An open API service for producing an overview of a list of open source projects.

https://github.com/UKGovernmentBEIS/inspect_evals

Score: 26.003780200866814

Last synced: about 12 hours ago
JSON representation

Repository metadata:

Collection of evals for Inspect AI


Owner metadata:


GitHub Events

Total
Last Year

Committers metadata

Last synced: 1 day ago

Total Commits: 2,603
Total Committers: 228
Avg Commits per committer: 11.417
Development Distribution Score (DDS): 0.813

Commits in past year: 1,351
Committers in past year: 146
Avg Commits per committer in past year: 9.253
Development Distribution Score (DDS) in past year: 0.8

Name Email Commits
Matt Fisher m****r@g****m 488
Scott-Simmons 5****s 213
Jay-Bailey 4****y 138
Tania 1****a 112
github-actions[bot] 4****] 98
Alexander Putilin a****3@y****u 87
dependabot[bot] 4****] 76
jjallaire j****e@g****m 67
claude-code-aisi[bot] 2****] 56
owen.parsons o****s@m****i 51
anaoaktree a****e 49
Arthit Suriyawongkul a****t@g****m 45
Celia Waggoner c****r@g****m 45
Charles Teague c****e@g****m 42
jeqcho j****i@c****u 40
enerrio 1****o 38
Alex M a****n@c****k 37
Matt Reed m****6@g****m 34
max-kaufmann m****n@g****m 32
Anthony Duong 4****9 31
Sai Sasank Y s****i@g****m 27
Joe.Skinner J****r@d****k 26
Caspar de Haes c****h@g****m 23
Alexandra Abbas 3****s 23
Vikram v****2@g****m 22
darkness8i8 j****k@g****m 19
Anselm Coogan a****n@i****m 19
ourmony e****e@o****m 18
Alex.Remedios A****s@d****k 17
Esther Guo s****i@g****m 17
and 198 more...

Issue and Pull Request metadata

Last synced: 1 day ago

Total issues: 306
Total pull requests: 910
Average time to close issues: about 1 month
Average time to close pull requests: 8 days
Total issue authors: 139
Total pull request authors: 184
Average comments per issue: 1.45
Average comments per pull request: 2.66
Merged pull request: 500
Bot issues: 13
Bot pull requests: 188

Past year issues: 191
Past year pull requests: 527
Past year average time to close issues: about 1 month
Past year average time to close pull requests: 8 days
Past year issue authors: 78
Past year pull request authors: 83
Past year average comments per issue: 1.56
Past year average comments per pull request: 3.9
Past year merged pull request: 267
Past year bot issues: 13
Past year bot pull requests: 137

More stats: https://issues.ecosyste.ms/repositories/lookup?url=https://github.com/UKGovernmentBEIS/inspect_evals

Top Issue Authors

  • MattFisher (52)
  • celiawaggoner (11)
  • craig-meridian (8)
  • cenab (8)
  • anthonyduong9 (7)
  • github-actions[bot] (7)
  • NelsonG-C (6)
  • shane485 (6)
  • Mamiglia (6)
  • claude-code-aisi[bot] (6)
  • AI-Sec-dev (5)
  • Lostmanu (5)
  • kohankhaki (5)
  • ItsTania (5)
  • Esther-Guo (4)

Top Pull Request Authors

  • MattFisher (153)
  • dependabot[bot] (83)
  • github-actions[bot] (54)
  • claude-code-aisi[bot] (51)
  • Scott-Simmons (44)
  • Jay-Bailey (44)
  • eleweek (24)
  • celiawaggoner (24)
  • ItsTania (20)
  • feiiiiii5 (19)
  • sylvesterkaczmarek (15)
  • alexandraabbas (9)
  • cenab (9)
  • skinnerjc (9)
  • arthi-arumugam-git (9)

Top Issue Labels

  • bug (41)
  • register-submission (34)
  • enhancement (29)
  • implementation (21)
  • low AI-generated score (17)
  • tests (7)
  • main-ci-red (7)
  • scoring (6)
  • upstream-migration (6)
  • scoring:parsing (4)
  • ci (4)
  • good first issue (4)
  • sandbox (3)
  • shared-utils (3)
  • needs-decision (3)
  • dependencies (3)
  • help wanted (2)
  • difficult (2)
  • lint (2)
  • question (2)
  • easy (2)
  • documentation (2)
  • github_actions (1)
  • tracking (1)
  • scoring:aggregation (1)
  • external-assets (1)
  • security (1)
  • average (1)

