{"id":"W4321016149","doi":"10.1007/s10994-023-06305-0","title":"Diverse and consistent multi-view networks for semi-supervised regression","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"Institute for Infocomm Research; Agency for Science, Technology and Research","keywords":"DICOM; Computer science; Consistency (knowledge bases); Probabilistic logic; Artificial intelligence; Machine learning; Graphical model; Data mining; Regression; Mathematics","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":[0.0007568914,0.0001628616,0.0001929575,0.0001276208,0.0005114336,0.0001778713,0.000336841,0.00007357347,0.00001223732],"category_scores_gemma":[0.0003860915,0.0001344944,0.00006190749,0.000388991,0.00003442406,0.0002221128,0.0003924474,0.0002954583,0.00003826501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001779356,"about_ca_system_score_gemma":0.00001600837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006338239,"about_ca_topic_score_gemma":0.000021913,"domain_scores_codex":[0.9986619,0.0001992809,0.000205975,0.0004757657,0.0001567653,0.0003003486],"domain_scores_gemma":[0.9990568,0.0003071225,0.0001196333,0.0003556397,0.00005101773,0.0001097655],"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":[0.00002615571,0.00005769887,0.07696668,0.000152886,0.00003363033,0.00001872414,0.0009518779,0.02347953,0.0007117944,0.004810042,0.002599133,0.8901919],"study_design_scores_gemma":[0.0006557015,0.00006045395,0.01923065,0.00006174268,0.00000995136,0.000007509839,0.00007655073,0.9267289,0.00001038487,0.00004824334,0.05295243,0.0001574481],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02200254,0.00121942,0.9716623,0.002893128,0.0003959805,0.0003805042,0.000008172188,0.001156162,0.0002818138],"genre_scores_gemma":[0.9588411,0.0006973069,0.03592686,0.0003925937,0.0001358564,0.00006975682,0.0003844895,0.00003466064,0.003517345],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368386,"threshold_uncertainty_score":0.5484524,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04672530729582696,"score_gpt":0.2984487345633164,"score_spread":0.2517234272674895,"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."}}