{"id":"W4388720918","doi":"10.1109/iecon51785.2023.10312336","title":"Lightweight Compressed Temporal and Compressed Spatial Attention with Augmentation Fusion in Remaining Useful Life Prediction","year":2023,"lang":"en","type":"article","venue":"","topic":"Insurance, Mortality, Demography, Risk Management","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National University of Singapore","keywords":"Computer science; Transformer; Artificial intelligence; Modular design; Data modeling; Machine learning; Preprocessor; Spatial analysis; Data mining; Engineering","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":[0.0009659092,0.000148566,0.0001958844,0.0003778976,0.0005061611,0.0001523997,0.0001280554,0.00009383882,0.00008077759],"category_scores_gemma":[0.00003099043,0.0001345664,0.00003940645,0.0008758903,0.0001860472,0.0004784191,0.00006776618,0.0001234324,0.00002096517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006635061,"about_ca_system_score_gemma":0.00004706685,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01084526,"about_ca_topic_score_gemma":0.02092249,"domain_scores_codex":[0.9979233,0.0003075235,0.0003521182,0.0003884502,0.0006948594,0.0003337071],"domain_scores_gemma":[0.9994122,0.00007247354,0.0001566409,0.000162392,0.00008386777,0.0001123858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001124927,0.00007980935,0.9913605,0.00004170039,0.00003066228,0.00001261796,0.003691659,0.000563991,0.0003413967,0.001421171,0.001218586,0.001125443],"study_design_scores_gemma":[0.001366141,0.00008580225,0.9781621,0.00008517512,0.00002646871,2.593936e-7,0.004353286,0.01312133,0.00004708275,0.0002790131,0.0023049,0.0001684158],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9866456,0.00002447075,0.002841129,0.000922154,0.0005142164,0.0008543307,0.00001047847,0.0003874772,0.007800189],"genre_scores_gemma":[0.9984709,0.0001661352,0.0004031565,0.00009520166,0.000167671,0.00006059248,0.0001291524,0.0000160618,0.0004910972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01319834,"threshold_uncertainty_score":0.9969431,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02469482609719478,"score_gpt":0.2809264686908105,"score_spread":0.2562316425936157,"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."}}