Top Pull Request Labels

  • dependencies (81)
  • automated-smoke-test-fix (33)
  • python:uv (24)
  • enhancement (20)
  • automated-heavy-test-fix (19)
  • implementation (19)
  • python (18)
  • github_actions (9)
  • ok to test (8)
  • documentation (7)
  • bug (7)
  • automated-issue-fix (2)
  • kind/bugfix (1)
  • area/dependencies (1)
  • area/smallrye (1)
  • ASET (1)
  • triage/flaky-test (1)

Package metadata

proxy.golang.org: github.com/UKGovernmentBeis/inspect_evals

proxy.golang.org: github.com/UKGOvernmentBEIS/inspect_evals

proxy.golang.org: github.com/UKGovernmentbeis/inspect_evals

proxy.golang.org: github.com/ukgovernmentbeis/inspect_evals

proxy.golang.org: github.com/UKGovernmentBEIS/inspect_evals

pypi.org: inspect-evals

Collection of large language model evaluations

  • Homepage:
  • Documentation: https://ukgovernmentbeis.github.io/inspect_evals/
  • Licenses: MIT
  • Latest release: 0.27.0 (published 4 days ago)
  • Last Synced: 2026-11-01T15:27:03.932Z (1 day ago)
  • Versions: 38
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 866,915 Last month
  • Rankings:
    • Forks count: 4.745%
    • Stargazers count: 5.662%
    • Dependent packages count: 8.402%
    • Average: 16.575%
    • Dependent repos count: 47.492%
  • Maintainers (1)
github actions: UKGovernmentBEIS/inspect_evals/.github/actions/clone-external-repos

Clones external repositories referenced by register eval.yaml files at their pinned commits into .external_repos/ and locks them read-only. Requires Python and uv to be available (e.g. via claude-setup with install_python_deps: true).

  • Homepage: https://ukgovernmentbeis.github.io/inspect_evals/
  • Licenses: mit
  • Latest release: v0.26.0 (published 11 days ago)
  • Last Synced: 2026-10-31T12:17:43.480Z (3 days ago)
  • Versions: 48
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Rankings:
    • Dependent packages count: 0.0%
    • Dependent repos count: 37.684%
    • Average: 37.684%
github actions: UKGovernmentBEIS/inspect_evals/.github/actions/claude-setup

Shared setup steps for Claude Code workflows: checkout, optional Python/uv dependencies, and AWS OIDC credentials.

  • Homepage: https://ukgovernmentbeis.github.io/inspect_evals/
  • Licenses: mit
  • Latest release: v0.26.0 (published 11 days ago)
  • Last Synced: 2026-10-31T12:17:43.469Z (3 days ago)
  • Versions: 48
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Rankings:
    • Dependent packages count: 0.0%
    • Dependent repos count: 37.684%
    • Average: 37.684%

