{"id":"W7010393549","doi":"","title":"Interpretable data reduction in prediction modeling: extended redundancy analysis and its extensions and applications","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Advanced Statistical Modeling Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Redundancy (engineering); Covariance; Data reduction; Statistical model; Statistical analysis; Data modeling; Reduction (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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006150093,0.000533251,0.0007517399,0.0008389625,0.0006645585,0.000185059,0.001274803,0.0004650992,0.000008613437],"category_scores_gemma":[0.0006963482,0.0006090677,0.00009560308,0.001683863,0.0000443086,0.002192653,0.0008564693,0.001260452,0.000008385268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000250626,"about_ca_system_score_gemma":0.0000578199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001169882,"about_ca_topic_score_gemma":0.0002795558,"domain_scores_codex":[0.9954874,0.0002149117,0.0009970393,0.002322407,0.0005234584,0.0004547647],"domain_scores_gemma":[0.9971721,0.0001487256,0.0003706116,0.001617437,0.0003477397,0.0003433651],"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":[0.0001434653,0.0002848335,0.000009318186,0.0003618127,0.0004574907,0.00003413188,0.00005768397,0.003112538,0.02514814,0.5218446,0.000005440681,0.4485406],"study_design_scores_gemma":[0.00023483,0.0000779076,0.0001296644,0.0002075967,0.0004589988,0.00002521346,0.0000672898,0.7841548,0.001940328,0.2114026,0.000750212,0.000550471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09082902,0.004235073,0.8794281,0.0002969754,0.001073302,0.005111261,0.00673444,0.003522132,0.008769625],"genre_scores_gemma":[0.8622823,0.001550809,0.1333203,0.00005498792,0.0000296567,0.0003443511,0.002142061,0.00006933625,0.0002061645],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7810423,"threshold_uncertainty_score":0.9996361,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03704890159027037,"score_gpt":0.2984371172308644,"score_spread":0.261388215640594,"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."}}