FrontisAI/NatureBench

Read, Grep, Glob, Bash, WebFetch, Write, Edit

- Run all download/script Bash calls in the **foreground** — never use `run_in_background: true`. - Set `timeout: 86400000` (24 hours) on every download, clone, and acquisition Bash call. Without an explicit timeout the Bash tool defaults t

- Acquisition is **idempotent**: before downloading/copying/generating, check whether the target already exists. Use `wget -c` to resume partial downloads. If a session ends mid-download (e.g., a multi-day dataset exceeds 24h), the next inv

- **Repositories**: If `<output_dir>/repositories/<owner>_<repo_name>/.git/` exists **and** `git -C <path> rev-parse HEAD` returns a valid commit hash, skip cloning. Otherwise delete the incomplete directory and re-clone (git clone is not r

- **Downloads**: Always use `wget -c` (resume) so that partially downloaded files continue from where they left off rather than restarting. If a file already exists and its size matches the expected size (from HTTP `Content-Length`), skip t

Download from URL to `data/<setting_dir>/` using `wget` or `curl`. Key requirements: - **Resume**: Always use `wget -c` (or `curl -C -`) to support interrupted/partial downloads

- **Resume**: Always use `wget -c` (or `curl -C -`) to support interrupted/partial downloads

wget -c \

curl --noproxy '*' -C - -L -o <output> <url>

# or:   env -u http_proxy -u https_proxy -u HTTP_PROXY -u HTTPS_PROXY \     wget -c --no-check-certificate <url>

env -u http_proxy -u https_proxy -u HTTP_PROXY -u HTTPS_PROXY      wget -c --no-check-certificate <url>

wget -c --no-check-certificate <url>

pip install h5py pandas pyarrow numpy scipy nibabel tifffile # torch: install separately per https://pytorch.org if PyTorch files need inspection

# torch: install separately per https://pytorch.org if PyTorch files need inspection

#!/usr/bin/env python3

Read, Grep, Glob, Bash(python *), Bash(python3 *), Bash(find *), Bash(wc *), Bash(head *), Bash(diff *), Write

Read, Grep, Glob, Bash, WebFetch, Write, Edit

Read, Grep, Glob, WebFetch, Bash(python *), Bash(python3 *)

"per_url_estimates": [     {       "url": "https://zenodo.org/record/xxx/files/data.tar.gz",

{       "url": "https://zenodo.org/record/xxx/files/data.tar.gz",       "estimated_bytes": 3221225472,

"url": "https://zenodo.org/record/xxx/files/data.tar.gz",

"results": [     {       "url": "https://zenodo.org/record/xxx",

{       "url": "https://zenodo.org/record/xxx",       "status": "accessible",

"url": "https://zenodo.org/record/xxx",

"http_code": 200,       "notes": null,       "final_url": "https://zenodo.org/record/xxx",

"notes": null,       "final_url": "https://zenodo.org/record/xxx",       "cloud_type": null

"final_url": "https://zenodo.org/record/xxx",

},     {       "url": "https://figshare.com/articles/xxx",

{       "url": "https://figshare.com/articles/xxx",       "status": "accessible",

"url": "https://figshare.com/articles/xxx",

"http_code": 202,       "notes": null,       "final_url": "https://figshare.com/articles/xxx",

"notes": null,       "final_url": "https://figshare.com/articles/xxx",       "cloud_type": null

"final_url": "https://figshare.com/articles/xxx",

},     {       "url": "https://physionet.org/content/mimiciii/",

{       "url": "https://physionet.org/content/mimiciii/",       "status": "requires_auth",

"url": "https://physionet.org/content/mimiciii/",

#!/usr/bin/env python3

[Credential-related source omitted]

try:         resp = requests.get(

resp = requests.get(

f"https://api.github.com/repos/{owner}/{repo}",

try:         resp = requests.get(

resp = requests.get(

f"https://zenodo.org/api/records/{record_id}",

try:         resp = requests.get(

resp = requests.get(

f"https://api.figshare.com/v2/articles/{article_id}",

try:         resp = requests.get(

resp = requests.get(

f"https://huggingface.co/api/{repo_type}/{repo_id}",

#!/usr/bin/env python3

[Credential-related source omitted]

direct_url = f"https://drive.google.com/uc?export=download&id={file_id}"

try:         headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)         result["http_code"] = response.status_c

response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

get_response = requests.get(direct_url, timeout=timeout, headers=headers, stream=True, verify=SSL_VERIFY)

try:         headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}         response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}         response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)         result["http_code"] = response.

