{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02772964,0.0009094398,0.001608685,0.002269463,0.000936244,0.0028156,0.002494076,0.002226517,0.003733435],"category_scores_gemma":[0.1673065,0.0006561574,0.001267279,0.001349957,0.002021301,0.004309156,0.00258683,0.003950706,0.000471892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001708324,"about_ca_system_score_gemma":0.001323066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006959843,"about_ca_topic_score_gemma":0.003522193,"domain_scores_codex":[0.9942,0.003392561,0.0002351861,0.0011983,0.0006909049,0.0002830732],"domain_scores_gemma":[0.7162458,0.2610842,0.006461607,0.006342258,0.008508021,0.001358179],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001203479,0.0002073446,0.02870645,0.0002430945,0.0005321468,0.0002671651,0.0004770511,0.8345982,0.002213557,0.06482403,0.003430249,0.06329714],"study_design_scores_gemma":[0.000009452336,0.00003723403,0.001396286,0.0000232581,0.00003015208,0.00001777798,0.00002863383,0.9866871,0.0003283262,0.01132248,0.0001097197,0.00000970578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3776474,0.002565712,0.6092844,0.003518423,0.0002443677,0.00009405136,0.0005944589,0.0006364219,0.005414866],"genre_scores_gemma":[0.9808966,0.0004131355,0.01599402,0.0002246305,0.0001351492,0.00004480467,0.0005545118,0.0001674063,0.001569642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9722704,"threshold_uncertainty_score":0.1466501,"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."}}