{"id":"W2605897081","doi":"10.1186/s41512-017-0012-3","title":"Validation of prediction models: examining temporal and geographic stability of baseline risk and estimated covariate effects","year":2017,"lang":"en","type":"article","venue":"Diagnostic and Prognostic Research","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Institute for Clinical Evaluative Sciences; Sunnybrook Health Science Centre","funders":"National Institute of Neurological Disorders and Stroke; Canadian Institutes of Health Research; Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Covariate; Baseline (sea); Stability (learning theory); Statistics; Econometrics; Computer science; Mathematics; Machine learning; Biology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004795097,0.0001535023,0.0003671769,0.000192169,0.0003268628,0.00007590359,0.0001397953,0.0001304365,0.000006768288],"category_scores_gemma":[0.06939388,0.0001329962,0.00001898451,0.000126264,0.0009328189,0.0003668357,0.0002622754,0.0003111243,1.913777e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001234418,"about_ca_system_score_gemma":0.00005042137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005606781,"about_ca_topic_score_gemma":0.00001611243,"domain_scores_codex":[0.9979902,0.000557263,0.000431078,0.0003516714,0.0004080942,0.0002616895],"domain_scores_gemma":[0.9757554,0.02283106,0.0003284352,0.0004558462,0.0005115365,0.0001177379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007341732,0.0001412745,0.974025,0.001216982,0.00003591498,0.000006473992,0.0005033895,0.000008449945,0.001046253,0.006362685,0.00001445471,0.01656575],"study_design_scores_gemma":[0.000769336,0.001092521,0.4623266,0.001230447,0.0001326688,0.000006863242,0.0001550587,0.03375661,0.01878414,0.4815931,0.000001573064,0.0001510663],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9351594,0.0005370146,0.06290278,0.00002729912,0.0000218787,0.001089983,0.0001116094,0.00005495192,0.00009505711],"genre_scores_gemma":[0.9773926,0.001879079,0.02054063,0.00000122477,0.00001637489,0.0001256545,0.00002431076,0.00001786612,0.000002235954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5116983,"threshold_uncertainty_score":0.938445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3648981795435242,"score_gpt":0.4617530783644725,"score_spread":0.09685489882094833,"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."}}