response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)

try:         headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)         result["http_code"] = response.status_c

response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

get_response = requests.get(url, timeout=timeout, allow_redirects=True,

response = requests.head(url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

description="Validate data link accessibility for zero-interaction acquisition check.",         epilog="Examples:\n"                "  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"

epilog="Examples:\n"                "  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"                "  python validate_links.py --file links.json\n"

"  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"

Read, Bash(python *)

"links": [     {       "url": "https://github.com/example/repo",

{       "url": "https://github.com/example/repo",       "type": "github | zenodo | codeocean | huggingface | google_drive | dropbox | other",

"url": "https://github.com/example/repo",

}   ],   "data_availability": ["https://..."],

],   "data_availability": ["https://..."],   "code_availability": ["https://github.com/..."],

"data_availability": ["https://..."],

"code_availability": ["https://github.com/..."],

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

Read, Grep, Glob, Bash, WebFetch, Write, Edit

gfortran \     git \     wget \

git \     wget \     curl \

wget \

curl \

&& rm -rf /var/lib/apt/lists/*

torchvision==0.21.0 \     torchaudio==2.6.0 \     --index-url https://download.pytorch.org/whl/cu118

--index-url https://download.pytorch.org/whl/cu118

# ── Node.js + Agent CLIs (Claude Code, Codex, Gemini) ────────────────────── RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

&& rm -rf /var/lib/apt/lists/* \

- `v3` standardizes on **CUDA 11.8 + cuDNN 8** with `torch==2.6.0`, `torchvision==0.21.0`, and `torchaudio==2.6.0` installed from `https://download.pytorch.org/whl/cu118`.

- Torch ecosystem packages with compiled extensions must match **both** the torch minor and the CUDA variant. This includes packages such as `dgl`, `torch-geometric`, `pyg-lib`, `torch-scatter`, `torch-sparse`, `torch-cluster`, `torch-harmo

- **JAX ecosystem lock (v3 base, CUDA 11.8)**: JAX dropped `cuda11` jaxlib wheels after `0.4.25` — `jaxlib==0.4.26` and later only publish `+cuda12.cudnn89` / `+cuda12.cudnn91` variants (verify at `https://storage.googleapis.com/jax-release

**Known compatibility issues** (discovered from verified Dockerfile failures): - `catboost==1.2.7`: declares `numpy>=1.16.0,<2.0`. Fully compatible with base numpy==1.26.4. No ABI issues. However, if the task's Dockerfile installs packages 

- `catboost==1.2.7`: declares `numpy>=1.16.0,<2.0`. Fully compatible with base numpy==1.26.4. No ABI issues. However, if the task's Dockerfile installs packages that trigger numpy upgrade to 2.x, catboost will break (`numpy.dtype size chang

- DGL from wrong torch wheel index: `dgl` installed from a mismatched wheel index will replace the base image's `torch==2.6.0+cu118` with a different version (e.g., CPU or newer minor version). This underlying change breaks the ABI for the 

- `vina==1.2.5`: builds from source and requires Boost C++ headers. The base image does not include Boost. Add `RUN apt-get update && apt-get install -y --no-install-recommends libboost-all-dev && rm -rf /var/lib/apt/lists/*` before `pip in

- `scikits.odes`: version 2.6.3 fails to build in the v3 base image environment — it relies on deprecated `numpy.distutils` which crashes with current setuptools (`TypeError: Compiler.__init__() takes from 1 to 3 positional arguments but 4 

- `neuraloperator==0.3.0`: the import name is `neuralop` (not `neuraloperator`). `torch-harmonics` is not declared as a hard dependency in its metadata, but `neuralop` imports it at runtime — import verification will fail with `No module na

- `pytfa==0.9.4` has malformed metadata that `pip>=24.1` strictly rejects. The specific bad line lives in `setup.cfg` under `[options.extras_require]` — a bare `python_version>="3.6"` entry inside the `equilibrator` extras list (it is being

