{"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/evaluate-code","entry":"evaluate_code","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":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":4,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"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_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6a7cafccc873c34d","mcp_get_code":{"code_sha256":"6a7cafccc873c34d"}},{"arxiv_id":"2410.02958","paper":"/paper/automl-agent-a-multi-agent-llm-framework-for","title":"AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML","date":"2024-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"DeepAuto-AI/automl-agent","path":"experiments/evaluation.py","file_url":"https://github.com/DeepAuto-AI/automl-agent/blob/HEAD/experiments/evaluation.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"ee22e84b6c85957b","mcp_get_code":{"code_sha256":"ee22e84b6c85957b"}},{"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_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":"6a7cafccc873c34d","mcp_get_code":{"code_sha256":"6a7cafccc873c34d"}},{"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_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":"6a7cafccc873c34d","mcp_get_code":{"code_sha256":"6a7cafccc873c34d"}},{"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_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":"6a7cafccc873c34d","mcp_get_code":{"code_sha256":"6a7cafccc873c34d"}},{"arxiv_id":"2007.08095","paper":"/paper/synthesize-execute-and-debug-learning-to","title":"Synthesize, Execute and Debug: Learning to Repair for Neural Program Synthesis","date":"2020-07-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sunblaze-ucb/SED","path":"program_synthesis/datasets/executor.py","file_url":"https://github.com/sunblaze-ucb/SED/blob/HEAD/program_synthesis/datasets/executor.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fef08668e5cc872a","mcp_get_code":{"code_sha256":"fef08668e5cc872a"}},{"arxiv_id":"1807.03168","paper":"/paper/naps-natural-program-synthesis-dataset","title":"NAPS: Natural Program Synthesis Dataset","date":"2018-07-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nearai/program_synthesis","path":"program_synthesis/algolisp/dataset/executor.py","file_url":"https://github.com/nearai/program_synthesis/blob/HEAD/program_synthesis/algolisp/dataset/executor.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":"4f400a0410389c02","mcp_get_code":{"code_sha256":"4f400a0410389c02"}}]}