{"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/read-predictions","entry":"read_predictions","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":8,"n_papers_ran":2,"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":9,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":9,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":3,"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":"2509.24088","paper":"/paper/arxiv-2509-24088","title":"CORRECT: Condensed Error Recognition via Knowledge Transfer in Multi-agent Systems","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"UIUC-MLSys/CORRECT","path":"src/evaluate.py","file_url":"https://github.com/UIUC-MLSys/CORRECT/blob/HEAD/src/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"d7e23813e9b7b1b0","mcp_get_code":{"code_sha256":"d7e23813e9b7b1b0"}},{"arxiv_id":"2505.00212","paper":"/paper/which-agent-causes-task-failures-and-when-on","title":"Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems","date":"2025-04-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mingyin1/agents_failure_attribution","path":"Automated_FA/evaluate.py","file_url":"https://github.com/mingyin1/agents_failure_attribution/blob/HEAD/Automated_FA/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"23b923056bf19e53","mcp_get_code":{"code_sha256":"23b923056bf19e53"}},{"arxiv_id":"2312.15614","paper":"/paper/a-comprehensive-evaluation-of-parameter","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwtnju/peft","path":"clone/evaluator/evaluator.py","file_url":"https://github.com/zwtnju/peft/blob/HEAD/clone/evaluator/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bc0a52fa08b13927","mcp_get_code":{"code_sha256":"bc0a52fa08b13927"}},{"arxiv_id":"2312.15614","paper":"/paper/a-comprehensive-evaluation-of-parameter","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","date":"2023-12-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zwtnju/peft","path":"defect/evaluator/evaluator.py","file_url":"https://github.com/zwtnju/peft/blob/HEAD/defect/evaluator/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"c5842e6ad19a6199","mcp_get_code":{"code_sha256":"c5842e6ad19a6199"}},{"arxiv_id":"2311.15781","paper":"/paper/increasing-coverage-and-precision-of-textual","title":"Increasing Coverage and Precision of Textual Information in Multilingual Knowledge Graphs","date":"2023-11-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-kge","path":"src/evaluation/evaluate_coverage.py","file_url":"https://github.com/apple/ml-kge/blob/HEAD/src/evaluation/evaluate_coverage.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":"7c669eba753b0ab5","mcp_get_code":{"code_sha256":"7c669eba753b0ab5"}},{"arxiv_id":"2206.08474","paper":"/paper/xlcost-a-benchmark-dataset-for-cross-lingual","title":"XLCoST: A Benchmark Dataset for Cross-lingual Code Intelligence","date":"2022-06-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"reddy-lab-code-research/xlcost","path":"code/codesearch/code2codesearch/evaluator/evaluator.py","file_url":"https://github.com/reddy-lab-code-research/xlcost/blob/HEAD/code/codesearch/code2codesearch/evaluator/evaluator.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":"bd511beb7477ff28","mcp_get_code":{"code_sha256":"bd511beb7477ff28"}},{"arxiv_id":"2112.02268","paper":"/paper/bridging-pre-trained-models-and-downstream","title":"Bridging Pre-trained Models and Downstream Tasks for Source Code Understanding","date":"2021-12-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wangdeze18/DACL","path":"algorithm_classification/evaluator/eva_MAP.py","file_url":"https://github.com/wangdeze18/DACL/blob/HEAD/algorithm_classification/evaluator/eva_MAP.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a82333e3033af699","mcp_get_code":{"code_sha256":"a82333e3033af699"}},{"arxiv_id":"2008.04838","paper":"/paper/transnet-v2-an-effective-deep-network","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","date":"2020-08-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shallwe999/TransNetV2-SBD-Visualize","path":"utils.py","file_url":"https://github.com/shallwe999/TransNetV2-SBD-Visualize/blob/HEAD/utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fa843917bfca3cfb","mcp_get_code":{"code_sha256":"fa843917bfca3cfb"}},{"arxiv_id":"2007.15207","paper":"/paper/mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","date":"2020-07-30","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"apple/ml-mkqa","path":"mkqa_eval.py","file_url":"https://github.com/apple/ml-mkqa/blob/HEAD/mkqa_eval.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":"e2e26d4764ff96b4","mcp_get_code":{"code_sha256":"e2e26d4764ff96b4"}}]}