{"id":"W4317627131","doi":"10.1016/j.eneco.2023.106521","title":"Foreseeing the worst: Forecasting electricity DART spikes","year":2023,"lang":"en","type":"article","venue":"Energy Economics","topic":"Electric Power System Optimization","field":"Engineering","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University; Group for Research in Decision Analysis; HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; HEC Montréal; Hydro-Québec","keywords":"Dart; Computer science; Spike (software development); Set (abstract data type); Predictive power; Electricity; Feature (linguistics); Operator (biology); Probabilistic forecasting; Econometrics; Machine learning; Artificial intelligence; Economics; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002026173,0.0001250135,0.0001316377,0.0001383181,0.0001304775,0.00006998348,0.0002069662,0.00006434006,0.00001238163],"category_scores_gemma":[0.00004351483,0.0001138463,0.00005201935,0.0004586924,0.000011864,0.0001488624,0.00003492026,0.00009554717,0.00002583444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435673,"about_ca_system_score_gemma":0.00001704696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003694736,"about_ca_topic_score_gemma":0.0001821588,"domain_scores_codex":[0.9992089,0.00001720272,0.0002336652,0.0001472255,0.00004305072,0.0003500079],"domain_scores_gemma":[0.9995457,0.0001292027,0.0000449428,0.0002243025,0.00001551763,0.00004035481],"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":[0.00000222084,0.000002396622,0.001186726,0.00001020431,0.00003207312,0.000003646236,0.0001219592,0.9774005,0.00007070212,0.004454566,0.004045562,0.01266945],"study_design_scores_gemma":[0.00008303794,0.000009106655,0.00008434807,0.000006751507,0.000005359484,0.00001185115,0.00002246104,0.9749548,0.001868776,0.0008174611,0.0220054,0.0001306236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7345277,0.0008789832,0.1751517,0.0004076711,0.002525843,0.0002748921,0.00001059077,0.002503213,0.08371938],"genre_scores_gemma":[0.998476,0.0002518693,0.0002222957,0.00003579853,0.0002471122,0.0000355765,0.00002308112,0.00005314042,0.0006551389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2639483,"threshold_uncertainty_score":0.4642517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01344774014926228,"score_gpt":0.1667998384117479,"score_spread":0.1533520982624857,"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."}}