests/fixtures/bad_r9.mddoc126 bytes
tests/fixtures/bad_r9_arrow_chain.mddoc237 bytes
tests/fixtures/bad_r9_arrow_splice.mddoc73 bytes
tests/fixtures/bad_responsive_dash_at_depth1.mddoc71 bytes
tests/fixtures/bad_responsive_ladder.mddoc141 bytes
tests/fixtures/bad_responsive_unbolded_attr.mddoc79 bytes
tests/fixtures/bad_wordy_top.mddoc122 bytes
tests/fixtures/bench/README.mddoc2,102 bytes
tests/fixtures/bench/base_outline.mddoc963 bytes
tests/fixtures/bench/base_source.mddoc977 bytes
tests/fixtures/bench/brevity_padded.mddoc1,206 bytes
tests/fixtures/bench/damage_series_1.mddoc964 bytes
tests/fixtures/bench/damage_series_2.mddoc968 bytes
tests/fixtures/bench/damage_series_3.mddoc968 bytes
tests/fixtures/bench/degenerate/allstop_outline.mddoc174 bytes
tests/fixtures/bench/degenerate/allstop_source.mddoc30 bytes
tests/fixtures/bench/degenerate/allstop_unit_source.mddoc170 bytes
tests/fixtures/bench/degenerate/empty.mddoc0 bytes
tests/fixtures/bench/degenerate/hallucinated_outline.mddoc403 bytes
tests/fixtures/bench/degenerate/single_fact_source.mddoc19 bytes
tests/fixtures/bench/degenerate/unrelated_outline.mddoc545 bytes
tests/fixtures/bench/retention_swapped.mddoc957 bytes
tests/fixtures/bench/robustness_violated.mddoc968 bytes
tests/fixtures/fidelity/branch_unsupported.mddoc803 bytes
tests/fixtures/fidelity/declaration_malformed.mddoc723 bytes
tests/fixtures/fidelity/hedge_dropped.mddoc708 bytes
tests/fixtures/fidelity/relation_upgraded.mddoc744 bytes
tests/fixtures/fidelity/relation_upgraded_wrapped.mddoc941 bytes
tests/fixtures/good_arrow_branch_preview.mddoc67 bytes
tests/fixtures/good_attribute.mddoc188 bytes
tests/fixtures/good_mixed_mode_regions.mddoc113 bytes
tests/fixtures/good_nonleaf_arrow.mddoc203 bytes
tests/fixtures/good_r11.mddoc336 bytes
tests/fixtures/good_r11_width120.mddoc222 bytes
tests/fixtures/good_r13.mddoc272 bytes
tests/fixtures/good_r14.mddoc258 bytes
tests/fixtures/good_r15.mddoc230 bytes
tests/fixtures/good_r16_depth_indent.mddoc245 bytes
tests/fixtures/good_r2_no_skip.mddoc181 bytes
tests/fixtures/good_r5_deep_arrows.mddoc290 bytes
tests/fixtures/good_r7_arrow_overlong_not_capped.mddoc93 bytes
tests/fixtures/good_r7_depth1_attr_within_cap.mddoc42 bytes
tests/fixtures/good_r9.mddoc251 bytes
tests/fixtures/good_r9_arrow_chain.mddoc219 bytes
tests/fixtures/good_responsive.mddoc469 bytes
tests/fixtures/good_responsive_explanation_leaf.mddoc62 bytes
tests/fixtures/good_responsive_glyphfree.mddoc117 bytes
tests/fixtures/good_responsive_role_ladder.mddoc1,195 bytes
tests/fixtures/good_single_clause_because_fragment.mddoc79 bytes
tests/fixtures/good_wrapped_continuation.mddoc384 bytes
tests/fixtures/kg/bad_arrow_rarity.jsonasset519 bytes
tests/fixtures/kg/bad_attr_under_attr.jsonasset402 bytes
tests/fixtures/kg/bad_concept_depth.jsonasset287 bytes
tests/fixtures/kg/bad_cycle.jsonasset520 bytes
tests/fixtures/kg/bad_dangling_ref.jsonasset226 bytes
tests/fixtures/kg/bad_duplicate_id.jsonasset282 bytes
tests/fixtures/kg/bad_edge_type_mismatch.jsonasset400 bytes
tests/fixtures/kg/bad_empty_text.jsonasset151 bytes
tests/fixtures/kg/bad_mixed_child_role.jsonasset407 bytes
tests/fixtures/kg/bad_mixed_part_order.jsonasset416 bytes
tests/fixtures/kg/bad_multiple_parents.jsonasset422 bytes
tests/fixtures/kg/bad_multiple_summaries.jsonasset673 bytes
tests/fixtures/kg/bad_no_root.jsonasset294 bytes
tests/fixtures/kg/bad_orphan.jsonasset344 bytes
tests/fixtures/kg/bad_part_depth.jsonasset541 bytes
tests/fixtures/kg/bad_rank.jsonasset280 bytes
tests/fixtures/kg/bad_rank_duplicate.jsonasset424 bytes
tests/fixtures/kg/bad_render_overflow.jsonasset595 bytes
tests/fixtures/kg/bad_schema.jsonasset268 bytes
tests/fixtures/kg/bad_text_delimiter_tail.jsonasset381 bytes
tests/fixtures/kg/bad_text_stray_marker.jsonasset176 bytes
tests/fixtures/kg/bad_unknown_edge_type.jsonasset283 bytes
tests/fixtures/kg/bad_unknown_node_type.jsonasset170 bytes
tests/fixtures/kg/bad_word_budget.jsonasset183 bytes
tests/fixtures/kg/canonical.jsonasset1,821 bytes
tests/fixtures/kg/golden/canonical.deep.mddoc413 bytes
tests/fixtures/kg/golden/canonical.skim.mddoc210 bytes
tests/fixtures/kg/golden/canonical.standard.mddoc413 bytes
tests/fixtures/kg/golden/valid_attronly.deep.mddoc120 bytes
tests/fixtures/kg/golden/valid_attronly.skim.mddoc59 bytes
tests/fixtures/kg/golden/valid_attronly.standard.mddoc120 bytes
tests/fixtures/kg/golden/valid_deep.deep.mddoc211 bytes
tests/fixtures/kg/golden/valid_deep.skim.mddoc65 bytes
tests/fixtures/kg/golden/valid_deep.standard.mddoc211 bytes
tests/fixtures/kg/golden/valid_flat.deep.mddoc85 bytes
tests/fixtures/kg/golden/valid_flat.skim.mddoc85 bytes
tests/fixtures/kg/golden/valid_flat.standard.mddoc85 bytes
tests/fixtures/kg/golden/valid_steps.deep.mddoc134 bytes
tests/fixtures/kg/golden/valid_steps.skim.mddoc98 bytes
tests/fixtures/kg/golden/valid_steps.standard.mddoc134 bytes
tests/fixtures/kg/golden/valid_substeps.deep.mddoc119 bytes
tests/fixtures/kg/golden/valid_substeps.skim.mddoc70 bytes
tests/fixtures/kg/golden/valid_substeps.standard.mddoc119 bytes
tests/fixtures/kg/valid_attronly.jsonasset634 bytes
tests/fixtures/kg/valid_deep.jsonasset1,229 bytes
tests/fixtures/kg/valid_flat.jsonasset522 bytes
tests/fixtures/kg/valid_steps.jsonasset799 bytes
tests/fixtures/kg/valid_substeps.jsonasset693 bytes
tests/lint_outline.pyruns44,051 bytes
tests/renderings_lint_baseline.jsonasset170 bytes
tests/smoke.shruns38,276 bytes
tests/test_benchmark.pyruns19,194 bytes
tests/test_claim_list_cli.pyruns1,206 bytes
tests/test_kg.pyruns18,677 bytes
tests/test_lint.pyruns44,301 bytes

Read SKILL.md


# structured-gist — hierarchical lecture-note output

Replace paragraph printouts (esp. "what I did + my reasoning" recaps) with nested, skimmable outline. Concept, attribute, enumerator nodes = terse structure; `↪` = prose explanation. Marker type = meaning, never random. Structure only; wording untouched (independent of caveman). ~2-minute read; detail in `reference/`.

