{"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-response","entry":"verify_response","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":5,"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":2,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":1,"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":"2603.05433","paper":"/paper/arxiv-2603-05433","title":"CRISP: Compressed Reasoning via Iterative Self-Policy Distillation","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"HJSang/OPSD_Reasoning_Compression","path":"workspace/src/self_distill_hybrid/sd_verifier.py","file_url":"https://github.com/HJSang/OPSD_Reasoning_Compression/blob/HEAD/workspace/src/self_distill_hybrid/sd_verifier.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"386bd97648077655","mcp_get_code":{"code_sha256":"386bd97648077655"}},{"arxiv_id":"2411.00264","paper":"/paper/turtlebench-a-visual-programming-benchmark-in","title":"TurtleBench: A Visual Programming Benchmark in Turtle Geometry","date":"2024-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sinaris76/turtlebench","path":"models/gemini.py","file_url":"https://github.com/sinaris76/turtlebench/blob/HEAD/models/gemini.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d6259b0d9750cac7","mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}},{"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/generate_response_geo_qwenvl.py","file_url":"https://github.com/dle666/r-cot/blob/HEAD/MathVista_eval/evaluation/generate_response_geo_qwenvl.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d6259b0d9750cac7","mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}},{"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/response.py","file_url":"https://github.com/pengshuai-rin/multimath/blob/HEAD/eval_mathvista/response.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":"d6259b0d9750cac7","mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}},{"arxiv_id":"2406.17294","paper":"/paper/math-llava-bootstrapping-mathematical","title":"Math-LLaVA: Bootstrapping Mathematical Reasoning for Multimodal Large Language Models","date":"2024-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hzq950419/math-llava","path":"evaluation_mathvista/response.py","file_url":"https://github.com/hzq950419/math-llava/blob/HEAD/evaluation_mathvista/response.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":"d6259b0d9750cac7","mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}},{"arxiv_id":"2403.03003","paper":"/paper/feast-your-eyes-mixture-of-resolution","title":"Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models","date":"2024-03-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"luogen1996/llava-hr","path":"llava_hr/eval/model_mathvista.py","file_url":"https://github.com/luogen1996/llava-hr/blob/HEAD/llava_hr/eval/model_mathvista.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":"d6259b0d9750cac7","mcp_get_code":{"code_sha256":"d6259b0d9750cac7"}}]}