{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001728323,0.0002948509,0.0003558775,0.0006680881,0.001408842,0.0005931039,0.0009692339,0.0003006342,0.06376603],"category_scores_gemma":[0.0005257847,0.0003407504,0.0001388129,0.0006994763,0.00003273317,0.0002152311,0.000769875,0.0008200597,0.003822508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000521427,"about_ca_system_score_gemma":0.000005642939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004059237,"about_ca_topic_score_gemma":0.000002081933,"domain_scores_codex":[0.9974975,0.0003690933,0.0005075131,0.0005459454,0.0005407589,0.0005392172],"domain_scores_gemma":[0.9987651,0.00005830685,0.0001285076,0.0007553156,0.0001453807,0.0001473829],"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":[0.00008131667,0.00008081766,1.238367e-7,0.0002628396,0.0000693706,0.00001217747,0.00006209527,0.0006115334,0.0001560634,0.000009227567,0.9959483,0.002706127],"study_design_scores_gemma":[0.001066103,0.0003234083,0.000007221649,0.00005378046,0.00005604035,0.00008136252,0.00007713271,0.001294823,0.00003029651,0.000007217076,0.996709,0.0002936257],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001280893,0.00009531619,0.0006653897,0.00001788887,0.0006961811,0.001281054,0.995312,0.0007002155,0.00110383],"genre_scores_gemma":[0.0005841636,0.00009082355,0.00001178743,0.00003808695,0.0004621438,0.00000120471,0.9973524,0.001296722,0.0001626908],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05994352,"threshold_uncertainty_score":0.9999045,"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."}}