{"id":"W4414305124","doi":"10.2139/ssrn.5500798","title":"Temporal Deep Explainer: A Model-Agnostic Feature Attribution Approach for Interpretable Time-Series Load Forecasting","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Robustness (evolution); Deep learning; Energy (signal processing); Feature (linguistics); Artificial neural network; Feature learning; Convolution (computer science); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001627712,0.001018359,0.0008333784,0.0007107401,0.0003603498,0.001283591,0.002093607,0.001311128,0.004905999],"category_scores_gemma":[0.005514632,0.0006637169,0.001285261,0.000759617,0.0004822005,0.002521123,0.001851698,0.003011851,0.0009419454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006161603,"about_ca_system_score_gemma":0.0008078626,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004067601,"about_ca_topic_score_gemma":0.005076495,"domain_scores_codex":[0.9996719,0.0001106042,0.00002001919,0.00009833336,0.00006073768,0.00003834179],"domain_scores_gemma":[0.9981071,0.001219642,0.0001374532,0.0003482084,0.0001305021,0.00005716622],"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":[0.0004595152,0.0002169397,0.002605478,0.0001457998,0.0003624693,0.0003606497,0.0001675717,0.6208683,0.005756462,0.05321348,0.009813122,0.3060302],"study_design_scores_gemma":[0.000005248779,0.000006432423,0.00007047398,0.000003132247,0.000008034634,0.00000626095,0.000002554932,0.9833307,0.0003267911,0.01597268,0.0002647321,0.000003043392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01225311,0.0001857536,0.9826992,0.0004463456,0.00007421834,0.00001846169,0.00038038,0.00320068,0.0007419361],"genre_scores_gemma":[0.6340054,0.0004557652,0.356545,0.0004112374,0.0002819967,0.0001241695,0.001558804,0.001066785,0.005550822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004905999,"threshold_uncertainty_score":0.0164122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01183848056069276,"score_gpt":0.2150521319787387,"score_spread":0.203213651418046,"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."}}