Dependencies

.github/workflows/build.yml actions
  • actions/cache v3 composite
  • actions/checkout v4 composite
  • actions/setup-python v4 composite
  • chartboost/ruff-action v1 composite
  • hynek/build-and-inspect-python-package v1 composite
pyproject.toml pypi
src/inspect_evals/agentdojo/data/suites/workspace_plus/environment.yaml conda
.github/workflows/register-submission-eval-validity.yaml actions
  • UKGovernmentBEIS/inspect_evals/.github/actions/claude-setup e1d6eb836e90bb6ab11bb39c3e9ca6f3225e4ae7 composite
  • UKGovernmentBEIS/inspect_evals/.github/actions/clone-external-repos e1d6eb836e90bb6ab11bb39c3e9ca6f3225e4ae7 composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/upload-artifact 043fb46d1a93c77aae656e7c1c64a875d1fc6a0a composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
.github/workflows/docker-image-rebuild.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • docker/login-action 06fb636fac595d6fb4b28a5dfcb21a6f5091859c composite
  • docker/setup-buildx-action bb05f3f5519dd87d3ba754cc423b652a5edd6d2c composite
  • tj-actions/changed-files 9426d40962ed5378910ee2e21d5f8c6fcbf2dd96 composite
src/inspect_evals/agentdojo/data/suites/travel/environment.yaml conda
src/inspect_evals/gdm_in_house_ctf/challenges/spray/Dockerfile docker
  • python 3-alpine build
src/inspect_evals/gdm_in_house_ctf/challenges/spray/requirements.txt pypi
  • flask ==2.3.2
.github/workflows/workflow-lint.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
.github/workflows/dep-bump-impact.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • peter-evans/create-or-update-comment e8674b075228eee787fea43ef493e45ece1004c9 composite
  • peter-evans/find-comment b30e6a3c0ed37e7c023ccd3f1db5c6c0b0c23aad composite
.github/workflows/publish.yaml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • pypa/gh-action-pypi-publish ba38be9e461d3875417946c167d0b5f3d385a247 composite
src/inspect_evals/compute_eval/Dockerfile docker
  • nvidia/cuda 12.9.0-devel-ubuntu24.04 build
.github/workflows/weekly-release.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • slackapi/slack-github-action dcb1066f776dd043e64d0e8ba94ca15cc7e1875d composite
.github/actions/clone-external-repos/action.yaml actions
.github/actions/claude-setup/action.yaml actions
  • actions/checkout de0fac2e4500dabe0009e67214ff5f5447ce83dd composite
  • actions/setup-python a309ff8b426b58ec0e2a45f0f869d46889d02405 composite
  • astral-sh/setup-uv 08807647e7069bb48b6ef5acd8ec9567f424441b composite
  • aws-actions/configure-aws-credentials 7474bc4690e29a8392af63c5b98e7449536d5c3a composite
.github/workflows/checks.yml actions
  • actions/cache 55cc8345863c7cc4c66a329aec7e433d2d1c52a9 composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/ruff-action 278981a28ce3188b1e39527901f38254bf3aac89 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • hynek/build-and-inspect-python-package d44ca7d91762de7a7d5436ddae667c6da6d1c3df composite
.github/workflows/register-submission.yaml actions
  • ./.github/actions/claude-setup * composite
  • UKGovernmentBEIS/inspect_evals/.github/actions/clone-external-repos e1d6eb836e90bb6ab11bb39c3e9ca6f3225e4ae7 composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/download-artifact 3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
.github/workflows/build-repo-context.yaml actions
  • ./.github/actions/claude-setup * composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
.github/workflows/claude-fix-tests.yaml actions
  • ./.github/actions/claude-setup * composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/create-github-app-token bcd2ba49218906704ab6c1aa796996da409d3eb1 composite
  • actions/github-script 3a2844b7e9c422d3c10d287c895573f7108da1b3 composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
.github/workflows/claude-issue-solver.yaml actions
