{"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/sanity-check","entry":"sanity_check","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":7,"n_papers_ran":5,"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":7,"n_samples_ran":4,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":2,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":3},"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":"2605.13076","paper":"/paper/arxiv-2605-13076","title":"TruncProof: A Guardrail for LLM-based JSON Generation under Token-Length Constraints","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Yosshi999/TruncProof","path":"truncproof/lexer.py","file_url":"https://github.com/Yosshi999/TruncProof/blob/HEAD/truncproof/lexer.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"cc5e656f1b51e943","mcp_get_code":{"code_sha256":"cc5e656f1b51e943"}},{"arxiv_id":"2605.03723","paper":"/paper/arxiv-2605-03723","title":"Segmenting Human-LLM Co-authored Text via Change Point Detection","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Mamba413/DetectLLMSegmentation","path":"ruptures/src/ruptures/detection/binseg.py","file_url":"https://github.com/Mamba413/DetectLLMSegmentation/blob/HEAD/ruptures/src/ruptures/detection/binseg.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0c78ca545c72b716","mcp_get_code":{"code_sha256":"0c78ca545c72b716"}},{"arxiv_id":"2503.07358","paper":"/paper/repost-scalable-repository-level-coding","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiqingxyq/RepoST","path":"RepoST/debug.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/debug.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7905fec7f88bb69","mcp_get_code":{"code_sha256":"a7905fec7f88bb69"}},{"arxiv_id":"2503.07358","paper":"/paper/repost-scalable-repository-level-coding","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","date":"2025-03-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiqingxyq/RepoST","path":"RepoST/sandboxing.py","file_url":"https://github.com/yiqingxyq/RepoST/blob/HEAD/RepoST/sandboxing.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dda16da5d86b85db","mcp_get_code":{"code_sha256":"dda16da5d86b85db"}},{"arxiv_id":"2501.14275","paper":"/paper/leveraging-online-olympiad-level-math","title":"Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation","date":"2025-01-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dsl-lab/aops","path":"parse_aops.py","file_url":"https://github.com/dsl-lab/aops/blob/HEAD/parse_aops.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d681a47633b8316f","mcp_get_code":{"code_sha256":"d681a47633b8316f"}},{"arxiv_id":"2410.10986","paper":"/paper/what-does-it-mean-to-be-a-transformer","title":"What Does It Mean to Be a Transformer? Insights from a Theoretical Hessian Analysis","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dalab/transformer-hessian","path":"TransformerLens/transformer_lens/evals.py","file_url":"https://github.com/dalab/transformer-hessian/blob/HEAD/TransformerLens/transformer_lens/evals.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"49d7660823635dab","mcp_get_code":{"code_sha256":"49d7660823635dab"}},{"arxiv_id":"2310.04625","paper":"/paper/copy-suppression-comprehensively","title":"Copy Suppression: Comprehensively Understanding an Attention Head","date":"2023-10-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"callummcdougall/seri-mats-2023-streamlit-pages","path":"transformer_lens/evals.py","file_url":"https://github.com/callummcdougall/seri-mats-2023-streamlit-pages/blob/HEAD/transformer_lens/evals.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"49d7660823635dab","mcp_get_code":{"code_sha256":"49d7660823635dab"}},{"arxiv_id":"2305.09072","paper":"/paper/skin-deep-investigating-subjectivity-in-skin","title":"Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets","date":"2023-05-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"social-futures-lab/skin-deep","path":"study_data/anonymize.py","file_url":"https://github.com/social-futures-lab/skin-deep/blob/HEAD/study_data/anonymize.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"06d4df4aeda24b26","mcp_get_code":{"code_sha256":"06d4df4aeda24b26"}}]}