{"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/parse-yes-no","entry":"parse_yes_no","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":5,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":1,"ran_draft_wrong":0,"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":"2608.11775","paper":"/paper/arxiv-2608-11775","title":"The Sleeping Agent: What Gist-Based Context Compression Loses and Why","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"kyrkewood/sleeping-agent","path":"src/judge.py","file_url":"https://github.com/kyrkewood/sleeping-agent/blob/HEAD/src/judge.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a1c7c0dc37ef0b5f","mcp_get_code":{"code_sha256":"a1c7c0dc37ef0b5f"}},{"arxiv_id":"2505.11765","paper":"/paper/omac-a-broad-optimization-framework-for-llm","title":"OMAC: A Broad Optimization Framework for LLM-Based Multi-Agent Collaboration","date":"2025-05-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xiwenchao/OMAC","path":"code/MATH/evol_eval_math.py","file_url":"https://github.com/xiwenchao/OMAC/blob/HEAD/code/MATH/evol_eval_math.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efece58874c297b1","mcp_get_code":{"code_sha256":"efece58874c297b1"}},{"arxiv_id":"2503.20648","paper":"/paper/tn-eval-rubric-and-evaluation-protocols-for","title":"TN-Eval: Rubric and Evaluation Protocols for Measuring the Quality of Behavioral Therapy Notes","date":"2025-03-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/TN-Eval","path":"src/run_metrics_reference_free.py","file_url":"https://github.com/amazon-science/TN-Eval/blob/HEAD/src/run_metrics_reference_free.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":"70be1bae7ab12c5d","mcp_get_code":{"code_sha256":"70be1bae7ab12c5d"}},{"arxiv_id":"2310.02170","paper":"/paper/dynamic-llm-agent-network-an-llm-agent","title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","date":"2023-10-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"salt-nlp/dylan","path":"code/MATH/eval_math.py","file_url":"https://github.com/salt-nlp/dylan/blob/HEAD/code/MATH/eval_math.py","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"efece58874c297b1","mcp_get_code":{"code_sha256":"efece58874c297b1"}},{"arxiv_id":"2025.emnlp-industry.190","paper":null,"title":"arXiv:2025.emnlp-industry.190","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ismail31416/CAPSTONE","path":"capstone/eval/metrics.py","file_url":"https://github.com/ismail31416/CAPSTONE/blob/HEAD/capstone/eval/metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"339d8d1b6b73b3e3","mcp_get_code":{"code_sha256":"339d8d1b6b73b3e3"}}]}