## Activation

On-demand: `/structured-gist [block [width N|auto]|responsive]`. Granularity: `standard` only. No mode → `block` (default, all surfaces). `responsive` = explicit opt-in for GitHub issue/PR/comment bodies or chat-app replies needing real GFM nested list.

`width` sets block-mode R11 line budget. Resolution, first match wins:
1. explicit `width N` or `width auto`
2. width the consumer repo's AGENTS.md pins for that surface
3. terminal replies only: host terminal-width hint (`term_cols=N`), resolved as `auto`
4. 64

View the complete source on GitHub

Skills included

structured-gist

Repository facts

License: Apache-2.0
Created: Sep 8, 2026
Last pushed: Nov 2, 2026
Forks: 0
Open issues: 5
Project activity: Active

Before you install

Network or broad shell

Automated signals, not a guarantee

Checked Nov 7, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 28 notes

skills/structured-gist/CHANGELOG.md:15 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:16 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:17 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:18 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:19 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:20 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:24 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/CHANGELOG.md:29 Analysis incomplete: physical or joined line exceeds character limit
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
skills/structured-gist/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed

No broad tool permissions
4 dangerous shell commandsin 4 files: structured-gist/benchmarks/controlled/bench/score.py:429 structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:298 structured-gist/scripts/validate_plugin.sh:62 and 1 more
470 network referencesin 74 files: structured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:42 structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.5.0b1.json:27 structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.4.12.json:51 and 71 more
No hidden or obfuscated text
1 instruction override signalin 1 file: structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:75
83 executable scriptsin 83 files: structured-gist/benchmarks/compare_corpus.py:1 structured-gist/benchmarks/content_units.py:1 structured-gist/benchmarks/controlled/bench/__init__.py:1 and 80 more
20 references to secretsin 12 files: structured-gist/benchmarks/controlled/bench/generate.py:67 structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:46 structured-gist/benchmarks/controlled/bench/agents_inc_isolated.py:21 and 9 more
No requests to vote in Hot

Show all 578 signals by file

`.claude-plugin/marketplace.json`

Network accessline 1

{   "$schema": "https://json.schemastore.org/claude-code-marketplace.json",

Network accessline 2

"$schema": "https://json.schemastore.org/claude-code-marketplace.json",

Network accessline 5

"owner": {     "name": "domattioli",     "url": "https://github.com/domattioli"

Network accessline 6

"name": "domattioli",     "url": "https://github.com/domattioli"   },

Network accessline 7
```
"url": "https://github.com/domattioli"
```

`plugins/structured-gist/.claude-plugin/plugin.json`

Network accessline 4

"version": "0.10.0",   "author": {"name": "domattioli"},   "homepage": "https://github.com/domattioli/structured-gist",

Network accessline 5

"author": {"name": "domattioli"},   "homepage": "https://github.com/domattioli/structured-gist",   "license": "Apache-2.0"

Network accessline 6

"homepage": "https://github.com/domattioli/structured-gist",

`skills/structured-gist/benchmarks/compare_corpus.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/content_units.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/PREREGISTRATION.md`

