{"id":"W4413144690","doi":"10.1109/cvpr52734.2025.00451","title":"HOT: Hadamard-based Optimized Training","year":2025,"lang":"en","type":"article","venue":"","topic":"Spreadsheets and End-User Computing","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Hadamard transform; Training (meteorology); Computer science; Artificial intelligence; Mathematics; Physics","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":[0.0006634137,0.0008347807,0.0005563481,0.0004059165,0.0003543586,0.0007813809,0.001624866,0.000893701,0.007096271],"category_scores_gemma":[0.003440555,0.0004260181,0.0003471856,0.0006095509,0.0005350827,0.001243214,0.0009808704,0.001474527,0.001608655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006859645,"about_ca_system_score_gemma":0.00142962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006476317,"about_ca_topic_score_gemma":0.01228257,"domain_scores_codex":[0.9995998,0.00009218936,0.00002313686,0.00007848506,0.0001463663,0.00006009538],"domain_scores_gemma":[0.9992006,0.0003830192,0.0000536104,0.0001549129,0.0001714324,0.00003646323],"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":[0.0003692224,0.00010886,0.001127591,0.0002024581,0.0001187377,0.0001456672,0.0001342041,0.603075,0.01559016,0.0182164,0.01915354,0.3417582],"study_design_scores_gemma":[0.00001598366,0.0000247185,0.000106345,0.000008901731,0.000005730794,0.00002970627,0.000008405435,0.9906088,0.00414883,0.003454994,0.001581464,0.00000626223],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01362209,0.0003550638,0.974857,0.0002065605,0.0001034126,0.00005148301,0.0001913295,0.006963145,0.00365005],"genre_scores_gemma":[0.2551993,0.0002269298,0.7335448,0.0003800524,0.00006031666,0.0001734917,0.0008691545,0.001309956,0.008235923],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007096271,"threshold_uncertainty_score":0.02373934,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0275991530131842,"score_gpt":0.2609878253753091,"score_spread":0.2333886723621248,"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."}}