{"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-answers","entry":"compare_answers","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-25T09:33:49+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":8,"n_papers_ran":7,"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":8,"n_samples_ran":7,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"ran_fixture":0,"ran":6,"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":"2606.29424","paper":"/paper/arxiv-2606-29424","title":"ENTROROUTER: Learning Efficient Model Routing via Entropy Regulation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"huggingface/Math-Verify","path":"evaluate_model_outputs.py","file_url":"https://github.com/huggingface/Math-Verify/blob/HEAD/evaluate_model_outputs.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"662b87687f2f200a","mcp_get_code":{"code_sha256":"662b87687f2f200a"}},{"arxiv_id":"2505.20347","paper":"/paper/serl-self-play-reinforcement-learning-for","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wantbook-book/serl","path":"evaluation/Math-Benchmarks/evaluate_outputs.py","file_url":"https://github.com/wantbook-book/serl/blob/HEAD/evaluation/Math-Benchmarks/evaluate_outputs.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"662b87687f2f200a","mcp_get_code":{"code_sha256":"662b87687f2f200a"}},{"arxiv_id":"2502.20122","paper":"/paper/self-training-elicits-concise-reasoning-in","title":"Self-Training Elicits Concise Reasoning in Large Language Models","date":"2025-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tergelmunkhbat/concise-reasoning","path":"src/preprocess.py","file_url":"https://github.com/tergelmunkhbat/concise-reasoning/blob/HEAD/src/preprocess.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"46e84dfabd0695d0","mcp_get_code":{"code_sha256":"46e84dfabd0695d0"}},{"arxiv_id":"2410.10799","paper":"/paper/towards-foundation-models-for-3d-vision-how","title":"Towards Foundation Models for 3D Vision: How Close Are We?","date":"2024-10-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"princeton-vl/uniqa-3d","path":"Human_Study/clevr_vqa/utils.py","file_url":"https://github.com/princeton-vl/uniqa-3d/blob/HEAD/Human_Study/clevr_vqa/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"c3c486bf7368e6dd","mcp_get_code":{"code_sha256":"c3c486bf7368e6dd"}},{"arxiv_id":"2406.10149","paper":"/paper/babilong-testing-the-limits-of-llms-with-long","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"booydar/babilong","path":"babilong/babilong_utils.py","file_url":"https://github.com/booydar/babilong/blob/HEAD/babilong/babilong_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"13c862882ed08796","mcp_get_code":{"code_sha256":"13c862882ed08796"}},{"arxiv_id":"2406.10149","paper":"/paper/babilong-testing-the-limits-of-llms-with-long","title":"BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack","date":"2024-06-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"booydar/babilong","path":"babilong/metrics.py","file_url":"https://github.com/booydar/babilong/blob/HEAD/babilong/metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"eebaceb4246b1413","mcp_get_code":{"code_sha256":"eebaceb4246b1413"}},{"arxiv_id":"2311.09603","paper":"/paper/score-a-framework-for-self-contradictory","title":"Self-Contradictory Reasoning Evaluation and Detection","date":"2023-11-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"uscnlp-lime/Self-Contradictory","path":"auto_detection/get_metrics.py","file_url":"https://github.com/uscnlp-lime/Self-Contradictory/blob/HEAD/auto_detection/get_metrics.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"e31f2e11cd735813","mcp_get_code":{"code_sha256":"e31f2e11cd735813"}},{"arxiv_id":"2302.13814","paper":"/paper/an-independent-evaluation-of-chatgpt-on","title":"An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)","date":"2023-02-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lab-v2/chatgpt_mwp_eval","path":"data_with_implementation/source/JSONGPT.py","file_url":"https://github.com/lab-v2/chatgpt_mwp_eval/blob/HEAD/data_with_implementation/source/JSONGPT.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"7392bcd76e77496b","mcp_get_code":{"code_sha256":"7392bcd76e77496b"}},{"arxiv_id":"1804.07656","paper":"/paper/acquisition-of-phrase-correspondences-using","title":"Acquisition of Phrase Correspondences using Natural Deduction Proofs","date":"2018-04-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mynlp/ccg2lambda","path":"en/report_results.py","file_url":"https://github.com/mynlp/ccg2lambda/blob/HEAD/en/report_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":"a348a12b155cc698","mcp_get_code":{"code_sha256":"a348a12b155cc698"}}]}