{"id":"W4413441258","doi":"10.1613/jair.1.19171","title":"An MRP Formulation for Supervised Learning: Generalized Temporal Difference Learning Models","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Royal Academy of Engineering; UK Research and Innovation","keywords":"Computer science; Artificial intelligence; Supervised learning; Temporal difference learning; Machine learning; Artificial neural network","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004473045,0.0001367079,0.0002997281,0.0009264002,0.0005681672,0.0006026554,0.0010788,0.0001237518,0.00007302209],"category_scores_gemma":[0.001304003,0.0001177979,0.0001907387,0.0009670589,0.0000682543,0.0009753851,0.0001084934,0.0007564322,0.00002546778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001237488,"about_ca_system_score_gemma":0.0004133484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000492011,"about_ca_topic_score_gemma":0.00002209915,"domain_scores_codex":[0.9968988,0.0007148305,0.0007836325,0.0003050827,0.0008193708,0.0004783109],"domain_scores_gemma":[0.9964211,0.000980698,0.0002038765,0.0002597816,0.001943453,0.0001910761],"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":[0.0002461694,0.0002132454,0.0004201834,0.00002780502,0.00003261061,0.0000107636,0.0009859696,0.01060795,0.02596856,0.1288812,0.0000752419,0.8325303],"study_design_scores_gemma":[0.00007628693,0.0004746286,0.0000720478,0.00006417239,0.00000576087,0.000007032848,0.0007335879,0.7652524,0.07037262,0.1623046,0.0005375627,0.00009938754],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1672778,0.00008319705,0.8307416,0.001016238,0.0002182615,0.0002273966,7.210139e-7,0.00003851196,0.0003961921],"genre_scores_gemma":[0.9289361,0.0001113891,0.07023592,0.00004562367,0.0001685863,0.00001718525,0.000003845641,0.0000106164,0.0004707343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8324309,"threshold_uncertainty_score":0.581142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3039810437019274,"score_gpt":0.4386553844920129,"score_spread":0.1346743407900856,"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."}}