Individual skill
ecai-experiments
Use when designing or auditing the evidence in an ECAI paper — choosing proof versus experiment by claim shape across ECAI's breadth (theory/KR, planning/search, ML, multi-agent, applied), fair baselines, seeds and spread, honest ablations, and provenance, all supporting a claim inside a 7-page body.
ECAI-Skills/skills/ecai-experiments/SKILL.md
Source commit 932eb23331721b16e967c59f093781be1928b498
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- Yes
- Observed behavior
- Network or broad shell
- Last checked
- Nov 9, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 1,405
- Repository last updated
- Sep 27, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- academic-writing Repository topic
- agent-skills Repository topic
- journal Repository topic
- academic-research Repository topic
- ai-agents Repository topic
- anthropic Repository topic
- awesome-list Repository topic
- claude Repository topic
- claude-code Repository topic
- economics Repository topic
- research Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 4,741 bytes
Read excerpt
# ECAI Experiments
The ECAI question is always the same: **is the evidence proportional to the claim?** But ECAI spans
symbolic and applied AI, so "evidence" ranges from a **proof** to a **fair empirical comparison**.
Choosing the right *kind* of evidence for your claim shape is the first and most important decision.
## Choose the evidence type by claim shape
| Claim | Primary evidence | Common ECAI failure |
|---|---|---|
| "Complete / sound / optimal / (1+ε)-bounded" | A **proof**, all assumptions explicit | Asserting it empirically only |
| "More efficient / fewer expansions / faster" | A **controlled comparison** on standard instances, with spread | One lucky run; unfair baseline tuning |
| "Learns/generalizes/calibrates better" | Fair comparison + a *reason why*, seeds, significance | A single benchmark delta with no mechanism |
| "Handles a broader class / new setting" | A construction/encoding + worked cases | Toy examples only |