{"id":"W123380392","doi":"","title":"Using Knowledge to Speed Learning: A Comparison of Knowledge-based Cascade-correlation and Multi-task Learning","year":2000,"lang":"en","type":"article","venue":"","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Cascade; Task (project management); Artificial intelligence; Multi-task learning; Correlation; Machine learning; Engineering; 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":[0.0004882316,0.0001534878,0.0002476138,0.0002753518,0.0003011393,0.0001058271,0.0002910995,0.00006464945,0.00007342036],"category_scores_gemma":[0.0001617699,0.0001475021,0.00005438744,0.000949771,0.00007659767,0.0003978994,0.0001438809,0.0002450352,0.0001443581],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004660218,"about_ca_system_score_gemma":0.0001190288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008836381,"about_ca_topic_score_gemma":0.00006735166,"domain_scores_codex":[0.9985942,0.0001678616,0.0003043821,0.0004556096,0.0001733026,0.0003046732],"domain_scores_gemma":[0.9992039,0.0001955382,0.00009118243,0.0001633817,0.0001931906,0.000152778],"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":[0.00002621016,0.0003699035,0.0631406,0.000054109,0.00001619437,0.000003235099,0.02276919,0.1111974,0.0309872,0.0007918212,0.0000930435,0.7705511],"study_design_scores_gemma":[0.0004837518,0.0001549295,0.01148523,0.00009442667,0.000008977316,0.000004006634,0.0003436392,0.9786084,0.004788782,0.00001651914,0.003811759,0.0001995636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4250058,0.0001751979,0.5662969,0.00005719151,0.00008261226,0.0001617058,1.872359e-7,0.0001050498,0.008115401],"genre_scores_gemma":[0.9637295,0.000002995532,0.03340689,0.00004140974,0.00002844739,0.000002122804,0.00000127638,0.000007804403,0.002779545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8674111,"threshold_uncertainty_score":0.6014959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07553596546970597,"score_gpt":0.3494412683639753,"score_spread":0.2739053028942693,"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."}}