{"id":"W4393495264","doi":"10.5281/zenodo.5907002","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":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining","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":[0.001685631,0.002608761,0.001273783,0.003679816,0.0009473681,0.001709504,0.002873345,0.002253077,0.01247976],"category_scores_gemma":[0.01002337,0.0008401221,0.001926006,0.006027274,0.000504266,0.002562779,0.00243298,0.002495296,0.02972369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00131049,"about_ca_system_score_gemma":0.00244374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02552817,"about_ca_topic_score_gemma":0.03449,"domain_scores_codex":[0.9970284,0.0003102014,0.0004138007,0.0007236906,0.001102691,0.0004211347],"domain_scores_gemma":[0.9929692,0.0009572071,0.0006436504,0.002239561,0.002534097,0.000656207],"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":[0.0001650004,0.00008096072,0.006759357,0.0004099315,0.0000663555,0.00008060726,0.00003826375,0.001396984,0.0005464333,0.000332784,0.9832678,0.006855525],"study_design_scores_gemma":[0.0006773077,0.0002934534,0.08948039,0.0004147477,0.0001144804,0.0004530187,0.0003760476,0.01603081,0.003826692,0.003270099,0.8848197,0.000243254],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002836772,0.0001545853,0.0006427651,0.0001789284,0.0001280626,0.00006725872,0.9900272,0.004995647,0.0009688087],"genre_scores_gemma":[0.002694411,0.00004077005,0.0008988276,0.00004501713,0.000017613,0.00007882524,0.9956506,0.0001799506,0.0003940389],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02552817,"threshold_uncertainty_score":0.05075914,"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."}}