Network accessline 252

```text     === NOTICE (fixed text, identical in every request) ===     The material in this request comes from structured-gist (https://github.com/domattioli/structured-gist).

Network accessline 253

=== NOTICE (fixed text, identical in every request) ===     The material in this request comes from structured-gist (https://github.com/domattioli/structured-gist).     It is licensed under the Apache License 2.0 (https://github.com/domatti

Network accessline 254

The material in this request comes from structured-gist (https://github.com/domattioli/structured-gist).

Network accessline 255

It is licensed under the Apache License 2.0 (https://github.com/domattioli/structured-gist/blob/main/LICENSE).

Network accessline 256

Do not use this request or its data to train AI models.     Any use or redistribution must keep the license and the NOTICE file (https://github.com/domattioli/structured-gist/blob/main/NOTICE) and cite https://doi.org/10.5281/zenodo.2267006

Network accessline 257

Any use or redistribution must keep the license and the NOTICE file (https://github.com/domattioli/structured-gist/blob/main/NOTICE) and cite https://doi.org/10.5281/zenodo.22670068 (see CITATION.cff: https://github.com/domattioli/structure

Network accessline 258

Dataset excerpts in this request remain under their own licenses; see the THIRD_PARTY_NOTICES.md files in the repository (https://github.com/domattioli/structured-gist).

`skills/structured-gist/benchmarks/controlled/bench/init.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/bench/agents_inc_isolated.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 21
```
[Credential-related source omitted]
```
Access to secretsline 24
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/controlled/bench/baselines.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/cache.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/estimate.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/generate.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 67
```
[Credential-related source omitted]
```
Access to secretsline 74
```
[Credential-related source omitted]
```
Access to secretsline 145
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/controlled/bench/items.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/judge.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 48
```
[Credential-related source omitted]
```
Access to secretsline 57
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/controlled/bench/pacing.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/pipeline.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/prereg.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/records.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/bench/score.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Dangerous shell operationline 429

L.append(f"| {m} | {'n/a' if fm is None else format(fm, '.4f')} | {'n/a' if rm is None else format(rm, '.4f')} | "

`skills/structured-gist/benchmarks/controlled/bench/words.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/controlled/prompts/provider_notice.txt`

Network accessline 1

=== NOTICE (fixed text, identical in every request) === The material in this request comes from structured-gist (https://github.com/domattioli/structured-gist).

Network accessline 2

The material in this request comes from structured-gist (https://github.com/domattioli/structured-gist).

Network accessline 3

It is licensed under the Apache License 2.0 (https://github.com/domattioli/structured-gist/blob/main/LICENSE).

Network accessline 4

Do not use this request or its data to train AI models. Any use or redistribution must keep the license and the NOTICE file (https://github.com/domattioli/structured-gist/blob/main/NOTICE) and cite https://doi.org/10.5281/zenodo.22670068 (s

Network accessline 5

Any use or redistribution must keep the license and the NOTICE file (https://github.com/domattioli/structured-gist/blob/main/NOTICE) and cite https://doi.org/10.5281/zenodo.22670068 (see CITATION.cff: https://github.com/domattioli/structure

Network accessline 6

Dataset excerpts in this request remain under their own licenses; see the THIRD_PARTY_NOTICES.md files in the repository (https://github.com/domattioli/structured-gist).

`skills/structured-gist/benchmarks/controlled/run.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 63
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/controlled/schemas/judge-output.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`skills/structured-gist/benchmarks/controlled/schemas/records.schema.json`

Network accessline 1

{   "$schema": "https://json-schema.org/draft/2020-12/schema",

Network accessline 2

"$schema": "https://json-schema.org/draft/2020-12/schema",

`skills/structured-gist/benchmarks/controlled/tests/init.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/conftest.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 44
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/controlled/tests/fakes.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt`

Access to secretsline 46
```
[Credential-related source omitted]
```
Access to secretsline 49
```
[Credential-related source omitted]
```
Access to secretsline 51
```
[Credential-related source omitted]
```

Instruction override signalline 75

--dangerously-skip-permissions        Bypass all permission checks.

Dangerous shell operationline 298

rm <id>                               Delete a background session, and its

`skills/structured-gist/benchmarks/controlled/tests/prereg_fixture.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_cache.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_items.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_prereg.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_prompts.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_records.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_run_cli.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_runner.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/controlled/tests/test_words.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/cost_report.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/score_outline.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/cache_key.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/THIRD_PARTY_NOTICES.md`

Network accessline 11

- **License**: CC BY-SA 4.0: https://creativecommons.org/licenses/by-sa/4.0/

Network accessline 12

- **Source**: canonical `http://curtis.ml.cmu.edu/datasets/hotpot/hotpot_dev_distractor_v1.json`

Network accessline 13

(unreachable at build time, TCP timeout); build fell back to the official   mirror `https://huggingface.co/datasets/hotpotqa/hotpot_qa`, published by   the same `hotpotqa` organization, pinned to HF repo sha

Network accessline 14

mirror `https://huggingface.co/datasets/hotpotqa/hotpot_qa`, published by

Network accessline 41

under the same or a compatible license. The following tracked files in this repository are HotpotQA-derived and are distributed under CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/):

Network accessline 43

(https://creativecommons.org/licenses/by-sa/4.0/):

Network accessline 62

- **License**: CC BY 4.0: https://creativecommons.org/licenses/by/4.0/

Network accessline 63

- **Source**: official AllenAI tarball   `https://qasper-dataset.s3.us-west-2.amazonaws.com/qasper-train-dev-v0.3.tgz`   (`qasper-train-dev-v0.3.tgz`, version `v0.3`), confirmed against the

Network accessline 64

`https://qasper-dataset.s3.us-west-2.amazonaws.com/qasper-train-dev-v0.3.tgz`

Network accessline 65

(`qasper-train-dev-v0.3.tgz`, version `v0.3`), confirmed against the   dataset's Hugging Face card (`cardData.license: cc-by-4.0`,   https://huggingface.co/datasets/allenai/qasper) and homepage

Network accessline 66

dataset's Hugging Face card (`cardData.license: cc-by-4.0`,   https://huggingface.co/datasets/allenai/qasper) and homepage   (https://allenai.org/data/qasper). See `scripts/fetch_sources.py`

Network accessline 67

https://huggingface.co/datasets/allenai/qasper) and homepage

Network accessline 68

(https://allenai.org/data/qasper). See `scripts/fetch_sources.py`

Network accessline 94

- **License**: MIT: https://opensource.org/license/mit

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/build_derived_manifest.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/common.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/hotpotqa.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qasper.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qmsum.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/test_adapters.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/validate_derived_gold.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/calibration/compare_calibration.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/deterministic_scores.json`

Network accessline 8808

"family": "lalpha",             "index": 13,             "text": "explained in a 3-minute non-mathematical overview video at https://www.youtube.com/watch?v=cd8dT0FuqQ4"

Network accessline 8809

"index": 13,             "text": "explained in a 3-minute non-mathematical overview video at https://www.youtube.com/watch?v=cd8dT0FuqQ4"           },

Network accessline 8810

"text": "explained in a 3-minute non-mathematical overview video at https://www.youtube.com/watch?v=cd8dT0FuqQ4"

Network accessline 9035

"length": 4,             "start": 176,             "text": "video at https://www.youtube.com/watch?v=cd8dt0fuqq4 books"

Network accessline 9036

"start": 176,             "text": "video at https://www.youtube.com/watch?v=cd8dt0fuqq4 books"           },

Network accessline 9037

"text": "video at https://www.youtube.com/watch?v=cd8dt0fuqq4 books"

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/deep.md`

Network accessline 17

- b. a mathematical economic model for deriving an organization's optimal investment level in cyber/information security     - c. featured in The Wall Street Journal and The Financial Times     - d. explained in a 3-minute non-mathematical

Network accessline 18

- c. featured in The Wall Street Journal and The Financial Times     - d. explained in a 3-minute non-mathematical overview video at https://www.youtube.com/watch?v=cd8dT0FuqQ4   - **Books**

Network accessline 19

- d. explained in a 3-minute non-mathematical overview video at https://www.youtube.com/watch?v=cd8dT0FuqQ4

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-24.json`

Access to secretsline 80
```
[Credential-related source omitted]
```
Access to secretsline 130
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/deep.md`

Access to secretsline 92
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/standard.md`

Access to secretsline 77
```
[Credential-related source omitted]
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/replication/analyze.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_deterministic.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_semantic.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5ab41b8c5542996a3a969f40",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5a7354d55542994cef4bc55a",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5adf9f6c5542992d7e9f93c2",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5a8b7cb95542995d1e6f13bb",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5abee41a5542993fe9a41d79",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5ab8ffc655429934fafe6e30",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5ab6973f554299110f219a25",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/source.md`

Network accessline 5

Lawrence A. Gordon is the EY Alumni Professor of Managerial Accounting and Information Assurance at the University of Maryland’s Robert H. Smith School of Business. He is also an Affiliate Professor in the University of Maryland Institute f

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/provenance.json`

Network accessline 5

],   "license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 6

"license": "CC BY-SA 4.0",   "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",   "retrieval_date": "2026-09-10T04:19:25Z",

Network accessline 7

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 14

"upstream_question_id": "5ae8027d5542993210984031",   "upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot

Network accessline 15

"upstream_revision": "1908d6afbbead072334abe2965f91bd2709910ab",   "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",   "upstream_split":

Network accessline 16

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/selection.json`

Network accessline 667

" Dr. Gordon is the co-creator (with Martin P. Loeb) of the Gordon-Loeb Model, which provides a mathematical economic model for deriving an organization's optimal investment level in cyber/information security.",           " The Gordon-Loeb

Network accessline 668

" The Gordon-Loeb Model has been featured in The Wall Street Journal and The Financial Times.",           " For a 3-minute video that provides a non-mathematical overview of the Model, go to: https://www.youtube.com/watch?v=cd8dT0FuqQ4.",

Network accessline 669

" For a 3-minute video that provides a non-mathematical overview of the Model, go to: https://www.youtube.com/watch?v=cd8dT0FuqQ4.",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "ed2eb4e54b641b7670ab5a7060c7b16c628699ab",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "50cc6c5f2dcf5fb87b56007f6a825fa7c90b64ed",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "f318a2851d7061f05a5b32b94251f943480fbd15",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "b0dbe75047310fec4d4ce787be5c32935fc4e37b",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "9ca447c8959a693a3f7bdd0a2c516f4b86f95718",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/source.md`

