{"id":"W4403564378","doi":"10.48550/arxiv.2410.09190","title":"Time to Retrain? Detecting Concept Drifts in Machine Learning Systems","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs","keywords":"Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000670151,0.0003747886,0.0004479613,0.0007595035,0.0000976844,0.0003484364,0.002490989,0.0003238985,0.00002822462],"category_scores_gemma":[0.0001755158,0.000453523,0.0001222023,0.001228553,0.00006837463,0.0002444973,0.006732746,0.001581845,0.0005544884],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004377483,"about_ca_system_score_gemma":0.0001522744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007402577,"about_ca_topic_score_gemma":0.00005630376,"domain_scores_codex":[0.9972902,0.0002729782,0.0003008985,0.001537819,0.0001331361,0.000465003],"domain_scores_gemma":[0.9981128,0.0001811352,0.0001901765,0.001256875,0.00008084974,0.0001781498],"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":[0.00007262272,0.0002084869,0.003283165,0.000879412,0.0003678934,0.009692309,0.008568155,0.8476818,0.00141278,0.09989859,0.007154635,0.02078012],"study_design_scores_gemma":[0.0001507618,0.0001106287,0.00006228154,0.0008907262,0.00002654708,0.00001628804,0.00008837444,0.9918464,0.0002639481,0.004172102,0.001804936,0.0005669512],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3332042,0.0005206055,0.6419811,0.00029625,0.00150465,0.001507916,0.0001371042,0.005256353,0.01559194],"genre_scores_gemma":[0.9893423,0.00001444711,0.005699894,0.00003864995,0.0000665124,0.0000031913,0.00002657902,0.00003806868,0.004770398],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6561381,"threshold_uncertainty_score":0.9997916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04464954284522915,"score_gpt":0.1929247307800332,"score_spread":0.148275187934804,"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."}}