- `pytfa==0.9.4` has malformed metadata that `pip>=24.1` strictly rejects. The specific bad line lives in `setup.cfg` under `[options.extras_require]` — a bare `python_version>="3.6"` entry inside the `equilibrator` extras list (it is being

2. **Before adding `apt-get install`**: check (a) whether the base image already includes the system package; (b) whether the target Python package has a pre-built wheel on PyPI — if so, the `-dev` header packages needed for source compilat

3. **When download is unavoidable**: apply the robust patterns below (retry + fallback + validation) - **General: `git clone` / `pip install git+` in Dockerfiles**: Direct GitHub cloning from Docker build environments frequently suffers fro

- **General: `git clone` / `pip install git+` in Dockerfiles**: Direct GitHub cloning from Docker build environments frequently suffers from absolute timeouts (even with 3+ retries, it often remains completely blocked). **Preferred approach

RUN set -eux; \       for url in \         "https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \

for url in \         "https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \         "https://codeload.github.com/<org>/<repo>/tar.gz/<commit>" \

"https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \

"https://codeload.github.com/<org>/<repo>/tar.gz/<commit>" \         "https://github.com/<org>/<repo>/archive/<commit>.tar.gz"; do \         if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \

"https://github.com/<org>/<repo>/archive/<commit>.tar.gz"; do \         if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \       done; \

