{"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/compare-numerical-ans","entry":"compare_numerical_ans","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":0,"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":1,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2604.11056","paper":"/paper/arxiv-2604-11056","title":"Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"QwenLM/Qwen2.5-Math","path":"evaluation/math_utils.py","file_url":"https://github.com/QwenLM/Qwen2.5-Math/blob/HEAD/evaluation/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2510.06307","paper":"/paper/arxiv-2510-06307","title":"Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"dengwentao99/BCCS","path":"MATH/math_utils.py","file_url":"https://github.com/dengwentao99/BCCS/blob/HEAD/MATH/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2505.19716","paper":"/paper/concise-reasoning-big-gains-pruning-long","title":"Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting","date":"2025-05-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evanwu1125/litecot","path":"eval/Qwen2.5-Math/evaluation/math_utils.py","file_url":"https://github.com/evanwu1125/litecot/blob/HEAD/eval/Qwen2.5-Math/evaluation/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2504.20571","paper":"/paper/reinforcement-learning-for-reasoning-in-large","title":"Reinforcement Learning for Reasoning in Large Language Models with One Training Example","date":"2025-04-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ypwang61/one-shot-rlvr","path":"Qwen2.5-Eval/evaluation/math_utils.py","file_url":"https://github.com/ypwang61/one-shot-rlvr/blob/HEAD/Qwen2.5-Eval/evaluation/math_utils.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":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2504.05185","paper":"/paper/concise-reasoning-via-reinforcement-learning","title":"Concise Reasoning via Reinforcement Learning","date":"2025-04-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ai-wand/concise-reasoning","path":"eval/math_utils.py","file_url":"https://github.com/ai-wand/concise-reasoning/blob/HEAD/eval/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2410.07985","paper":"/paper/omni-math-a-universal-olympiad-level","title":"Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kbsdjames/omni-math-rule","path":"evaluation/math_utils.py","file_url":"https://github.com/kbsdjames/omni-math-rule/blob/HEAD/evaluation/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}},{"arxiv_id":"2405.14365","paper":"/paper/jiuzhang3-0-efficiently-improving","title":"JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models","date":"2024-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/jiuzhang3.0","path":"eval/math_utils.py","file_url":"https://github.com/rucaibox/jiuzhang3.0/blob/HEAD/eval/math_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"81082f28e1440f9d","mcp_get_code":{"code_sha256":"81082f28e1440f9d"}}]}