{"id":"W4293574627","doi":"10.21203/rs.3.rs-1867622/v1","title":"Pattern Discovery and Disentanglement: A New Interpretable Machine Learning Paradigm for Relational Datasets","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Statistical relational learning; Machine learning; Data science; Data mining; Relational database","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002068829,0.0002667678,0.0003022474,0.0004196978,0.0007978013,0.001225477,0.001585125,0.0001140524,0.0003200124],"category_scores_gemma":[0.0005713276,0.0002724359,0.0001265426,0.0004197042,0.0001023365,0.001019973,0.007931706,0.001669487,0.00003381382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003802298,"about_ca_system_score_gemma":0.0005472521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002097359,"about_ca_topic_score_gemma":0.0003544752,"domain_scores_codex":[0.9958362,0.0005777907,0.0004306207,0.001171298,0.00118766,0.0007964184],"domain_scores_gemma":[0.9972914,0.001121438,0.000150923,0.001064065,0.0001028919,0.0002693078],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000528658,0.0009769541,0.07749297,0.003902754,0.0005905878,0.000526776,0.01631884,0.05370897,0.0003052568,0.5030523,0.06995469,0.2726412],"study_design_scores_gemma":[0.0004049401,0.0006093712,0.001573254,0.0005694627,0.00001959001,0.00001481974,0.0007262909,0.6809734,0.0004217242,0.111379,0.2026183,0.0006898759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004425971,0.002814762,0.9821082,0.005558928,0.0004781359,0.002029271,0.00193968,0.0001468941,0.000498176],"genre_scores_gemma":[0.9711314,0.0009405772,0.01124508,0.0002349068,0.0005320465,0.001356305,0.008122029,0.0001020043,0.006335596],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9708631,"threshold_uncertainty_score":0.9999728,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1076358882748366,"score_gpt":0.4015043464945937,"score_spread":0.2938684582197571,"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."}}