{"id":"W4327989833","doi":"10.48550/arxiv.2303.09616","title":"Cross-validatory Z-Residual for Diagnosing Shared Frailty Models","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Statistical Methods and Inference","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Outlier; Cross-validation; Context (archaeology); Discriminative model; Computer science; Goodness of fit; Statistics; Data mining; Regression; Algorithm; Mathematics; Artificial intelligence; Geography","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006262261,0.0003725864,0.0005669135,0.0001648373,0.0002183276,0.0001564714,0.0007492094,0.0004884678,0.0002095472],"category_scores_gemma":[0.002452966,0.0004195925,0.0002767084,0.0002035367,0.0002005549,0.0001637666,0.001009443,0.0005545726,0.00005520464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000170086,"about_ca_system_score_gemma":0.0001905346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001100925,"about_ca_topic_score_gemma":0.00003551766,"domain_scores_codex":[0.9978572,0.0001690122,0.0003548658,0.001023448,0.0001174081,0.0004780952],"domain_scores_gemma":[0.9941258,0.004226228,0.000289683,0.0008640029,0.0003027823,0.0001914781],"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":[0.00008582598,0.0001157989,0.001308925,0.000716248,0.0001658072,0.0001211631,0.0002084513,0.03018986,0.00002711638,0.9622992,0.004257561,0.0005040719],"study_design_scores_gemma":[0.0004356266,0.00004015613,0.0009340696,0.000212161,0.0001648979,5.638864e-7,0.00005597058,0.1577834,0.000142962,0.8396987,0.0001179433,0.0004135876],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1756617,0.0000190852,0.8202508,0.00003637131,0.0005876904,0.0005939624,0.001337368,0.0003339365,0.001179044],"genre_scores_gemma":[0.8632864,0.00007745943,0.1311636,0.00007861503,0.0002842069,0.00001986164,0.0001238083,0.0001231398,0.004842854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6890872,"threshold_uncertainty_score":0.9998256,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5702021073177328,"score_gpt":0.354218981537205,"score_spread":0.2159831257805278,"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."}}