{"id":"W2415002020","doi":"10.1007/978-4-431-66996-8_73","title":"Knowledge-based Cascade-correlation: Varying the Size and Shape of Relevant Prior Knowledge","year":2003,"lang":"en","type":"book-chapter","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Cascade; Relevance (law); Computer science; Correlation; Artificial intelligence; Artificial neural network; Machine learning; Space (punctuation); Pattern recognition (psychology); Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003218585,0.0008956442,0.001447059,0.0009775329,0.0007245986,0.001343717,0.002643505,0.001696993,0.005518609],"category_scores_gemma":[0.01411171,0.0007809195,0.0006762529,0.001440991,0.001035947,0.004519125,0.001978523,0.001699678,0.0008227915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001104914,"about_ca_system_score_gemma":0.001576067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003436885,"about_ca_topic_score_gemma":0.006496743,"domain_scores_codex":[0.9991683,0.0002427903,0.00003763999,0.000258061,0.000204145,0.00008904745],"domain_scores_gemma":[0.9931291,0.004729847,0.0002863679,0.0008745054,0.0007352288,0.000244993],"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":[0.001748938,0.0007298987,0.002504623,0.0004332707,0.0002642229,0.0003977055,0.0004093285,0.3752622,0.02186971,0.04191242,0.012493,0.5419747],"study_design_scores_gemma":[0.00004628259,0.00008633649,0.0005152745,0.00002265066,0.00007604381,0.00008790383,0.00001864307,0.9722908,0.006945515,0.01914969,0.0007367595,0.00002404886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07570708,0.001610035,0.9109485,0.000397678,0.000135517,0.0001315971,0.0002054383,0.001412976,0.009451115],"genre_scores_gemma":[0.747748,0.0009639642,0.2458653,0.0002603215,0.0001395645,0.000131803,0.000380442,0.0003097098,0.004200819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005518609,"threshold_uncertainty_score":0.01846159,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02514725935898053,"score_gpt":0.2518630680762625,"score_spread":0.2267158087172819,"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."}}