{"id":"W3024356476","doi":"10.1007/s10664-020-09878-9","title":"On the time-based conclusion stability of cross-project defect prediction models","year":2020,"lang":"en","type":"preprint","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Stability (learning theory); Computer science; Software; Predictive modelling; Product (mathematics); Limit (mathematics); Data mining; Time limit; Analytics; Data science; Empirical research; Econometrics; Reliability engineering; Statistics; Machine learning; Mathematics; Engineering; Systems engineering","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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00119249,0.0005626199,0.0006346086,0.0002614307,0.0001352895,0.0002657011,0.002273106,0.0004639075,0.00004129364],"category_scores_gemma":[0.01018346,0.0004514486,0.0005248895,0.000885552,0.0001068478,0.000233586,0.002514463,0.001890225,0.00003580355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004824474,"about_ca_system_score_gemma":0.000538572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004456575,"about_ca_topic_score_gemma":3.607605e-7,"domain_scores_codex":[0.996013,0.0001950782,0.0006746554,0.001179395,0.001338309,0.0005995297],"domain_scores_gemma":[0.9898993,0.007568093,0.0001675652,0.001837602,0.0003116339,0.0002157804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000343278,0.0000835348,0.01016482,0.0005089681,0.00007981791,0.00001467723,0.0003661675,0.9866076,0.0002526774,0.0003378683,0.001312641,0.000236965],"study_design_scores_gemma":[0.0002885892,0.0002011673,0.01560464,0.0003107572,0.0000168846,0.000002199585,0.000001122333,0.9790263,0.002911403,0.001069504,0.0001703155,0.0003971529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2354688,0.0001486282,0.760733,0.0004163155,0.0005636569,0.0008056509,0.0001086977,0.001736491,0.00001875912],"genre_scores_gemma":[0.9682839,0.000005675488,0.03105244,0.0001424255,0.000165395,0.0002024159,0.0000508444,0.00008748394,0.000009437477],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7328151,"threshold_uncertainty_score":0.9997937,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07151071104906312,"score_gpt":0.3198984049856826,"score_spread":0.2483876939366194,"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."}}