if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \

python -m pip install --no-cache-dir /tmp/<repo>-<commit>     ```   - *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>`

```   - *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>` — note that `pip install git+` cannot do the multi-URL fallba

- *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>` — note that `pip install git+` cannot do the multi-URL fallback loo

RUN wget -q https://primary-source.com/binary -O /usr/local/bin/binary \

|| wget -q https://backup-source.com/binary -O /usr/local/bin/binary \

RUN set -eux;      export DEBIAN_FRONTEND=noninteractive;      sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc

RUN set -eux; \     export DEBIAN_FRONTEND=noninteractive; \     sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /e

export DEBIAN_FRONTEND=noninteractive; \     sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list;

sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list; \

rm -rf /var/lib/apt/lists/*; \

if apt-get update && apt-get install -y --no-install-recommends <packages> && rm -rf /var/lib/apt/lists/*; then \

RUN apt-get update && apt-get install -y --no-install-recommends      libxxx-dev      && rm -rf /var/lib/apt/lists/*

&& rm -rf /var/lib/apt/lists/*

RUN apt-get update && apt-get install -y --no-install-recommends      software-properties-common build-essential cmake git wget curl      && add-apt-repository ppa:deadsnakes/ppa -y      && apt-get update      && apt-get install -y --no-ins

RUN apt-get update && apt-get install -y --no-install-recommends \     software-properties-common build-essential cmake git wget curl \

software-properties-common build-essential cmake git wget curl \

&& rm -rf /var/lib/apt/lists/*

# Install all required packages from scratch RUN python -m pip install --no-cache-dir \     torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

RUN python -m pip install --no-cache-dir      torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Read, Grep, Glob, Bash, WebFetch, Write, Edit

Read, Grep, Glob, Write, Bash(python *), Bash(find *), Bash(ls *), Bash(mkdir *), Bash(rm *), Bash(cp *)

allowed-tools: Read, Grep, Glob, Write, Bash(python *), Bash(find *), Bash(ls *), Bash(mkdir *), Bash(rm *), Bash(cp *)

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(mv *), Bash(du 

context: fork agent: general-purpose allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip 

agent: general-purpose allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzi

allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(

allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(

Read, Grep, Glob, Bash, WebFetch, Write, Edit

- Run all download/script Bash calls in the **foreground** — never use `run_in_background: true`. - Set `timeout: 86400000` (24 hours) on every download, clone, and acquisition Bash call. Without an explicit timeout the Bash tool defaults t

- Acquisition is **idempotent**: before downloading/copying/generating, check whether the target already exists. Use `wget -c` to resume partial downloads. If a session ends mid-download (e.g., a multi-day dataset exceeds 24h), the next inv

- **Repositories**: If `<output_dir>/repositories/<owner>_<repo_name>/.git/` exists **and** `git -C <path> rev-parse HEAD` returns a valid commit hash, skip cloning. Otherwise delete the incomplete directory and re-clone (git clone is not r

- **Downloads**: Always use `wget -c` (resume) so that partially downloaded files continue from where they left off rather than restarting. If a file already exists and its size matches the expected size (from HTTP `Content-Length`), skip t

Download from URL to `data/<setting_dir>/` using `wget` or `curl`. Key requirements: - **Resume**: Always use `wget -c` (or `curl -C -`) to support interrupted/partial downloads

- **Resume**: Always use `wget -c` (or `curl -C -`) to support interrupted/partial downloads

wget -c \

curl --noproxy '*' -C - -L -o <output> <url>

# or:   env -u http_proxy -u https_proxy -u HTTP_PROXY -u HTTPS_PROXY \     wget -c --no-check-certificate <url>

env -u http_proxy -u https_proxy -u HTTP_PROXY -u HTTPS_PROXY      wget -c --no-check-certificate <url>

wget -c --no-check-certificate <url>

pip install h5py pandas pyarrow numpy scipy nibabel tifffile # torch: install separately per https://pytorch.org if PyTorch files need inspection

# torch: install separately per https://pytorch.org if PyTorch files need inspection

#!/usr/bin/env python3

Read, Grep, Glob, Bash(python *), Bash(python3 *), Bash(find *), Bash(wc *), Bash(head *), Bash(diff *), Write

Read, Grep, Glob, Bash, WebFetch, Write, Edit

Read, Grep, Glob, WebFetch, Bash(python *), Bash(python3 *)

"per_url_estimates": [     {       "url": "https://zenodo.org/record/xxx/files/data.tar.gz",

{       "url": "https://zenodo.org/record/xxx/files/data.tar.gz",       "estimated_bytes": 3221225472,

"url": "https://zenodo.org/record/xxx/files/data.tar.gz",

"results": [     {       "url": "https://zenodo.org/record/xxx",

{       "url": "https://zenodo.org/record/xxx",       "status": "accessible",

"url": "https://zenodo.org/record/xxx",

"http_code": 200,       "notes": null,       "final_url": "https://zenodo.org/record/xxx",

"notes": null,       "final_url": "https://zenodo.org/record/xxx",       "cloud_type": null

"final_url": "https://zenodo.org/record/xxx",

},     {       "url": "https://figshare.com/articles/xxx",

{       "url": "https://figshare.com/articles/xxx",       "status": "accessible",

"url": "https://figshare.com/articles/xxx",

"http_code": 202,       "notes": null,       "final_url": "https://figshare.com/articles/xxx",

"notes": null,       "final_url": "https://figshare.com/articles/xxx",       "cloud_type": null

"final_url": "https://figshare.com/articles/xxx",

},     {       "url": "https://physionet.org/content/mimiciii/",

{       "url": "https://physionet.org/content/mimiciii/",       "status": "requires_auth",

"url": "https://physionet.org/content/mimiciii/",

#!/usr/bin/env python3

[Credential-related source omitted]

try:         resp = requests.get(

resp = requests.get(

f"https://api.github.com/repos/{owner}/{repo}",

try:         resp = requests.get(

resp = requests.get(

f"https://zenodo.org/api/records/{record_id}",

try:         resp = requests.get(

resp = requests.get(

f"https://api.figshare.com/v2/articles/{article_id}",

try:         resp = requests.get(

resp = requests.get(

f"https://huggingface.co/api/{repo_type}/{repo_id}",

#!/usr/bin/env python3

[Credential-related source omitted]

direct_url = f"https://drive.google.com/uc?export=download&id={file_id}"

try:         headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)         result["http_code"] = response.status_c

