{"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/clean-code","entry":"clean_code","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":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":5,"n_samples_ran":5,"n_samples_fingerprinted":4,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":3,"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":"2604.22239","paper":"/paper/arxiv-2604-22239","title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Zhanli-Li/MuDABench","path":"agent/agent_runner.py","file_url":"https://github.com/Zhanli-Li/MuDABench/blob/HEAD/agent/agent_runner.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"5b43b0d8ca375888","mcp_get_code":{"code_sha256":"5b43b0d8ca375888"}},{"arxiv_id":"2505.20881","paper":"/paper/generalizable-heuristic-generation-through","title":"Generalizable Heuristic Generation Through Large Language Models with Meta-Optimization","date":"2025-05-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yiding-s/MoH","path":"moh.py","file_url":"https://github.com/yiding-s/MoH/blob/HEAD/moh.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7bb761fcfadb6e28","mcp_get_code":{"code_sha256":"7bb761fcfadb6e28"}},{"arxiv_id":"2409.20550","paper":"/paper/llm-hallucinations-in-practical-code","title":"LLM Hallucinations in Practical Code Generation: Phenomena, Mechanism, and Mitigation","date":"2024-09-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"deepsoftwareanalytics/llmcodinghallucination","path":"eval_original.py","file_url":"https://github.com/deepsoftwareanalytics/llmcodinghallucination/blob/HEAD/eval_original.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c8230eeeb2532352","mcp_get_code":{"code_sha256":"c8230eeeb2532352"}},{"arxiv_id":"2401.04621","paper":"/paper/debugbench-evaluating-debugging-capability-of","title":"DebugBench: Evaluating Debugging Capability of Large Language Models","date":"2024-01-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thunlp/debugbench","path":"dataset_construction/clean_comments.py","file_url":"https://github.com/thunlp/debugbench/blob/HEAD/dataset_construction/clean_comments.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":"84fd42bee7fa9feb","mcp_get_code":{"code_sha256":"84fd42bee7fa9feb"}},{"arxiv_id":"2310.18338","paper":"/paper/small-language-models-fine-tuned-to","title":"Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning","date":"2023-10-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lcs2-iiitd/daslam","path":"LLAMA13B/Context/Environment.py","file_url":"https://github.com/lcs2-iiitd/daslam/blob/HEAD/LLAMA13B/Context/Environment.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"91bfd3001b4da16a","mcp_get_code":{"code_sha256":"91bfd3001b4da16a"}}]}