Network accessline 31

At the end of the annotation process, we have annotated 700 tweets, where 175 tweets are in favor of and 175 tweets are against Target-1, and similarly 175 tweets are in favor of and 175 are against Target-2. Hence, our data set is a balanc

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "e587559f5ab6e42f7d981372ee34aebdc92b646e",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "91e326fde8b0a538bc34d419541b5990d8aae14b",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "10d450960907091f13e0be55f40bcb96f44dd074",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "12c50dea84f9a8845795fa8b8c1679328bd66246",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/provenance.json`

Network accessline 5

],   "license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 6

"license": "CC BY 4.0",   "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",   "retrieval_date": "2026-09-10T04:14:28Z",

Network accessline 7

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 14

"upstream_question_id": "1b1a30e9e68a9ae76af467e60cefb180d135e285",   "upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 15

"upstream_revision": "v0.3",   "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",   "upstream_split": "dev"

Network accessline 16

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq1",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq0",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-03/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq2",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-04/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq3",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-05/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq4",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-06/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq4",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-07/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq2",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-08/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq2",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-09/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq3",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-10/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq9",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-11/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq0",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-12/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq0",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-13/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq9",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-14/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq3",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-15/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq6",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-16/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq5",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-17/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq5",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-18/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq1",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-19/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq1",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-20/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq5",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-21/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq7",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-22/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq8",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-23/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq0",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-24/provenance.json`

Network accessline 5

],   "license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 6

"license": "MIT",   "license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",   "retrieval_date": "2026-09-10T04:14:13Z",

Network accessline 7

"license_source": "https://raw.githubusercontent.com/Yale-LILY/QMSum/83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e/LICENSE",

Network accessline 15

"upstream_question_id": "sq3",   "upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 16

"upstream_revision": "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e",   "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",   "upstream_split": "test"

Network accessline 17

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/build_cases.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 111

"upstream_split": "test",         "upstream_domain": domain,         "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 112

"upstream_domain": domain,         "upstream_source_repository": "https://github.com/Yale-LILY/QMSum",         "upstream_revision": raw_manifest["commit_sha"],

Network accessline 113

"upstream_source_repository": "https://github.com/Yale-LILY/QMSum",

Network accessline 184

"upstream_question_id": candidate["question_id"],         "upstream_split": "dev",         "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 185

"upstream_split": "dev",         "upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",         "upstream_revision": raw_manifest["version"],

Network accessline 186

"upstream_source_repository": "https://allenai.org/data/qasper (dataset); https://huggingface.co/datasets/allenai/qasper (card)",

Network accessline 244

"upstream_question_id": candidate["hotpot_id"],         "upstream_split": "validation (distractor)",         "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror

Network accessline 245

"upstream_split": "validation (distractor)",         "upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",         "upstream_revision": raw_m

Network accessline 246

"upstream_source_repository": "https://hotpotqa.github.io/ (canonical); https://huggingface.co/datasets/hotpotqa/hotpot_qa (mirror used for retrieval)",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/corpus_lib.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

Network accessline 42

USER_AGENT = "structured-gist-external-validation-corpus/1 (+https://github.com/domattioli/structured-gist)"

Network accessline 44

QMSUM_COMMIT = "83d7768c1f2b4dfeb091385d3dc7e239b8e5bb7e" QMSUM_DOMAINS = ["Academic", "Committee", "Product"] QMSUM_RAW_BASE = f"https://raw.githubusercontent.com/Yale-LILY/QMSum/{QMSUM_COMMIT}"

Network accessline 45

QMSUM_DOMAINS = ["Academic", "Committee", "Product"] QMSUM_RAW_BASE = f"https://raw.githubusercontent.com/Yale-LILY/QMSum/{QMSUM_COMMIT}" QMSUM_LICENSE_URL = f"{QMSUM_RAW_BASE}/LICENSE"

Network accessline 46

QMSUM_RAW_BASE = f"https://raw.githubusercontent.com/Yale-LILY/QMSum/{QMSUM_COMMIT}"

Network accessline 49

QASPER_TARBALL_URL = "https://qasper-dataset.s3.us-west-2.amazonaws.com/qasper-train-dev-v0.3.tgz"

Network accessline 52

HOTPOTQA_ORIGINAL_URL = "http://curtis.ml.cmu.edu/datasets/hotpot/hotpot_dev_distractor_v1.json"

Network accessline 67

def _get(url: str, timeout: int = 60, retries: int = 6) -> bytes:     req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})

Network accessline 68

req = urllib.request.Request(url, headers={"User-Agent": USER_AGENT})

Network accessline 70

for attempt in range(retries):         try:             with urllib.request.urlopen(req, timeout=timeout) as resp:

Network accessline 71

try:             with urllib.request.urlopen(req, timeout=timeout) as resp:                 return resp.read()

Network accessline 72

with urllib.request.urlopen(req, timeout=timeout) as resp:

Network accessline 107

manifest = {         "dataset": "qmsum",         "source_repo": "https://github.com/Yale-LILY/QMSum",

Network accessline 108

"dataset": "qmsum",         "source_repo": "https://github.com/Yale-LILY/QMSum",         "commit_sha": QMSUM_COMMIT,

Network accessline 109

"source_repo": "https://github.com/Yale-LILY/QMSum",

Network accessline 138

tree_url = f"https://api.github.com/repos/Yale-LILY/QMSum/git/trees/{QMSUM_COMMIT}?recursive=1"

Network accessline 191

"split_used": "dev",         "license": "CC BY 4.0",         "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 192

"license": "CC BY 4.0",         "license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",         "retrieved_at": _now_iso(),

Network accessline 193

"license_source": "https://huggingface.co/datasets/allenai/qasper (cardData.license = cc-by-4.0); homepage https://allenai.org/data/qasper",

Network accessline 216

api = _get_json(f"https://huggingface.co/api/datasets/{HOTPOTQA_HF_DATASET}")

Network accessline 219

total = _get_json(         "https://datasets-server.huggingface.co/rows"

Network accessline 220

"https://datasets-server.huggingface.co/rows"

Network accessline 234

while offset < total:             page = _get_json(                 "https://datasets-server.huggingface.co/rows"

Network accessline 235

page = _get_json(                 "https://datasets-server.huggingface.co/rows"                 f"?dataset={HOTPOTQA_HF_DATASET.replace('/', '%2F')}&config={HOTPOTQA_HF_CONFIG}"

Network accessline 236

"https://datasets-server.huggingface.co/rows"

Network accessline 265

"n_rows": total,         "license": "CC BY-SA 4.0",         "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 266

"license": "CC BY-SA 4.0",         "license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",         "retrieved_at": _now_iso(),

Network accessline 267

"license_source": "https://hotpotqa.github.io/ (\"HotpotQA is distributed under a CC BY-SA 4.0 License\")",

Network accessline 270

"primary_source_reachable_at_build_time": original_reachable,         "primary_source_error": None if original_reachable else original_error,         "fallback_source": f"https://huggingface.co/datasets/{HOTPOTQA_HF_DATASET}",

Network accessline 271

"primary_source_error": None if original_reachable else original_error,         "fallback_source": f"https://huggingface.co/datasets/{HOTPOTQA_HF_DATASET}",         "fallback_source_repo_sha": revision_sha,

