{"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/shuffledict","entry":"shuffleDict","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":6,"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":1,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":0,"unverified":0},"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":"2409.04057","paper":"/paper/self-harmonized-chain-of-thought","title":"Self-Harmonized Chain of Thought","date":"2024-09-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Xalp/ECHO","path":"utils.py","file_url":"https://github.com/Xalp/ECHO/blob/HEAD/utils.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":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}},{"arxiv_id":"2407.07099","paper":"/paper/nash-cot-multi-path-inference-with-preference","title":"Nash CoT: Multi-Path Inference with Preference Equilibrium","date":"2024-06-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-science/auto-cot","path":"utils.py","file_url":"https://github.com/amazon-science/auto-cot/blob/HEAD/utils.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":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}},{"arxiv_id":"2401.04925","paper":"/paper/the-impact-of-reasoning-step-length-on-large","title":"The Impact of Reasoning Step Length on Large Language Models","date":"2024-01-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"jmyissb/The-Impact-of-Reasoning-Step-Length-on-Large-Language-Models","path":"utils.py","file_url":"https://github.com/jmyissb/The-Impact-of-Reasoning-Step-Length-on-Large-Language-Models/blob/HEAD/utils.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":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}},{"arxiv_id":"2308.07702","paper":"/paper/better-zero-shot-reasoning-with-role-play","title":"Better Zero-Shot Reasoning with Role-Play Prompting","date":"2023-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"nku-hlt/role-play-prompting","path":"utils.py","file_url":"https://github.com/nku-hlt/role-play-prompting/blob/HEAD/utils.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":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}},{"arxiv_id":"2210.03493","paper":"/paper/automatic-chain-of-thought-prompting-in-large","title":"Automatic Chain of Thought Prompting in Large Language Models","date":"2022-10-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"amazon-research/auto-cot","path":"utils.py","file_url":"https://github.com/amazon-research/auto-cot/blob/HEAD/utils.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":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}},{"arxiv_id":"2024.emnlp-main.758","paper":null,"title":"arXiv:2024.emnlp-main.758","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"HuangOwen/CoT-Influx","path":"utils.py","file_url":"https://github.com/HuangOwen/CoT-Influx/blob/HEAD/utils.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ae2495a11361cc1d","mcp_get_code":{"code_sha256":"ae2495a11361cc1d"}}]}