response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

get_response = requests.get(direct_url, timeout=timeout, headers=headers, stream=True, verify=SSL_VERIFY)

try:         headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}         response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36"}         response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)         result["http_code"] = response.

response = requests.get(url, timeout=timeout, headers=headers, allow_redirects=True, verify=SSL_VERIFY)

try:         headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

headers = {"User-Agent": "Mozilla/5.0 (compatible; PaperFilterBot/1.0)"}         response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)         result["http_code"] = response.status_c

response = requests.head(direct_url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

get_response = requests.get(url, timeout=timeout, allow_redirects=True,

response = requests.head(url, timeout=timeout, allow_redirects=True, headers=headers, verify=SSL_VERIFY)

description="Validate data link accessibility for zero-interaction acquisition check.",         epilog="Examples:\n"                "  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"

epilog="Examples:\n"                "  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"                "  python validate_links.py --file links.json\n"

"  python validate_links.py https://example.com/data.zip https://zenodo.org/record/xxx\n"

Read, Bash(python *)

"links": [     {       "url": "https://github.com/example/repo",

{       "url": "https://github.com/example/repo",       "type": "github | zenodo | codeocean | huggingface | google_drive | dropbox | other",

"url": "https://github.com/example/repo",

}   ],   "data_availability": ["https://..."],

],   "data_availability": ["https://..."],   "code_availability": ["https://github.com/..."],

"data_availability": ["https://..."],

"code_availability": ["https://github.com/..."],

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

#!/usr/bin/env python3

Read, Grep, Glob, Bash, WebFetch, Write, Edit

gfortran \     git \     wget \

git \     wget \     curl \

wget \

curl \

&& rm -rf /var/lib/apt/lists/*

torchvision==0.21.0 \     torchaudio==2.6.0 \     --index-url https://download.pytorch.org/whl/cu118

--index-url https://download.pytorch.org/whl/cu118

# ── Node.js + Agent CLIs (Claude Code, Codex, Gemini) ────────────────────── RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

RUN curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \

&& rm -rf /var/lib/apt/lists/* \

- `v3` standardizes on **CUDA 11.8 + cuDNN 8** with `torch==2.6.0`, `torchvision==0.21.0`, and `torchaudio==2.6.0` installed from `https://download.pytorch.org/whl/cu118`.

- Torch ecosystem packages with compiled extensions must match **both** the torch minor and the CUDA variant. This includes packages such as `dgl`, `torch-geometric`, `pyg-lib`, `torch-scatter`, `torch-sparse`, `torch-cluster`, `torch-harmo

- **JAX ecosystem lock (v3 base, CUDA 11.8)**: JAX dropped `cuda11` jaxlib wheels after `0.4.25` — `jaxlib==0.4.26` and later only publish `+cuda12.cudnn89` / `+cuda12.cudnn91` variants (verify at `https://storage.googleapis.com/jax-release

**Known compatibility issues** (discovered from verified Dockerfile failures): - `catboost==1.2.7`: declares `numpy>=1.16.0,<2.0`. Fully compatible with base numpy==1.26.4. No ABI issues. However, if the task's Dockerfile installs packages 

- `catboost==1.2.7`: declares `numpy>=1.16.0,<2.0`. Fully compatible with base numpy==1.26.4. No ABI issues. However, if the task's Dockerfile installs packages that trigger numpy upgrade to 2.x, catboost will break (`numpy.dtype size chang

- DGL from wrong torch wheel index: `dgl` installed from a mismatched wheel index will replace the base image's `torch==2.6.0+cu118` with a different version (e.g., CPU or newer minor version). This underlying change breaks the ABI for the 

- `vina==1.2.5`: builds from source and requires Boost C++ headers. The base image does not include Boost. Add `RUN apt-get update && apt-get install -y --no-install-recommends libboost-all-dev && rm -rf /var/lib/apt/lists/*` before `pip in

- `scikits.odes`: version 2.6.3 fails to build in the v3 base image environment — it relies on deprecated `numpy.distutils` which crashes with current setuptools (`TypeError: Compiler.__init__() takes from 1 to 3 positional arguments but 4 

- `neuraloperator==0.3.0`: the import name is `neuralop` (not `neuraloperator`). `torch-harmonics` is not declared as a hard dependency in its metadata, but `neuralop` imports it at runtime — import verification will fail with `No module na

- `pytfa==0.9.4` has malformed metadata that `pip>=24.1` strictly rejects. The specific bad line lives in `setup.cfg` under `[options.extras_require]` — a bare `python_version>="3.6"` entry inside the `equilibrator` extras list (it is being

- `pytfa==0.9.4` has malformed metadata that `pip>=24.1` strictly rejects. The specific bad line lives in `setup.cfg` under `[options.extras_require]` — a bare `python_version>="3.6"` entry inside the `equilibrator` extras list (it is being

2. **Before adding `apt-get install`**: check (a) whether the base image already includes the system package; (b) whether the target Python package has a pre-built wheel on PyPI — if so, the `-dev` header packages needed for source compilat

3. **When download is unavoidable**: apply the robust patterns below (retry + fallback + validation) - **General: `git clone` / `pip install git+` in Dockerfiles**: Direct GitHub cloning from Docker build environments frequently suffers fro

- **General: `git clone` / `pip install git+` in Dockerfiles**: Direct GitHub cloning from Docker build environments frequently suffers from absolute timeouts (even with 3+ retries, it often remains completely blocked). **Preferred approach

RUN set -eux; \       for url in \         "https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \

for url in \         "https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \         "https://codeload.github.com/<org>/<repo>/tar.gz/<commit>" \

"https://mirror.ghproxy.com/https://github.com/<org>/<repo>/archive/<commit>.tar.gz" \

"https://codeload.github.com/<org>/<repo>/tar.gz/<commit>" \         "https://github.com/<org>/<repo>/archive/<commit>.tar.gz"; do \         if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \

"https://github.com/<org>/<repo>/archive/<commit>.tar.gz"; do \         if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \       done; \

if wget -q --tries=3 --timeout=30 "$url" -O /tmp/repo.tar.gz; then break; fi; \

python -m pip install --no-cache-dir /tmp/<repo>-<commit>     ```   - *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>`