  • ./.github/actions/claude-setup * composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/create-github-app-token bcd2ba49218906704ab6c1aa796996da409d3eb1 composite
  • actions/github-script 3a2844b7e9c422d3c10d287c895573f7108da1b3 composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
src/inspect_evals/gdm_in_house_ctf/challenges/grafana/Dockerfile docker
  • grafana/grafana 8.3.0 build
.github/workflows/claude-review.yaml actions
  • ./.github/actions/claude-setup * composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/github-script 3a2844b7e9c422d3c10d287c895573f7108da1b3 composite
  • anthropics/claude-code-action 44423bdec74b97d67543eb16c110546762c110b2 composite
.github/workflows/docs.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • quarto-dev/quarto-actions/publish 8a96df13519ee81fd526f2dfca5962811136661b composite
  • quarto-dev/quarto-actions/render 8a96df13519ee81fd526f2dfca5962811136661b composite
  • quarto-dev/quarto-actions/setup 8a96df13519ee81fd526f2dfca5962811136661b composite
.github/workflows/docs-preview.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • quarto-dev/quarto-actions/render 8a96df13519ee81fd526f2dfca5962811136661b composite
  • quarto-dev/quarto-actions/setup 8a96df13519ee81fd526f2dfca5962811136661b composite
.github/workflows/dependabot-lock-sync.yml actions
  • actions/checkout 9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 composite
  • actions/create-github-app-token bcd2ba49218906704ab6c1aa796996da409d3eb1 composite
  • actions/download-artifact 3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c composite
  • actions/upload-artifact 043fb46d1a93c77aae656e7c1c64a875d1fc6a0a composite
  • astral-sh/setup-uv 11f9893b081a58869d3b5fccaea48c9e9e46f990 composite
src/inspect_evals/gdm_in_house_ctf/challenges/cmd_injection/Dockerfile docker
  • python 3-alpine build
.github/workflows/lint-new-evals.yml actions
  • actions/cache 55cc8345863c7cc4c66a329aec7e433d2d1c52a9 composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
src/inspect_evals/frontier_cs/Dockerfile docker
  • ubuntu 24.04 build
src/inspect_evals/bigcodebench/docker-requirements.txt pypi
  • Django ==4.2.7
  • Faker ==20.1.0
  • Flask-Mail ==0.9.1
  • Levenshtein ==0.25.0
  • Pillow ==10.3.0
  • PyYAML ==6.0.1
  • Requests ==2.31.0
  • WTForms ==3.1.2
  • Werkzeug ==3.0.1
  • beautifulsoup4 ==4.8.2
  • blake3 ==0.4.1
  • chardet ==5.2.0
  • cryptography ==38.0.0
  • datetime ==5.5
  • dnspython ==2.6.1
  • docxtpl ==0.11.5
  • flask ==3.0.3
  • flask_login ==0.6.3
  • flask_restful ==0.3.10
  • flask_wtf ==1.2.1
  • folium ==0.16.0
  • gensim ==4.3.2
  • geopandas ==0.13.2
  • geopy ==2.4.1
  • holidays ==0.29
  • keras ==2.11.0
  • librosa ==0.10.1
  • lxml ==4.9.3
  • matplotlib ==3.7.0
  • mechanize ==0.4.9
  • natsort ==7.1.1
  • networkx ==2.6.3
  • nltk ==3.8
  • numba ==0.55.0
  • numpy ==1.21.2
  • opencv-python-headless ==4.9.0.80
  • openpyxl ==3.1.2
  • pandas ==2.0.3
  • prettytable ==3.10.0
  • psutil ==6.0.0
  • pycryptodome ==3.14.1
  • pyfakefs ==5.4.1
  • pyquery ==1.4.3
  • pytesseract ==0.3.10
  • pytest ==8.2.0
  • python-Levenshtein-wheels *
  • python-dateutil ==2.9.0
  • python-docx ==1.1.0
  • python_http_client ==3.3.7
  • pytz ==2023.3.post1
  • requests ==2.31.0
  • requests_mock ==1.11.0
  • rsa ==4.9
  • scikit-image ==0.19.3
  • scikit-learn ==1.3.1
  • scipy ==1.7.2
  • seaborn ==0.13.2
  • selenium ==4.15
  • sendgrid ==6.11.0
  • shapely ==2.0.4
  • soundfile ==0.12.1
  • statsmodels ==0.14.0
  • sympy ==1.12
  • tensorflow *
  • textblob ==0.18.0
  • texttable ==1.7.0
  • wikipedia ==1.4.0
  • wordcloud ==1.9.5
  • wordninja ==2.0.0
  • xlrd ==2.0.1
  • xlwt ==1.3.0
  • xmltodict ==0.13.0
.github/workflows/markdown-lint.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
.github/workflows/pr-template-check.yml actions
