{"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/match-answer","entry":"match_answer","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":3,"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":2,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"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":"2602.02979","paper":"/paper/arxiv-2602-02979","title":"CPMöbius: Iterative Coach-Player Reasoning for Data-Free Reinforcement Learning","date":null,"month_inferred_from_arxiv_id":"2026-02","title_source":"syntology","repo":"thunlp/CPMobius","path":"evaluation/utils/chat_eval.py","file_url":"https://github.com/thunlp/CPMobius/blob/HEAD/evaluation/utils/chat_eval.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":"c780311bfb03fdc4","mcp_get_code":{"code_sha256":"c780311bfb03fdc4"}},{"arxiv_id":"2506.08249","paper":"/paper/2506-08249","title":"RADAR: Benchmarking Language Models on Imperfect Tabular Data","date":"2025-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"kenqgu/radar","path":"radar/evaluate/measure.py","file_url":"https://github.com/kenqgu/radar/blob/HEAD/radar/evaluate/measure.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":"cae88d7799e65f6a","mcp_get_code":{"code_sha256":"cae88d7799e65f6a"}},{"arxiv_id":"2505.24630","paper":"/paper/the-hallucination-dilemma-factuality-aware","title":"The Hallucination Dilemma: Factuality-Aware Reinforcement Learning for Large Reasoning Models","date":"2025-05-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nusnlp/fspo","path":"evaluate/inference.py","file_url":"https://github.com/nusnlp/fspo/blob/HEAD/evaluate/inference.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"2f9d8e7d769c59d5","mcp_get_code":{"code_sha256":"2f9d8e7d769c59d5"}},{"arxiv_id":"2504.02259","paper":"/paper/re-thinking-temporal-search-for-long-form","title":"Re-thinking Temporal Search for Long-Form Video Understanding","date":"2025-04-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"longvideohaystack/tstar","path":"LVHaystackBench/val_qa_results.py","file_url":"https://github.com/longvideohaystack/tstar/blob/HEAD/LVHaystackBench/val_qa_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"8c9b12c71fd729ac","mcp_get_code":{"code_sha256":"8c9b12c71fd729ac"}},{"arxiv_id":"2406.07791","paper":"/paper/judging-the-judges-a-systematic-investigation","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Slimshilin/Position-Bias-Analyzer-Demo","path":"position_bias_analyzer/calculate_consistency_and_preference/consistency_preference_util.py","file_url":"https://github.com/Slimshilin/Position-Bias-Analyzer-Demo/blob/HEAD/position_bias_analyzer/calculate_consistency_and_preference/consistency_preference_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ecf4b23852cb6c61","mcp_get_code":{"code_sha256":"ecf4b23852cb6c61"}},{"arxiv_id":"2406.07791","paper":"/paper/judging-the-judges-a-systematic-investigation","title":"Judging the Judges: A Systematic Study of Position Bias in LLM-as-a-Judge","date":"2024-06-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Slimshilin/Position-Bias-Analyzer-Demo","path":"subeval/subjective/analyze_util.py","file_url":"https://github.com/Slimshilin/Position-Bias-Analyzer-Demo/blob/HEAD/subeval/subjective/analyze_util.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"1f3d4cff9e4b57fd","mcp_get_code":{"code_sha256":"1f3d4cff9e4b57fd"}},{"arxiv_id":"2310.13650","paper":"/paper/botchat-evaluating-llms-capabilities-of","title":"BotChat: Evaluating LLMs' Capabilities of Having Multi-Turn Dialogues","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"open-compass/botchat","path":"botchat/analyze.py","file_url":"https://github.com/open-compass/botchat/blob/HEAD/botchat/analyze.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"dfedb899004eb9d4","mcp_get_code":{"code_sha256":"dfedb899004eb9d4"}}]}