{"id":"W4384026501","doi":"10.1109/msr59073.2023.00085","title":"Defectors: A Large, Diverse Python Dataset for Defect Prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Python (programming language); Computer science; Approx; Machine learning; Artificial intelligence; Source lines of code; Source code; Data mining; Programming language; Software; Operating system","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001282414,0.001606227,0.0006507442,0.0036146,0.0007465841,0.0007826888,0.002268924,0.001340034,0.003686301],"category_scores_gemma":[0.006792988,0.000495394,0.001049166,0.003854283,0.0008436788,0.001738337,0.002051404,0.001954438,0.005063416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009160871,"about_ca_system_score_gemma":0.002229611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01024717,"about_ca_topic_score_gemma":0.01671146,"domain_scores_codex":[0.9981855,0.0001932136,0.0002016786,0.0003630675,0.0008282025,0.0002284172],"domain_scores_gemma":[0.9955201,0.0008248826,0.0006058628,0.001372085,0.001166119,0.0005109996],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001005318,0.0009185289,0.06635253,0.001469115,0.0002301066,0.001226699,0.0004173284,0.01729124,0.00938968,0.00315143,0.8134291,0.08511894],"study_design_scores_gemma":[0.0008237,0.0009708845,0.2392643,0.0004538985,0.0002197433,0.003016535,0.0007663391,0.1632659,0.03279707,0.01554823,0.5424407,0.0004327863],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.113544,0.000565284,0.01520521,0.0008602719,0.000223258,0.0004416886,0.8244975,0.03896041,0.005702391],"genre_scores_gemma":[0.07544892,0.0002407106,0.01640607,0.0002200546,0.00004768114,0.0004646986,0.9035211,0.001399436,0.002251309],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01024717,"threshold_uncertainty_score":0.02037507,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06861649982258129,"score_gpt":0.3296325204209574,"score_spread":0.2610160205983761,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}