{"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/check-correct","entry":"check_correct","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":6,"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":5,"n_samples_ran":3,"n_samples_fingerprinted":1,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":1,"ran":1,"unverified":2},"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":"2505.02735","paper":"/paper/formalmath-benchmarking-formal-mathematical","title":"FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sphere-ai-lab/formalmath-bench","path":"evaluate_results.py","file_url":"https://github.com/sphere-ai-lab/formalmath-bench/blob/HEAD/evaluate_results.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":"f7fa34e021f66336","mcp_get_code":{"code_sha256":"f7fa34e021f66336"}},{"arxiv_id":"2411.13112","paper":"/paper/drivemllm-a-benchmark-for-spatial","title":"DriveMLLM: A Benchmark for Spatial Understanding with Multimodal Large Language Models in Autonomous Driving","date":"2024-11-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiandaguo/drive-mllm","path":"training/grpo/grpo.py","file_url":"https://github.com/xiandaguo/drive-mllm/blob/HEAD/training/grpo/grpo.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"23d0e56a5a85e59d","mcp_get_code":{"code_sha256":"23d0e56a5a85e59d"}},{"arxiv_id":"2411.00715","paper":"/paper/b-cosification-transforming-deep-neural","title":"B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable","date":"2024-11-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shrebox/B-cosification","path":"evaluate.py","file_url":"https://github.com/shrebox/B-cosification/blob/HEAD/evaluate.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"d853932b4bc4ddc6","mcp_get_code":{"code_sha256":"d853932b4bc4ddc6"}},{"arxiv_id":"2405.09851","paper":"/paper/region-of-interest-detection-in-melanocytic-1","title":"Region of Interest Detection in Melanocytic Skin Tumor Whole Slide Images -- Nevus & Melanoma","date":"2024-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cymichael/roi_detection","path":"score_pcla_3class.py","file_url":"https://github.com/cymichael/roi_detection/blob/HEAD/score_pcla_3class.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"255cfced4b740086","mcp_get_code":{"code_sha256":"255cfced4b740086"}},{"arxiv_id":"2306.10898","paper":"/paper/b-cos-alignment-for-inherently-interpretable","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","date":"2023-06-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"d853932b4bc4ddc6","mcp_get_code":{"code_sha256":"d853932b4bc4ddc6"}},{"arxiv_id":"2023.emnlp-main.447","paper":null,"title":"arXiv:2023.emnlp-main.447","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wietsedv/dumb","path":"research/export_correct.py","file_url":"https://github.com/wietsedv/dumb/blob/HEAD/research/export_correct.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":"3d3d9cd6a76977b1","mcp_get_code":{"code_sha256":"3d3d9cd6a76977b1"}}]}