{"id":"W4415153955","doi":"10.1002/sim.70269","title":"Specification of Estimands for Complex Disease Processes Using Multistate Models and Utility Functions","year":2025,"lang":"en","type":"article","venue":"Statistics in Medicine","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Jackknife resampling; Ranking (information retrieval); Disease; Simplicity; Variance (accounting); Resampling; Clinical trial","routes":{"ca_aff":true,"ca_fund":true,"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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002272465,0.0001373711,0.0005566404,0.0001605798,0.00006859362,0.000006998459,0.000101862,0.00005729771,0.00005030606],"category_scores_gemma":[0.1169391,0.0001178593,0.00001874365,0.000345589,0.0006086303,0.0000358319,0.00004170739,0.0001246636,1.571798e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003984972,"about_ca_system_score_gemma":0.0001275791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000398098,"about_ca_topic_score_gemma":0.00004582336,"domain_scores_codex":[0.9981097,0.0001491446,0.001036687,0.0002987913,0.0002248653,0.0001807943],"domain_scores_gemma":[0.9579611,0.04095294,0.0002497644,0.000269408,0.0004664403,0.000100291],"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":[0.001284029,0.0003740836,0.002841629,0.006326254,0.00006920749,0.000006858551,0.0003210811,0.0001465284,0.0002068826,0.943565,0.00742992,0.03742853],"study_design_scores_gemma":[0.001269076,0.00006966034,0.004506612,0.0003437932,0.0001809685,2.781801e-7,0.0001155227,0.2264406,0.00002239107,0.7668666,0.0001147949,0.00006966437],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001901234,0.0001339967,0.9947554,0.0002053034,0.0002468872,0.0007651224,0.001553585,0.00002103137,0.0004174598],"genre_scores_gemma":[0.1396071,0.00005827202,0.8600328,0.0000533095,0.00005981683,0.00003262713,0.00003669214,0.00001278686,0.0001065942],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2262941,"threshold_uncertainty_score":0.8904993,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7557390693740194,"score_gpt":0.6269280900231367,"score_spread":0.1288109793508827,"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."}}