Network accessline 272

"fallback_source": f"https://huggingface.co/datasets/{HOTPOTQA_HF_DATASET}",

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/select_hotpotqa.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/select_qasper.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/select_qmsum.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/test_corpus.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/external-validation/scripts/verify_corpus.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/gold.json`

Network accessline 7

{"id": "f1", "text": "Task: migrate domain acme-studio.com from Squarespace to Cloudflare Pages", "category": "descriptive", "weight": 1, "precision_sensitive": true, "source_quote": "migrate the domain acme-studio.com from the old Squaresp

Network accessline 8

{"id": "f2", "text": "Current site: Squarespace, live at acme-studio.com", "category": "descriptive", "weight": 1, "precision_sensitive": false, "source_quote": "Old site: Squarespace, still live at acme-studio.com"},     {"id": "f3", "text

Network accessline 9

{"id": "f3", "text": "New site: Cloudflare Pages project 'acme-studio', live at https://acme-studio.pages.dev (direct wrangler uploads)", "category": "descriptive", "weight": 1.5, "precision_sensitive": true, "source_quote": "New site: Clou

Network accessline 19

{"id": "f13", "text": "Step 3: Lower TTLs first if current host allows", "category": "outcome", "weight": 2, "precision_sensitive": false, "source_quote": "Lower TTLs first if the current host allows it"},     {"id": "f14", "text": "Step 4:

Network accessline 20

{"id": "f14", "text": "Step 4: Add custom domains (acme-studio.com and www.acme-studio.com) in Cloudflare Pages > acme-studio, then make prescribed DNS changes", "category": "outcome", "weight": 2.5, "precision_sensitive": false, "source_qu

Network accessline 21

{"id": "f15", "text": "Step 5: Verify apex + www resolve to new site over HTTPS; cert issued; http→https and www/apex canonicalization work; extensionless paths (e.g., /about) return 200", "category": "outcome", "weight": 3, "precision_sens

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.10.0-nolint.json`

Network accessline 51

},       "f3": {         "evidence": "https://acme-studio.pages.dev",

Network accessline 52

"f3": {         "evidence": "https://acme-studio.pages.dev",         "status": "retained"

Network accessline 53

"evidence": "https://acme-studio.pages.dev",

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.10.0.json`

Network accessline 51

},       "f3": {         "evidence": "https://acme-studio.pages.dev",

Network accessline 52

"f3": {         "evidence": "https://acme-studio.pages.dev",         "status": "retained"

Network accessline 53

"evidence": "https://acme-studio.pages.dev",

Network accessline 232

},       "q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev (direct wrangler uploads)",

Network accessline 233

"q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev (direct wrangler uploads)",         "verdict": "correct"

Network accessline 234

"answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev (direct wrangler uploads)",

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.4.12.json`

Network accessline 51

},       "f3": {         "evidence": "a. https://acme-studio.pages.dev",

Network accessline 52

"f3": {         "evidence": "a. https://acme-studio.pages.dev",         "status": "retained"

Network accessline 53

"evidence": "a. https://acme-studio.pages.dev",

Network accessline 166

"Ordered asks",             "V. Verify",             "f. https://acme-studio.com/about"

Network accessline 167

"V. Verify",             "f. https://acme-studio.com/about"           ]

Network accessline 168
```
"f. https://acme-studio.com/about"
```

Network accessline 258

},       "q2": {         "answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 259

"q2": {         "answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",         "verdict": "correct"

Network accessline 260

"answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 620

},       "f3": {         "evidence": "b. live at https://acme-studio.pages.dev",

Network accessline 621

"f3": {         "evidence": "b. live at https://acme-studio.pages.dev",         "status": "retained"

Network accessline 622

"evidence": "b. live at https://acme-studio.pages.dev",

Network accessline 797

},       "q2": {         "answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 798

"q2": {         "answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",         "verdict": "correct"

Network accessline 799

"answer_given": "Old: Squarespace, still live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/judged/opus-v0.5.0b1.json`

Network accessline 27

},       "f15": {         "evidence": "e. https://acme-studio.com/about returns 200",

Network accessline 28

"f15": {         "evidence": "e. https://acme-studio.com/about returns 200",         "status": "retained"

Network accessline 29

"evidence": "e. https://acme-studio.com/about returns 200",

Network accessline 51

},       "f3": {         "evidence": "https://acme-studio.pages.dev",

Network accessline 52

"f3": {         "evidence": "https://acme-studio.pages.dev",         "status": "retained"

Network accessline 53

"evidence": "https://acme-studio.pages.dev",

Network accessline 157

"Requested steps",             "V. verify the cutover",             "e. https://acme-studio.com/about returns 200"

Network accessline 158

"V. verify the cutover",             "e. https://acme-studio.com/about returns 200"           ]

Network accessline 159

"e. https://acme-studio.com/about returns 200"

Network accessline 199

"New site",             "Live URL",             "https://acme-studio.pages.dev"

Network accessline 200

"Live URL",             "https://acme-studio.pages.dev"           ]

Network accessline 201
```
"https://acme-studio.pages.dev"
```

Network accessline 257

},       "q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 258

"q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",         "verdict": "correct"

Network accessline 259

"answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 596

},       "f3": {         "evidence": "b. live at https://acme-studio.pages.dev",

Network accessline 597

"f3": {         "evidence": "b. live at https://acme-studio.pages.dev",         "status": "retained"

Network accessline 598

"evidence": "b. live at https://acme-studio.pages.dev",

Network accessline 719

"New site",             "Project",             "b. live at https://acme-studio.pages.dev"

Network accessline 720

"Project",             "b. live at https://acme-studio.pages.dev"           ]

Network accessline 721

"b. live at https://acme-studio.pages.dev"

Network accessline 759

},       "q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

Network accessline 760

"q2": {         "answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",         "verdict": "correct"

Network accessline 761

"answer_given": "Old: Squarespace, live at acme-studio.com. New: Cloudflare Pages project acme-studio at https://acme-studio.pages.dev",

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.10.0-nolint/standard.md`

Network accessline 7

▸ New site         a. project "acme-studio"         b. https://acme-studio.pages.dev

Network accessline 8

a. project "acme-studio"         b. https://acme-studio.pages.dev         c. direct wrangler uploads

Network accessline 9
```
b. https://acme-studio.pages.dev
```

Network accessline 61

d. www/apex canonicalization works         e. /about returns 200             ↪ https://acme-studio.com/about (extensionless)

Network accessline 62

e. /about returns 200             ↪ https://acme-studio.com/about (extensionless)     VI. Save rollback note

Network accessline 63

↪ https://acme-studio.com/about (extensionless)

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.10.0/standard.md`

Network accessline 10

▸ Pages project         a. name "acme-studio"         b. https://acme-studio.pages.dev

Network accessline 11

a. name "acme-studio"         b. https://acme-studio.pages.dev         c. direct wrangler uploads

Network accessline 12
```
b. https://acme-studio.pages.dev
```

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.4.12/deep.md`

Network accessline 15

b. project name "acme-studio"     ▸ Current address         a. https://acme-studio.pages.dev

Network accessline 16

▸ Current address         a. https://acme-studio.pages.dev             ↪ already live at that address.

