{"id":"W4412354256","doi":"10.1101/2025.07.08.25330734","title":"Exploring scalable assessment methods for terminated trials in ClinicalTrials.gov: A cohort analysis of German and Californian trials","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"German; Scalability; Cohort; Medicine; Computer science; Internal medicine; History","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4613088,0.002033695,0.002382879,0.005244309,0.001263965,0.00593701,0.004048825,0.002309373,0.006879489],"category_scores_gemma":[0.658621,0.00154253,0.008718153,0.006077591,0.002727578,0.004999836,0.005418569,0.003557705,0.0008643533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00318068,"about_ca_system_score_gemma":0.009611994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008270128,"about_ca_topic_score_gemma":0.009061924,"domain_scores_codex":[0.6318216,0.3006847,0.02895055,0.01923128,0.01741885,0.001893012],"domain_scores_gemma":[0.1969005,0.6345398,0.08486793,0.06541014,0.01642456,0.001857099],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01489794,0.0007593221,0.5008536,0.01154975,0.04925409,0.0009339136,0.005110345,0.09578115,0.001307821,0.05292001,0.02534562,0.2412864],"study_design_scores_gemma":[0.01074924,0.005199571,0.2858727,0.008718265,0.02081321,0.001539306,0.001544391,0.4540341,0.003136978,0.1245389,0.08304948,0.0008039774],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1926495,0.01040614,0.7337653,0.004507699,0.0005874711,0.02262956,0.02756722,0.002874888,0.005012199],"genre_scores_gemma":[0.6197377,0.001109058,0.3376908,0.001493191,0.0002218428,0.02444213,0.0137765,0.0004234052,0.001105263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5386912,"threshold_uncertainty_score":0.6643021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8599393442775416,"score_gpt":0.7299780568250449,"score_spread":0.1299612874524967,"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."}}