{"id":"W4387951146","doi":"10.1109/ccece58730.2023.10288888","title":"Analyzing the Benefits of Data Augmentation for Smart Grid Anomaly Detection and Forecasting","year":2023,"lang":"en","type":"article","venue":"","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Anomaly detection; Computer science; Smart grid; Machine learning; Time series; Grid; Anomaly (physics); Data modeling; Data mining; Artificial intelligence; Generative grammar; Electricity; Engineering; Database","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":[0.0004046205,0.00004577151,0.00005676906,0.00007611969,0.000217769,0.00005468222,0.0003432712,0.00002023263,0.000001587073],"category_scores_gemma":[0.00002659395,0.00003429291,0.00001948193,0.000501034,0.0000183473,0.0003646713,0.0002336871,0.00002801378,0.000001396442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006824395,"about_ca_system_score_gemma":0.000007627613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007652978,"about_ca_topic_score_gemma":0.0001054684,"domain_scores_codex":[0.999472,0.00001127391,0.0001601485,0.0002091781,0.00005990332,0.00008745449],"domain_scores_gemma":[0.9993154,0.0001452343,0.00009187688,0.000379171,0.00005154889,0.00001676608],"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":[0.000003656237,0.000007407704,0.001034581,0.00001713963,0.00001186271,4.123499e-8,0.00007426852,0.000116557,0.006434925,0.01529703,0.0003848152,0.9766177],"study_design_scores_gemma":[0.0001543649,0.00008075047,0.02717471,0.000009282857,0.00001307521,0.000005995448,0.00009205769,0.926405,0.04106653,0.002951642,0.001952192,0.00009446793],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07544433,0.00002415402,0.9234453,0.0004299121,0.00004466111,0.0002373709,0.00001286219,0.0001827527,0.0001786138],"genre_scores_gemma":[0.9521037,0.00003229825,0.04758833,0.00002825152,0.00004379481,0.00007353033,0.00001494516,0.00000434315,0.0001107605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9765233,"threshold_uncertainty_score":0.1674925,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1001418483813062,"score_gpt":0.3074218420944518,"score_spread":0.2072799937131457,"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."}}