{"id":"W4393745689","doi":"10.5281/zenodo.5907847","title":"ApacheJIT: A Large Dataset for Just-In-Time Defect Prediction","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Industrial Vision Systems and Defect Detection","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","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":[0.001864199,0.002752635,0.001309592,0.003716913,0.001003458,0.001836913,0.002923412,0.002326404,0.01215601],"category_scores_gemma":[0.0104266,0.0009069618,0.002177289,0.006102607,0.0005212605,0.002678656,0.002441736,0.002667279,0.02842827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001333226,"about_ca_system_score_gemma":0.002480285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02425832,"about_ca_topic_score_gemma":0.03128957,"domain_scores_codex":[0.9968521,0.0003267361,0.000462274,0.0007744652,0.001160613,0.0004237742],"domain_scores_gemma":[0.9925052,0.001042924,0.0006829084,0.002479468,0.002603343,0.0006862711],"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":[0.0001741537,0.00009194786,0.007532861,0.0004751495,0.00008100793,0.00008645919,0.00004287287,0.001827072,0.0006024165,0.0004061798,0.9811736,0.007506291],"study_design_scores_gemma":[0.0006634513,0.0002867739,0.0800522,0.0004117446,0.0001239503,0.0004479171,0.0003561891,0.01901839,0.003747994,0.003640202,0.8910061,0.0002450712],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002928711,0.0001710467,0.0007877159,0.0002020201,0.0001377798,0.00007340853,0.9886512,0.005989028,0.001059032],"genre_scores_gemma":[0.002836204,0.00004680485,0.001041237,0.00005015564,0.00001829783,0.00008361558,0.9953263,0.0002089081,0.00038842],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02425832,"threshold_uncertainty_score":0.04823422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03686167095575488,"score_gpt":0.2507893453558344,"score_spread":0.2139276744000795,"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."}}