{"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/process-answer","entry":"process_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":4,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":3,"n_places":6,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":2,"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":"2509.23415","paper":"/paper/arxiv-2509-23415","title":"From Conversation to Query Execution: Benchmarking User and Tool Interactions for EHR Database Agents","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"glee4810/EHR-ChatQA","path":"src/utils.py","file_url":"https://github.com/glee4810/EHR-ChatQA/blob/HEAD/src/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b2b4771dd457e441","mcp_get_code":{"code_sha256":"b2b4771dd457e441"}},{"arxiv_id":"2505.02735","paper":"/paper/formalmath-benchmarking-formal-mathematical","title":"FormalMATH: Benchmarking Formal Mathematical Reasoning of Large Language Models","date":"2025-05-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sphere-ai-lab/formalmath-bench","path":"verify_answers.py","file_url":"https://github.com/sphere-ai-lab/formalmath-bench/blob/HEAD/verify_answers.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":"aa547b75c4c59632","mcp_get_code":{"code_sha256":"aa547b75c4c59632"}},{"arxiv_id":"2402.11863","paper":"/paper/how-interpretable-are-reasoning-explanations","title":"How Interpretable are Reasoning Explanations from Prompting Large Language Models?","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wj210/cot_interpretability","path":"template/refine_template.py","file_url":"https://github.com/wj210/cot_interpretability/blob/HEAD/template/refine_template.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9e0cd81e8cf96360","mcp_get_code":{"code_sha256":"9e0cd81e8cf96360"}},{"arxiv_id":"2402.10962","paper":"/paper/measuring-and-controlling-instruction-in","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","date":"2024-02-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"likenneth/persona_drift","path":"utils.py","file_url":"https://github.com/likenneth/persona_drift/blob/HEAD/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7bd611331e824bed","mcp_get_code":{"code_sha256":"7bd611331e824bed"}},{"arxiv_id":"2301.07695","paper":"/paper/ehrsql-a-practical-text-to-sql-benchmark-for-1","title":"EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records","date":"2023-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"glee4810/EHRSQL","path":"evaluate.py","file_url":"https://github.com/glee4810/EHRSQL/blob/HEAD/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"CC-BY-4.0","inline_ok":false,"code_sha256_prefix":"8b5b025f2da2bbf5","mcp_get_code":{"code_sha256":"8b5b025f2da2bbf5"}},{"arxiv_id":"2109.05014","paper":"/paper/an-empirical-study-of-gpt-3-for-few-shot","title":"An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA","date":"2021-09-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"microsoft/PICa","path":"gpt3_api_okvqa.py","file_url":"https://github.com/microsoft/PICa/blob/HEAD/gpt3_api_okvqa.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7af8e1a13b97aae9","mcp_get_code":{"code_sha256":"7af8e1a13b97aae9"}}]}