{"id":"W4415271767","doi":"10.1016/j.nxener.2025.100462","title":"Enhancing forecasting accuracy in dynamic environments via PELT-driven drift detection and model adaptation","year":2025,"lang":"en","type":"article","venue":"Next Energy","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"University of Michigan-Dearborn","keywords":"Robustness (evolution); Concept drift; Perceptron; Time series; Feature (linguistics); Multilayer perceptron; Artificial neural network; Baseline (sea); Generalizability theory","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":[],"consensus_categories":[],"category_scores_codex":[0.0001143235,0.0001098103,0.0001045327,0.0002130798,0.00007578445,0.00009125123,0.0003015837,0.00006721984,8.035937e-7],"category_scores_gemma":[0.00007878175,0.0001232387,0.00001743092,0.0002250499,0.00001967497,0.0008416992,0.0003025102,0.0000863312,9.44387e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001128439,"about_ca_system_score_gemma":0.00002759076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000319105,"about_ca_topic_score_gemma":0.001323117,"domain_scores_codex":[0.9991205,0.00003925636,0.0001991027,0.0003486398,0.0001134596,0.0001789789],"domain_scores_gemma":[0.9994791,0.00009867266,0.00008206081,0.0003003157,0.0000116717,0.00002819984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004624626,0.00002117012,0.00004997295,0.00000785005,0.000005042083,0.000004077015,0.0003681672,0.01419538,0.08977751,0.002566964,0.000009635868,0.8929896],"study_design_scores_gemma":[0.0001313029,0.0000264411,0.0003674919,0.00005683222,0.000003176658,0.000004051091,0.00002548988,0.9687005,0.02399468,0.006352544,0.0002402312,0.0000972573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05712197,0.00004400812,0.9421764,0.00006439979,0.0000625127,0.00005270182,9.568506e-7,0.0001103978,0.0003666291],"genre_scores_gemma":[0.8592961,0.00004528642,0.1404027,0.0001035351,0.000005857348,0.00003065221,0.00000593005,0.000006532865,0.0001033791],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9545051,"threshold_uncertainty_score":0.502553,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0181527636859241,"score_gpt":0.243487834029392,"score_spread":0.2253350703434679,"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."}}