{"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/chat-gpt","entry":"chat_gpt","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":0,"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":0,"n_samples_fingerprinted":0,"n_places":8,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":6},"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":"2510.21891","paper":"/paper/arxiv-2510-21891","title":"Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"dhrupadb/semantic_isotropy","path":"lib/python/semantic_isotropy/llm/chat.py","file_url":"https://github.com/dhrupadb/semantic_isotropy/blob/HEAD/lib/python/semantic_isotropy/llm/chat.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":"be3e7e1de0d35f5e","mcp_get_code":{"code_sha256":"be3e7e1de0d35f5e"}},{"arxiv_id":"2412.11605","paper":"/paper/spar-self-play-with-tree-search-refinement-to","title":"SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models","date":"2024-12-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/SPaR","path":"src/tree_search.py","file_url":"https://github.com/thu-coai/SPaR/blob/HEAD/src/tree_search.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":"6af0652b632cb33b","mcp_get_code":{"code_sha256":"6af0652b632cb33b"}},{"arxiv_id":"2402.10178","paper":"/paper/tdag-a-multi-agent-framework-based-on-dynamic","title":"TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxwang8775/tdag","path":"run/run_webshop.py","file_url":"https://github.com/yxwang8775/tdag/blob/HEAD/run/run_webshop.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"28521e6bc5ae5c0b","mcp_get_code":{"code_sha256":"28521e6bc5ae5c0b"}},{"arxiv_id":"2402.10178","paper":"/paper/tdag-a-multi-agent-framework-based-on-dynamic","title":"TDAG: A Multi-Agent Framework based on Dynamic Task Decomposition and Agent Generation","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yxwang8775/tdag","path":"utils/api_service.py","file_url":"https://github.com/yxwang8775/tdag/blob/HEAD/utils/api_service.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d4800823ff95ae22","mcp_get_code":{"code_sha256":"d4800823ff95ae22"}},{"arxiv_id":"2311.04155","paper":"/paper/black-box-prompt-optimization-aligning-large","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/bpo","path":"src/data_construction/chatgpt_infer.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/data_construction/chatgpt_infer.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":"c6e5695547deaf80","mcp_get_code":{"code_sha256":"c6e5695547deaf80"}},{"arxiv_id":"2311.04155","paper":"/paper/black-box-prompt-optimization-aligning-large","title":"Black-Box Prompt Optimization: Aligning Large Language Models without Model Training","date":"2023-11-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-coai/bpo","path":"src/evaluation/gpt4_score.py","file_url":"https://github.com/thu-coai/bpo/blob/HEAD/src/evaluation/gpt4_score.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":"1350e6afade56462","mcp_get_code":{"code_sha256":"1350e6afade56462"}},{"arxiv_id":"2024.acl-long.176","paper":null,"title":"arXiv:2024.acl-long.176","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thu-coai/BPO","path":"src/data_construction/chatgpt_infer.py","file_url":"https://github.com/thu-coai/BPO/blob/HEAD/src/data_construction/chatgpt_infer.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":"c6e5695547deaf80","mcp_get_code":{"code_sha256":"c6e5695547deaf80"}},{"arxiv_id":"2024.acl-long.176","paper":null,"title":"arXiv:2024.acl-long.176","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"thu-coai/BPO","path":"src/evaluation/gpt4_score.py","file_url":"https://github.com/thu-coai/BPO/blob/HEAD/src/evaluation/gpt4_score.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":"1350e6afade56462","mcp_get_code":{"code_sha256":"1350e6afade56462"}}]}