src/inspect_evals/agentdojo/data/suites/workspace/environment.yaml conda
packages/novelty_bench/pyproject.toml pypi
  • accelerate >=1.11.0
  • inspect-evals *
  • protobuf >=6.33.1
  • sentencepiece >=0.2.1
  • torch >=2.9.1
  • transformers >=4.57.1
src/inspect_evals/cti_realm/docker/sigma_indexer/requirements.txt pypi
  • pyyaml ==6.0
  • requests ==2.31.0
src/inspect_evals/gdm_in_house_ctf/challenges/cmd_injection/requirements.txt pypi
  • flask ==2.3.2
src/inspect_evals/gdm_in_house_ctf/challenges/sqli/requirements.txt pypi
  • flask ==2.3.2
.github/workflows/register-issue-submission.yaml actions
  • actions/cache 55cc8345863c7cc4c66a329aec7e433d2d1c52a9 composite
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • actions/setup-python 5fda3b95a4ea91299a34e894583c3862153e4b97 composite
  • astral-sh/setup-uv c771a70e6277c0a99b617c7a806ffedaca235ff9 composite
  • aws-actions/configure-aws-credentials e6de054238d6b7531b4efff3b6587d9aade6a06c composite
.github/workflows/register-submission-programmatic-checks.yaml actions
  • actions/upload-artifact 043fb46d1a93c77aae656e7c1c64a875d1fc6a0a composite
.github/workflows/release-on-merge.yml actions
  • actions/checkout 3d3c42e5aac5ba805825da76410c181273ba90b1 composite
  • slackapi/slack-github-action dcb1066f776dd043e64d0e8ba94ca15cc7e1875d composite
src/inspect_evals/agentdojo/data/suites/banking/environment.yaml conda
src/inspect_evals/agentdojo/data/suites/slack/environment.yaml conda
src/inspect_evals/cti_realm/docker/kusto_init/Dockerfile docker
  • python 3.11-slim@sha256 build
src/inspect_evals/gdm_in_house_ctf/challenges/attacker/Dockerfile docker
  • marshw/kali-base latest build
src/inspect_evals/gdm_in_house_ctf/challenges/sqli/Dockerfile docker
  • python 3-alpine build
src/inspect_evals/agentdojo/data/suites/workspace_plus/terminal/emma-computer/Dockerfile docker
  • ubuntu 24.04@sha256 build
src/inspect_evals/cybergym/task_template/controller/Dockerfile docker
  • python 3.12.11-slim build
src/inspect_evals/gdm_in_house_ctf/challenges/db_3/Dockerfile docker
  • postgres alpine3.18 build
src/inspect_evals/gdm_in_house_ctf/challenges/idor/Dockerfile docker
  • python 3-alpine build
src/inspect_evals/gdm_in_house_ctf/challenges/privesc_7z/Dockerfile docker
  • debian trixie-slim build
src/inspect_evals/gdm_in_house_ctf/challenges/privesc_bash/Dockerfile docker
  • debian trixie-slim build
src/inspect_evals/gdm_in_house_ctf/challenges/privesc_find/Dockerfile docker
  • debian trixie-slim build
src/inspect_evals/gdm_in_house_ctf/challenges/privesc_sed/Dockerfile docker
  • debian trixie-slim build
src/inspect_evals/gdm_in_house_ctf/challenges/ssh/Dockerfile docker
  • alpine 3.18.2 build
packages/abstention_bench/uv.lock pypi
  • 142 dependencies
src/inspect_evals/gdm_in_house_ctf/challenges/webmin/Dockerfile docker
  • vulhub/webmin 1.910 build
src/inspect_evals/gdm_self_proliferation/data/base/Dockerfile docker
  • python 3.10 build
packages/bold/pyproject.toml pypi
  • detoxify *
  • inspect-evals *
  • torch *
  • transformers >=5.0.0
  • vadersentiment *
packages/bold/uv.lock pypi
  • 138 dependencies
packages/abstention_bench/pyproject.toml pypi
  • hydra-core >=1.4.0.dev1
  • inspect-evals [gdown]
  • jsonlines *
  • loguru *
  • omegaconf >=2.4.0.dev2
  • scikit-learn *
  • torch *
packages/cve_bench/uv.lock pypi
  • 131 dependencies
packages/kernelbench/pyproject.toml pypi
  • inspect-evals *
  • kernelbench @ git+https://github.com/ScalingIntelligence/KernelBench@2f65279
  • torch *
packages/cve_bench/pyproject.toml pypi
  • cvebench @ git+https://github.com/Scott-Simmons/cve-bench.git@92541add2ebd89e5b15ed260eb5d0e9b5102c33e
  • inspect-evals *
packages/kernelbench/uv.lock pypi
  • 192 dependencies
packages/livebench/pyproject.toml pypi
  • inspect-evals *
  • livebench @ git+https://github.com/LiveBench/LiveBench.git@1c4c655 ; sys_platform != 'win32' or python_version < '3.13'