```   - *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>` — note that `pip install git+` cannot do the multi-URL fallba

- *Git+ Pip Install (only when archive+sed patching is not viable)*: `RUN python -m pip install git+https://mirror.ghproxy.com/https://github.com/<org>/<repo>.git@<commit>` — note that `pip install git+` cannot do the multi-URL fallback loo

RUN wget -q https://primary-source.com/binary -O /usr/local/bin/binary \

|| wget -q https://backup-source.com/binary -O /usr/local/bin/binary \

RUN set -eux;      export DEBIAN_FRONTEND=noninteractive;      sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc

RUN set -eux; \     export DEBIAN_FRONTEND=noninteractive; \     sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /e

export DEBIAN_FRONTEND=noninteractive; \     sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list;

sed -i 's|http://archive.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g; s|http://security.ubuntu.com/ubuntu|https://mirrors.tuna.tsinghua.edu.cn/ubuntu|g' /etc/apt/sources.list; \

rm -rf /var/lib/apt/lists/*; \

if apt-get update && apt-get install -y --no-install-recommends <packages> && rm -rf /var/lib/apt/lists/*; then \

RUN apt-get update && apt-get install -y --no-install-recommends      libxxx-dev      && rm -rf /var/lib/apt/lists/*

&& rm -rf /var/lib/apt/lists/*

RUN apt-get update && apt-get install -y --no-install-recommends      software-properties-common build-essential cmake git wget curl      && add-apt-repository ppa:deadsnakes/ppa -y      && apt-get update      && apt-get install -y --no-ins

RUN apt-get update && apt-get install -y --no-install-recommends \     software-properties-common build-essential cmake git wget curl \

software-properties-common build-essential cmake git wget curl \

&& rm -rf /var/lib/apt/lists/*

# Install all required packages from scratch RUN python -m pip install --no-cache-dir \     torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

RUN python -m pip install --no-cache-dir      torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

torch==2.6.0 torchvision==0.21.0 --index-url https://download.pytorch.org/whl/cu118

[Credential-related source omitted]

[Credential-related source omitted]

[Credential-related source omitted]

Read, Grep, Glob, Bash, WebFetch, Write, Edit

Read, Grep, Glob, Write, Bash(python *), Bash(find *), Bash(ls *), Bash(mkdir *), Bash(rm *), Bash(cp *)

allowed-tools: Read, Grep, Glob, Write, Bash(python *), Bash(find *), Bash(ls *), Bash(mkdir *), Bash(rm *), Bash(cp *)

#!/usr/bin/env python3

[Credential-related source omitted]

[Credential-related source omitted]

Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(mv *), Bash(du 

context: fork agent: general-purpose allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip 

agent: general-purpose allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzi

allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(

allowed-tools: Read, Grep, Glob, Write, Bash(rm *), Bash(mkdir *), Bash(find *), Bash(ls *), Bash(git clone *), Bash(GIT_SSL_NO_VERIFY=1 git clone *), Bash(wget *), Bash(curl *), Bash(tar *), Bash(unzip *), Bash(gunzip *), Bash(cp *), Bash(