{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/compute-pass-at-k","entry":"compute_pass_at_k","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":4,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":3,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":1},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.16497","paper":"/paper/arxiv-2606-16497","title":"daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"GAIR-NLP/daVinci-kernel","path":"davinci-kernel/kernel/main_grading.py","file_url":"https://github.com/GAIR-NLP/daVinci-kernel/blob/HEAD/davinci-kernel/kernel/main_grading.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"da6d24aab8a8bcf5","mcp_get_code":{"code_sha256":"da6d24aab8a8bcf5"}},{"arxiv_id":"2412.13147","paper":"/paper/are-your-llms-capable-of-stable-reasoning","title":"Are Your LLMs Capable of Stable Reasoning?","date":"2024-12-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-compass/gpassk","path":"lighteval/src/lighteval_metric.py","file_url":"https://github.com/open-compass/gpassk/blob/HEAD/lighteval/src/lighteval_metric.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d2a746e088a94b53","mcp_get_code":{"code_sha256":"d2a746e088a94b53"}},{"arxiv_id":"2410.22821","paper":"/paper/evocodebench-an-evolving-code-generation-1","title":"EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations","date":"2024-10-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/EvoCodeBench","path":"pass_k.py","file_url":"https://github.com/seketeam/EvoCodeBench/blob/HEAD/pass_k.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"41f57204e706d18f","mcp_get_code":{"code_sha256":"41f57204e706d18f"}},{"arxiv_id":"2405.19856","paper":"/paper/deveval-a-manually-annotated-code-generation","title":"DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/deveval","path":"pass_k.py","file_url":"https://github.com/seketeam/deveval/blob/HEAD/pass_k.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"41f57204e706d18f","mcp_get_code":{"code_sha256":"41f57204e706d18f"}},{"arxiv_id":"2404.00599","paper":"/paper/evocodebench-an-evolving-code-generation","title":"EvoCodeBench: An Evolving Code Generation Benchmark Aligned with Real-World Code Repositories","date":"2024-03-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"seketeam/evocodebench","path":"pass_k.py","file_url":"https://github.com/seketeam/evocodebench/blob/HEAD/pass_k.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"41f57204e706d18f","mcp_get_code":{"code_sha256":"41f57204e706d18f"}}]}