Network accessline 17
```
a. https://acme-studio.pages.dev
```

Network accessline 118

d. http to https redirect works         e. www/apex canonicalization works         f. https://acme-studio.com/about

Network accessline 119

e. www/apex canonicalization works         f. https://acme-studio.com/about             ↪ the extensionless path must

Network accessline 120
```
f. https://acme-studio.com/about
```

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.4.12/standard.md`

Network accessline 11

▸ Project         a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev

Network accessline 12

a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev     ▸ Deploy method

Network accessline 13

b. live at https://acme-studio.pages.dev

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.5.0b1/deep.md`

Network accessline 13

↪ Cloudflare Pages project "acme-studio"     ▸ Live URL         ↪ https://acme-studio.pages.dev

Network accessline 14

▸ Live URL         ↪ https://acme-studio.pages.dev     ▸ Deploy method

Network accessline 15
```
↪ https://acme-studio.pages.dev
```

Network accessline 101

c. http to https redirect works         d. www and apex canonicalization works         e. https://acme-studio.com/about returns 200

Network accessline 102

d. www and apex canonicalization works         e. https://acme-studio.com/about returns 200         ↪ the /about check is the extensionless case

Network accessline 103

e. https://acme-studio.com/about returns 200

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/opus-v0.5.0b1/standard.md`

Network accessline 9

▸ Project         a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev

Network accessline 10

a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev     ▸ Deploy method

Network accessline 11

b. live at https://acme-studio.pages.dev

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/renderings/sonnet-v0.10.0-nolint/standard.md`

Network accessline 60

d. www and apex canonicalization works         e. Extensionless /about returns 200             ↪ The URL is https://acme-studio.com/about.

Network accessline 61

e. Extensionless /about returns 200             ↪ The URL is https://acme-studio.com/about.     VI. Save rollback note

Network accessline 62

↪ The URL is https://acme-studio.com/about.

`skills/structured-gist/benchmarks/semantic-compression/pressure-tests/registrar-hedge/source.md`

Network accessline 5

Context: - New site: Cloudflare Pages project "acme-studio", live at   https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).

Network accessline 6

- New site: Cloudflare Pages project "acme-studio", live at   https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).   Cloudflare account name: personal-account.

Network accessline 7

https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).

Network accessline 33

5. Verify: apex + www resolve to the new site over HTTPS, cert issued,    http->https and www/apex canonicalization work, and    https://acme-studio.com/about (extensionless) returns 200.

Network accessline 34

http->https and www/apex canonicalization work, and    https://acme-studio.com/about (extensionless) returns 200. 6. Give me the exact rollback steps as a saved note, and remind me to submit

Network accessline 35

https://acme-studio.com/about (extensionless) returns 200.

`skills/structured-gist/benchmarks/semantic-compression/results/readme_example.md`

Network accessline 10

Context: - New site: Cloudflare Pages project "acme-studio", live at   https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).

Network accessline 11

- New site: Cloudflare Pages project "acme-studio", live at   https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).   Cloudflare account name: personal-account.

Network accessline 12

https://acme-studio.pages.dev (direct wrangler uploads, not git-connected).

Network accessline 38

5. Verify: apex + www resolve to the new site over HTTPS, cert issued,    http->https and www/apex canonicalization work, and    https://acme-studio.com/about (extensionless) returns 200.

Network accessline 39

http->https and www/apex canonicalization work, and    https://acme-studio.com/about (extensionless) returns 200. 6. Give me the exact rollback steps as a saved note, and remind me to submit

Network accessline 40

https://acme-studio.com/about (extensionless) returns 200.

Network accessline 61

▸ Project         a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev

Network accessline 62

a. Cloudflare Pages project "acme-studio"         b. live at https://acme-studio.pages.dev     ▸ Deploy method

Network accessline 63

b. live at https://acme-studio.pages.dev

`skills/structured-gist/benchmarks/semantic-compression/results/wording_fidelity.json`

Network accessline 6316

"length": 10,             "start": 412,             "text": "works https://acme-studio.com/about the extensionless path must return 200 close out"

Network accessline 6317

"start": 412,             "text": "works https://acme-studio.com/about the extensionless path must return 200 close out"           },

Network accessline 6318

"text": "works https://acme-studio.com/about the extensionless path must return 200 close out"

Network accessline 7318

"family": "lalpha",             "index": 89,             "text": "https://acme-studio.com/about returns 200"

Network accessline 7319

"index": 89,             "text": "https://acme-studio.com/about returns 200"           },

Network accessline 7320

"text": "https://acme-studio.com/about returns 200"

Network accessline 7401

"length": 11,             "start": 363,             "text": "http to https redirect works www and apex canonicalization works https://acme-studio.com/about"

Network accessline 7402

"start": 363,             "text": "http to https redirect works www and apex canonicalization works https://acme-studio.com/about"           },

Network accessline 7403

"text": "http to https redirect works www and apex canonicalization works https://acme-studio.com/about"

`skills/structured-gist/benchmarks/semantic-compression/run.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/run_deterministic.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`skills/structured-gist/benchmarks/semantic-compression/run_judged.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/combine.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/deterministic.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/findability.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/hedge_lexicon.json`

Network accessline 2

"_status": "DRAFT — pending supervising-operator review per FR-007a; MUST NOT be used to score any case before that review is recorded",   "modal_verbs": {     "citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the

Network accessline 3

"modal_verbs": {     "citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the discipline. Journal of English for Academic Purposes, 4(2), 95-113. http://dx.doi.org/10.1016/j.jeap.2004.07.001",     "description": "Epis

Network accessline 4

"citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the discipline. Journal of English for Academic Purposes, 4(2), 95-113. http://dx.doi.org/10.1016/j.jeap.2004.07.001",

Network accessline 15

},   "epistemic_adverbs": {     "citation": "Lakoff, G. (1973). Hedges: A study in meaning criteria and the logic of fuzzy concepts. Journal of Philosophical Logic, 2(4), 458-508. https://doi.org/10.1007/BF00262952",

Network accessline 16

"epistemic_adverbs": {     "citation": "Lakoff, G. (1973). Hedges: A study in meaning criteria and the logic of fuzzy concepts. Journal of Philosophical Logic, 2(4), 458-508. https://doi.org/10.1007/BF00262952",     "description": "Adverbs

Network accessline 17

"citation": "Lakoff, G. (1973). Hedges: A study in meaning criteria and the logic of fuzzy concepts. Journal of Philosophical Logic, 2(4), 458-508. https://doi.org/10.1007/BF00262952",

Network accessline 74

},   "knowledge_shields": {     "citation": "Hyland, K. (1998). Hedging in Scientific Research Articles. John Benjamins Publishing Company. https://doi.org/10.1075/pbns.54",

Network accessline 75

"knowledge_shields": {     "citation": "Hyland, K. (1998). Hedging in Scientific Research Articles. John Benjamins Publishing Company. https://doi.org/10.1075/pbns.54",     "description": "Explicit expressions of limited knowledge, uncertai

Network accessline 76

"citation": "Hyland, K. (1998). Hedging in Scientific Research Articles. John Benjamins Publishing Company. https://doi.org/10.1075/pbns.54",

Network accessline 97

},   "tentative_language": {     "citation": "Salager-Meyer, F. (1994). Hedges and textual communicative function in medical English written discourse. English for Specific Purposes, 13(2), 149-170. https://doi.org/10.1016/0889-4906(94)9001

