{"id":"W2625701074","doi":"","title":"Fast Robust Model Selection in Large Datasets","year":2010,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Advanced Statistical Methods and Models","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"HEC Montréal","funders":"","keywords":"Outlier; Estimator; Selection (genetic algorithm); Covariate; Computer science; Robust regression; Model selection; Context (archaeology); Robustness (evolution); Linear regression; Robust statistics; Feature selection; Linear model; Regression; Statistics; Machine learning; Mathematics; Artificial intelligence","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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002270275,0.0001461418,0.0002091817,0.0001045437,0.0001492205,0.00003027567,0.0001866301,0.0001044387,0.00004330864],"category_scores_gemma":[0.0005977258,0.000127094,0.00005167003,0.0001470641,0.00002417928,0.0002339585,0.00003717391,0.003283486,0.000007655881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002600064,"about_ca_system_score_gemma":0.0006434549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008967297,"about_ca_topic_score_gemma":0.004605612,"domain_scores_codex":[0.9973945,0.00007916352,0.0003209205,0.0002066446,0.0002047542,0.001793997],"domain_scores_gemma":[0.9994312,0.0001623188,0.0001202278,0.0001370586,0.00005243736,0.00009673707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002982233,0.0001383244,0.00009559563,0.000006955646,0.00001741449,0.000003030704,0.00005743997,0.001724574,0.002138629,0.9829867,0.00012914,0.01267234],"study_design_scores_gemma":[0.0005386096,0.0000606508,0.00002674622,0.000008347627,0.00001576527,0.0001994179,0.0001165048,0.1420101,0.00008443212,0.8566214,0.0001885628,0.0001294227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03713839,0.00004606944,0.9620274,0.0001137248,0.00008731445,0.0001039379,0.00005518116,0.00002754662,0.0004004337],"genre_scores_gemma":[0.5431926,0.0002249272,0.4555929,0.00006185002,0.0001872028,0.000009732835,0.00001453608,0.000040765,0.0006754244],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5064344,"threshold_uncertainty_score":0.999016,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04707642951867836,"score_gpt":0.3820002722049438,"score_spread":0.3349238426862655,"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."}}