{"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-conversation","entry":"parse_conversation","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":4,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"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":"2607.02510","paper":"/paper/arxiv-2607-02510","title":"Online Safety Monitoring for LLMs","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"monasch/llm-monitor","path":"python_scripts/llama_guard.py","file_url":"https://github.com/monasch/llm-monitor/blob/HEAD/python_scripts/llama_guard.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"309d7502de75dc46","mcp_get_code":{"code_sha256":"309d7502de75dc46"}},{"arxiv_id":"2606.07402","paper":"/paper/arxiv-2606-07402","title":"M 3 Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"WujiangXu/A-mem","path":"load_dataset.py","file_url":"https://github.com/WujiangXu/A-mem/blob/HEAD/load_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a1510da2b417c43","mcp_get_code":{"code_sha256":"4a1510da2b417c43"}},{"arxiv_id":"2604.18349","paper":"/paper/arxiv-2604-18349","title":"HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"ZeroLoss-Lab/HiGMem","path":"load_dataset.py","file_url":"https://github.com/ZeroLoss-Lab/HiGMem/blob/HEAD/load_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a1510da2b417c43","mcp_get_code":{"code_sha256":"4a1510da2b417c43"}},{"arxiv_id":"2502.12110","paper":"/paper/a-mem-agentic-memory-for-llm-agents","title":"A-MEM: Agentic Memory for LLM Agents","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wujiangxu/agenticmemory","path":"load_dataset.py","file_url":"https://github.com/wujiangxu/agenticmemory/blob/HEAD/load_dataset.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4a1510da2b417c43","mcp_get_code":{"code_sha256":"4a1510da2b417c43"}},{"arxiv_id":"2405.19444","paper":"/paper/mathchat-benchmarking-mathematical-reasoning","title":"MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions","date":"2024-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhenwen-nlp/mathchat","path":"Eval_Scripts/error_analysis_llama.py","file_url":"https://github.com/zhenwen-nlp/mathchat/blob/HEAD/Eval_Scripts/error_analysis_llama.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"8e1d617cb7b9976e","mcp_get_code":{"code_sha256":"8e1d617cb7b9976e"}},{"arxiv_id":"2403.07008","paper":"/paper/autoeval-done-right-using-synthetic-data-for","title":"AutoEval Done Right: Using Synthetic Data for Model Evaluation","date":"2024-03-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pierreboyeau/autoeval","path":"workflow/scripts/llm_experiment.py","file_url":"https://github.com/pierreboyeau/autoeval/blob/HEAD/workflow/scripts/llm_experiment.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6117e0d3fbaeb640","mcp_get_code":{"code_sha256":"6117e0d3fbaeb640"}}]}