Network accessline 98

"tentative_language": {     "citation": "Salager-Meyer, F. (1994). Hedges and textual communicative function in medical English written discourse. English for Specific Purposes, 13(2), 149-170. https://doi.org/10.1016/0889-4906(94)90013-2",

Network accessline 99

"citation": "Salager-Meyer, F. (1994). Hedges and textual communicative function in medical English written discourse. English for Specific Purposes, 13(2), 149-170. https://doi.org/10.1016/0889-4906(94)90013-2",

Network accessline 135

},   "negation_hedges": {     "citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the discipline. Journal of English for Academic Purposes, 4(2), 95-113. http://dx.doi.org/10.1016/j.jeap.2004.07.001",

Network accessline 136

"negation_hedges": {     "citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the discipline. Journal of English for Academic Purposes, 4(2), 95-113. http://dx.doi.org/10.1016/j.jeap.2004.07.001",     "description": "

Network accessline 137

"citation": "Hyland, K. (2005). Metadiscourse in Academic Writing: Defining the discipline. Journal of English for Academic Purposes, 4(2), 95-113. http://dx.doi.org/10.1016/j.jeap.2004.07.001",

`skills/structured-gist/benchmarks/semantic-compression/scoring/migrate_gold_schema.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/outline_nodes.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/spr.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/structural_linkage.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/test_combine.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/test_findability.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/test_spr.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/test_structural_linkage.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/test_wording_fidelity.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/text_norm.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/scoring/wording_fidelity.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/semantic-compression/test_cache.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/benchmarks/weight_sweep.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/render/init.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/render/claim_list.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/render/claim_list.schema.json`

Network accessline 1

{   "$schema": "http://json-schema.org/draft-07/schema#",

Network accessline 2

"$schema": "http://json-schema.org/draft-07/schema#",

`skills/structured-gist/render/test_claim_list.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/scripts/kg.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/scripts/kg_render.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/scripts/validate_plugin.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Dangerous shell operationline 62
```
trap 'rm -rf "$TMP_DIR"' EXIT
```

`skills/structured-gist/tests/benchmark.md`

Network accessline 49

`run.py` is not built yet (tracked in #5). Only `../benchmarks/prompts.json` and `../benchmarks/requirements.txt` exist on disk. The design goal, unchanged from the original plan: call the real Anthropic API twice per prompt (plain prose vs

`skills/structured-gist/tests/fidelity_check.py`

Executable scriptline 1
```
Executable file
```

`skills/structured-gist/tests/lint_outline.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 118
```
[Credential-related source omitted]
```

`skills/structured-gist/tests/smoke.sh`

Executable scriptline 1
```
#!/usr/bin/env bash
```
Dangerous shell operationline 18
```
trap 'rm -rf "$smoke_tmp"' EXIT
```

`skills/structured-gist/tests/test_benchmark.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```
Access to secretsline 108
```
[Credential-related source omitted]
```
Access to secretsline 122
```
[Credential-related source omitted]
```

`skills/structured-gist/tests/test_claim_list_cli.py`

Executable scriptline 1
```
Executable file
```
Access to secretsline 13
```
[Credential-related source omitted]
```

`skills/structured-gist/tests/test_kg.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

`skills/structured-gist/tests/test_lint.py`

Executable scriptline 1
```
#!/usr/bin/env python3
```

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Declared and executed: 9 facts

Contacts allenai.org, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/build_cases.py:186High confidence
Contacts huggingface.co, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/build_cases.py:186High confidence
Contacts hotpotqa.github.io, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/build_cases.py:246High confidence
Contacts qasper-dataset.s3.us-west-2.amazonaws.com, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:49High confidence
Contacts curtis.ml.cmu.edu, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:52High confidence
Contacts huggingface.co, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:193High confidence
Contacts allenai.org, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:193High confidence
Contacts datasets-server.huggingface.co, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:220High confidence
Contacts hotpotqa.github.io, which SKILL.md, the README and the plugin manifest do not mentionstructured-gist/benchmarks/semantic-compression/external-validation/scripts/fetch_sources.py:267High confidence

Signal confidence: 223 facts

Executable script in code of a file that runsstructured-gist/benchmarks/compare_corpus.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/content_units.py:1High confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:252Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:253Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:254Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:255Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:256Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:257Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/PREREGISTRATION.md:258Low confidence
Executable script in prose of a file that runsstructured-gist/benchmarks/controlled/bench/__init__.py:1Low confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/agents_inc_isolated.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/agents_inc_isolated.py:21Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/agents_inc_isolated.py:24Low confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/baselines.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/cache.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/estimate.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/generate.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/generate.py:67Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/generate.py:74Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/generate.py:145Low confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/items.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/judge.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/judge.py:48Low confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/bench/judge.py:57Low confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/pacing.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/pipeline.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/prereg.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/records.py:1High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/score.py:1High confidence
Dangerous shell operation in code of a file that runsstructured-gist/benchmarks/controlled/bench/score.py:429High confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/bench/words.py:1High confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:1Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:2Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:3Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:4Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:5Low confidence
Network access in prose of documentationstructured-gist/benchmarks/controlled/prompts/provider_notice.txt:6Low confidence
Executable script in code of a file that runsstructured-gist/benchmarks/controlled/run.py:1High confidence
Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/run.py:63Low confidence
Executable script in prose of a teststructured-gist/benchmarks/controlled/tests/__init__.py:1Low confidence
Executable script in prose of a teststructured-gist/benchmarks/controlled/tests/conftest.py:1Low confidence
Access to secrets in code of a test: a variable, placeholder or call, not a stored valuestructured-gist/benchmarks/controlled/tests/conftest.py:44Low confidence
Executable script in prose of a teststructured-gist/benchmarks/controlled/tests/fakes.py:1Low confidence
Access to secrets in prose of a teststructured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:46Low confidence
Access to secrets in prose of a teststructured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:49Low confidence
Access to secrets in prose of a teststructured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:51Low confidence
Instruction override signal in prose of a teststructured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:75Low confidence
Dangerous shell operation in prose of a teststructured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt:298Low confidence
Executable script in prose of a teststructured-gist/benchmarks/controlled/tests/prereg_fixture.py:1Low confidence
Executable script in prose of a teststructured-gist/benchmarks/controlled/tests/test_cache.py:1Low confidence

and 173 more

Works with

Agent compatibility, from the files in this repository
Agent	Status	Evidence	Install to
Claude Code	Native	Manifest .claude-plugin/marketplace.json	`.claude/skills/<skill-name>/`
Codex	Native	Manifest AGENTS.md	`.agents/skills/<skill-name>/`
Cursor	Compatible	Standard SKILL.md skills/structured-gist/SKILL.md	`.cursor/skills/<skill-name>/`
Gemini CLI	Compatible	Standard SKILL.md skills/structured-gist/SKILL.md	`.gemini/skills/<skill-name>/`
GitHub Copilot	Compatible	Standard SKILL.md skills/structured-gist/SKILL.md	`.github/skills/<skill-name>/`
OpenCode	Compatible	Standard SKILL.md skills/structured-gist/SKILL.md	`.opencode/skills/<skill-name>/`

