{"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/get-cot-prompt","entry":"get_cot_prompt","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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":1,"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":"2410.16676","paper":"/paper/improving-causal-reasoning-in-large-language","title":"Improving Causal Reasoning in Large Language Models: A Survey","date":"2024-10-22","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chendl02/awesome-llm-causal-reasoning","path":"src/eval_all.py","file_url":"https://github.com/chendl02/awesome-llm-causal-reasoning/blob/HEAD/src/eval_all.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":"5efd35f5c46aee1b","mcp_get_code":{"code_sha256":"5efd35f5c46aee1b"}},{"arxiv_id":"2407.13237","paper":"/paper/llm-empowered-state-representation-for","title":"LLM-Empowered State Representation for Reinforcement Learning","date":"2024-07-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thu-rllab/LESR","path":"lesr_main.py","file_url":"https://github.com/thu-rllab/LESR/blob/HEAD/lesr_main.py","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f5e2428b80e2f9aa","mcp_get_code":{"code_sha256":"f5e2428b80e2f9aa"}},{"arxiv_id":"2403.11807","paper":"/paper/how-far-are-we-on-the-decision-making-of-llms","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments","date":"2024-03-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cuhk-arise/gamabench","path":"server.py","file_url":"https://github.com/cuhk-arise/gamabench/blob/HEAD/server.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"code_sha256_prefix":"e23367e419898eca","mcp_get_code":{"code_sha256":"e23367e419898eca"}},{"arxiv_id":"2312.16702","paper":"/paper/rethinking-tabular-data-understanding-with","title":"Rethinking Tabular Data Understanding with Large Language Models","date":"2023-12-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Leolty/tablellm","path":"run_helper.py","file_url":"https://github.com/Leolty/tablellm/blob/HEAD/run_helper.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"0cf45bc29c09c932","mcp_get_code":{"code_sha256":"0cf45bc29c09c932"}},{"arxiv_id":"2306.06283","paper":"/paper/14-examples-of-how-llms-can-transform","title":"14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model Hackathon","date":"2023-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"qai222/llm_organic_synthesis","path":"workplace_cot/cot_gpt.py","file_url":"https://github.com/qai222/llm_organic_synthesis/blob/HEAD/workplace_cot/cot_gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9505b9029260a857","mcp_get_code":{"code_sha256":"9505b9029260a857"}}]}