  • nltk *
  • sentencepiece >=0.2.1
packages/livebench/uv.lock pypi
  • 222 dependencies
packages/mle_bench/uv.lock pypi
  • 192 dependencies
packages/mle_bench/pyproject.toml pypi
  • docker *
  • inspect-evals *
  • kaggle *
  • mlebench @ git+https://github.com/openai/mle-bench.git@2451bcb
packages/novelty_bench/uv.lock pypi
  • 138 dependencies
src/inspect_evals/class_eval/docker-requirements.txt pypi
  • PyPDF2 *
  • bs4 *
  • gensim *
  • nltk *
  • numpy *
  • openpyxl *
  • pandas *
  • pillow *
  • python-docx *
  • scipy *
src/inspect_evals/cti_realm/docker/kusto_init/requirements.txt pypi
  • psutil *
  • requests *
src/inspect_evals/ds1000/docker-requirements.txt pypi
  • PyYAML ==6.0.2
  • gensim ==4.3.2
  • matplotlib ==3.8.4
  • numpy ==1.26.4
  • pandas ==1.5.3
  • scikit-learn ==1.4.0
  • scipy ==1.12.0
  • seaborn ==0.13.2
  • statsmodels ==0.14.1
  • tensorflow ==2.16.1
  • torch ==2.2.0
  • xgboost ==2.0.3
src/inspect_evals/gdm_in_house_ctf/challenges/idor/requirements.txt pypi
  • flask ==2.3.2
src/inspect_evals/gdm_self_proliferation/data/setup.py pypi
src/inspect_evals/ds1000/Dockerfile docker
  • python 3.10-slim build
src/inspect_evals/cybench/challenges/shuffled_aes/images/victim/chall/Cargo.toml cargo
src/inspect_evals/cybench/challenges/shuffled_aes/resources/Cargo.toml cargo
src/inspect_evals/cybench/agent_sandbox/Dockerfile docker
  • kalilinux/kali-last-release@sha256 92935ba0b1053dc765e627edb65d1981341b662ccaea99271f5ab40e387483a1 build
src/inspect_evals/cybench/challenges/avatar/images/victim/Dockerfile docker
  • python 3.10-alpine build
src/inspect_evals/cybench/challenges/back_to_the_past/images/victim/Dockerfile docker
  • nginx 1.23.2 build
src/inspect_evals/cybench/challenges/chunky/images/blog/Dockerfile docker
  • ubuntu 20.04 build
src/inspect_evals/cybench/challenges/chunky/images/nginx/Dockerfile docker
  • nginx 1.18.0 build
src/inspect_evals/cybench/challenges/chunky/images/rcache/Dockerfile docker
  • golang 1.20 build
src/inspect_evals/cybench/challenges/delulu/images/victim/Dockerfile docker
  • alpine latest build
src/inspect_evals/cybench/challenges/diffecient/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/ezmaze/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/failproof/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/flag_command/images/victim/Dockerfile docker
  • python 3.11-alpine build
src/inspect_evals/cybench/challenges/frog_waf/images/victim/Dockerfile docker
  • gradle 7.5-jdk11 build
  • openjdk 11-slim build
src/inspect_evals/cybench/challenges/glacier_exchange/images/victim/Dockerfile docker
  • python 3.9-alpine build
src/inspect_evals/cybench/challenges/just_another_pickle_jail/images/victim/Dockerfile docker
  • python 3.11 build
src/inspect_evals/cybench/challenges/labyrinth_linguist/images/victim/Dockerfile docker
  • maven 3.8.5-openjdk-11-slim build
src/inspect_evals/cybench/challenges/locktalk/images/victim/Dockerfile docker
  • alpine edge build
src/inspect_evals/cybench/challenges/network_tools/images/victim/Dockerfile docker
  • ubuntu 20.04 build
src/inspect_evals/cybench/challenges/noisier_crc/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/noisy_crc/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/randsubware/images/victim/Dockerfile docker
  • python 3.9-slim-buster build
src/inspect_evals/cybench/challenges/robust_cbc/images/victim/Dockerfile docker
  • ubuntu focal build
src/inspect_evals/cybench/challenges/shuffled_aes/images/victim/Dockerfile docker
  • alpine latest build
  • rust alpine build
src/inspect_evals/cybench/challenges/skilift/images/victim/Dockerfile docker
  • debian bookworm-slim build
src/inspect_evals/cybench/challenges/unbreakable/images/victim/Dockerfile docker
  • python 3.11-slim-buster build