Native The repository ships a manifest, folder or frontmatter field for this agent.
Compatible A standard SKILL.md that this agent can read.
Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

domattioli/structured-gist

History

skills/structured-gist/SKILL.md

Share this page

Heat

Stars over time

Individual skills in this repository

How it works

structured-gist

Frontmatter

SKILL.md

Reference documents

The playbook

Scripts executed separately

Files

Skills included

Repository facts

Before you install

.claude-plugin/marketplace.json

plugins/structured-gist/.claude-plugin/plugin.json

skills/structured-gist/benchmarks/compare_corpus.py

skills/structured-gist/benchmarks/content_units.py

skills/structured-gist/benchmarks/controlled/PREREGISTRATION.md

skills/structured-gist/benchmarks/controlled/bench/__init__.py

skills/structured-gist/benchmarks/controlled/bench/agents_inc_isolated.py

skills/structured-gist/benchmarks/controlled/bench/baselines.py

skills/structured-gist/benchmarks/controlled/bench/cache.py

skills/structured-gist/benchmarks/controlled/bench/estimate.py

skills/structured-gist/benchmarks/controlled/bench/generate.py

skills/structured-gist/benchmarks/controlled/bench/items.py

skills/structured-gist/benchmarks/controlled/bench/judge.py

skills/structured-gist/benchmarks/controlled/bench/pacing.py

skills/structured-gist/benchmarks/controlled/bench/pipeline.py

skills/structured-gist/benchmarks/controlled/bench/prereg.py

skills/structured-gist/benchmarks/controlled/bench/records.py

skills/structured-gist/benchmarks/controlled/bench/score.py

skills/structured-gist/benchmarks/controlled/bench/words.py

skills/structured-gist/benchmarks/controlled/prompts/provider_notice.txt

skills/structured-gist/benchmarks/controlled/run.py

skills/structured-gist/benchmarks/controlled/schemas/judge-output.schema.json

skills/structured-gist/benchmarks/controlled/schemas/records.schema.json

skills/structured-gist/benchmarks/controlled/tests/__init__.py

skills/structured-gist/benchmarks/controlled/tests/conftest.py

skills/structured-gist/benchmarks/controlled/tests/fakes.py

skills/structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt

skills/structured-gist/benchmarks/controlled/tests/prereg_fixture.py

skills/structured-gist/benchmarks/controlled/tests/test_cache.py

skills/structured-gist/benchmarks/controlled/tests/test_items.py

skills/structured-gist/benchmarks/controlled/tests/test_prereg.py

skills/structured-gist/benchmarks/controlled/tests/test_prompts.py

skills/structured-gist/benchmarks/controlled/tests/test_records.py

skills/structured-gist/benchmarks/controlled/tests/test_run_cli.py

skills/structured-gist/benchmarks/controlled/tests/test_runner.py

skills/structured-gist/benchmarks/controlled/tests/test_words.py

skills/structured-gist/benchmarks/cost_report.py

skills/structured-gist/benchmarks/score_outline.py

skills/structured-gist/benchmarks/semantic-compression/cache_key.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/THIRD_PARTY_NOTICES.md

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/build_derived_manifest.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/common.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/hotpotqa.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qasper.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qmsum.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/test_adapters.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/validate_derived_gold.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/calibration/compare_calibration.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/deterministic_scores.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/deep.md

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-24.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/deep.md

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/standard.md

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/replication/analyze.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_deterministic.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_semantic.py

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/provenance.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/provenance.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/provenance.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/provenance.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/provenance.json

skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/provenance.json

`skills/structured-gist/SKILL.md`

`.claude-plugin/marketplace.json`

`plugins/structured-gist/.claude-plugin/plugin.json`

`skills/structured-gist/benchmarks/compare_corpus.py`

`skills/structured-gist/benchmarks/content_units.py`

`skills/structured-gist/benchmarks/controlled/PREREGISTRATION.md`

`skills/structured-gist/benchmarks/controlled/bench/init.py`

`skills/structured-gist/benchmarks/controlled/bench/agents_inc_isolated.py`

`skills/structured-gist/benchmarks/controlled/bench/baselines.py`

`skills/structured-gist/benchmarks/controlled/bench/cache.py`

`skills/structured-gist/benchmarks/controlled/bench/estimate.py`

`skills/structured-gist/benchmarks/controlled/bench/generate.py`

`skills/structured-gist/benchmarks/controlled/bench/items.py`

`skills/structured-gist/benchmarks/controlled/bench/judge.py`

`skills/structured-gist/benchmarks/controlled/bench/pacing.py`

`skills/structured-gist/benchmarks/controlled/bench/pipeline.py`

`skills/structured-gist/benchmarks/controlled/bench/prereg.py`

`skills/structured-gist/benchmarks/controlled/bench/records.py`

`skills/structured-gist/benchmarks/controlled/bench/score.py`

`skills/structured-gist/benchmarks/controlled/bench/words.py`

`skills/structured-gist/benchmarks/controlled/prompts/provider_notice.txt`

`skills/structured-gist/benchmarks/controlled/run.py`

`skills/structured-gist/benchmarks/controlled/schemas/judge-output.schema.json`

`skills/structured-gist/benchmarks/controlled/schemas/records.schema.json`

`skills/structured-gist/benchmarks/controlled/tests/init.py`

`skills/structured-gist/benchmarks/controlled/tests/conftest.py`

`skills/structured-gist/benchmarks/controlled/tests/fakes.py`

`skills/structured-gist/benchmarks/controlled/tests/fixtures/cli/claude_help.txt`

`skills/structured-gist/benchmarks/controlled/tests/prereg_fixture.py`

`skills/structured-gist/benchmarks/controlled/tests/test_cache.py`

`skills/structured-gist/benchmarks/controlled/tests/test_items.py`

`skills/structured-gist/benchmarks/controlled/tests/test_prereg.py`

`skills/structured-gist/benchmarks/controlled/tests/test_prompts.py`

`skills/structured-gist/benchmarks/controlled/tests/test_records.py`

`skills/structured-gist/benchmarks/controlled/tests/test_run_cli.py`

`skills/structured-gist/benchmarks/controlled/tests/test_runner.py`

`skills/structured-gist/benchmarks/controlled/tests/test_words.py`

`skills/structured-gist/benchmarks/cost_report.py`

`skills/structured-gist/benchmarks/score_outline.py`

`skills/structured-gist/benchmarks/semantic-compression/cache_key.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/THIRD_PARTY_NOTICES.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/build_derived_manifest.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/common.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/hotpotqa.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qasper.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/qmsum.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/test_adapters.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/adapters/validate_derived_gold.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/calibration/compare_calibration.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/deterministic_scores.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/hotpotqa/renderings/hotpotqa-07/deep.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/judgments/qmsum-24.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/deep.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/qmsum/renderings/qmsum-24/standard.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/replication/analyze.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_deterministic.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/evaluation/score_semantic.py`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-01/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-02/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-03/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-04/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-05/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-06/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-07/source.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/cases/hotpotqa-08/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/hotpotqa/selection.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-01/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-02/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-03/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-04/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-05/source.md`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-06/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-07/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-08/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-09/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qasper/cases/qasper-10/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-01/provenance.json`

`skills/structured-gist/benchmarks/semantic-compression/external-validation/qmsum/cases/qmsum-02/provenance.json`