{"id":"W4385696049","doi":"10.2139/ssrn.4536609","title":"Detecting Concept Drift for the Reliability Prediction of Software Defects Using Instance Interpretation","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Software; Data mining; Reliability (semiconductor); Concept drift; Stability (learning theory); Baseline (sea); Reliability engineering; Machine learning; Artificial intelligence; 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004133052,0.0002501573,0.0003212336,0.0001799852,0.0003221318,0.000193904,0.001855959,0.0002208984,5.760905e-7],"category_scores_gemma":[0.001839462,0.0002059545,0.0002534681,0.0002975281,0.0001000461,0.0004486805,0.0008645447,0.002653239,6.180744e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001337617,"about_ca_system_score_gemma":0.002742851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001184587,"about_ca_topic_score_gemma":0.0002277935,"domain_scores_codex":[0.9970554,0.0002006293,0.0006577909,0.0005409378,0.0003965359,0.001148738],"domain_scores_gemma":[0.9967964,0.0008169696,0.001017176,0.0009272821,0.0004006279,0.0000414913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003052483,0.0002004568,0.006610363,0.0007211188,0.001224076,0.000006304595,0.007842164,0.08696274,0.002065943,0.05431685,0.0007437496,0.839001],"study_design_scores_gemma":[0.0003413649,0.000472653,0.0006562851,0.0007854123,0.0001299389,0.0001132276,0.000479887,0.3868899,0.003510827,0.6062589,0.0000817164,0.0002798523],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03945141,0.0009006358,0.9572791,0.0001362395,0.001137892,0.0006201203,0.00006511271,0.0004033294,0.000006147222],"genre_scores_gemma":[0.8988456,0.0005051825,0.1002816,0.00001854428,0.0002097179,0.00006120188,0.00001635983,0.00003806111,0.00002381985],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8593941,"threshold_uncertainty_score":0.9996477,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02896934055053236,"score_gpt":0.2906084040883843,"score_spread":0.2616390635378519,"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."}}