{"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/verify-extraction","entry":"verify_extraction","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":2,"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":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2509.19003","paper":"/paper/arxiv-2509-19003","title":"Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"baaivision/CoS","path":"eval/mathvista/extract_answer.py","file_url":"https://github.com/baaivision/CoS/blob/HEAD/eval/mathvista/extract_answer.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":"db6b1bcee6eab96f","mcp_get_code":{"code_sha256":"db6b1bcee6eab96f"}},{"arxiv_id":"2412.09413","paper":"/paper/imitate-explore-and-self-improve-a","title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/virgo","path":"evaluation/MathVerse/evaluation/extract_answer_s1.py","file_url":"https://github.com/rucaibox/virgo/blob/HEAD/evaluation/MathVerse/evaluation/extract_answer_s1.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"350d0bc5afcc4922","mcp_get_code":{"code_sha256":"350d0bc5afcc4922"}},{"arxiv_id":"2410.17885","paper":"/paper/r-cot-reverse-chain-of-thought-problem","title":"R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models","date":"2024-10-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dle666/r-cot","path":"MathVista_eval/evaluation/extract_answer.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/extract_answer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a7852c6582967cfa","mcp_get_code":{"code_sha256":"a7852c6582967cfa"}},{"arxiv_id":"2409.00147","paper":"/paper/multimath-bridging-visual-and-mathematical","title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","date":"2024-08-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pengshuai-rin/multimath","path":"eval_mathvista/extract_answer.py","file_url":"https://github.com/pengshuai-rin/multimath/blob/HEAD/eval_mathvista/extract_answer.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"350d0bc5afcc4922","mcp_get_code":{"code_sha256":"350d0bc5afcc4922"}},{"arxiv_id":"Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","paper":null,"title":"arXiv:Guo_Integrating_Visual_Interpretation_and_Linguistic_Reasoning_for_Geometric_Problem_Solving_ICCV_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"guozix/DVLR","path":"eval/MathVerse/evaluation/extract_answer.py","file_url":"https://github.com/guozix/DVLR/blob/HEAD/eval/MathVerse/evaluation/extract_answer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a7852c6582967cfa","mcp_get_code":{"code_sha256":"a7852c6582967cfa"}}]}