{"id":"W2754566416","doi":"10.1007/s10637-017-0510-8","title":"Comparison of reporting phase I trial results in ClinicalTrials.gov and matched publications","year":2017,"lang":"en","type":"review","venue":"Investigational New Drugs","topic":"Statistical Methods in Clinical Trials","field":"Mathematics","cited_by":38,"is_retracted":false,"has_abstract":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"","keywords":"Medicine; Clinical trial; Interquartile range; Adverse effect; Internal medicine; Clinical endpoint; MEDLINE","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"reporting","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"medium","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.02375586,0.0004946809,0.006382068,0.0003548514,0.0001368618,0.000148505,0.0007655091,0.0008686631,0.00008619604],"category_scores_gemma":[0.7733957,0.00042475,0.0006360341,0.0004374039,0.0007795555,0.0001487233,0.000285759,0.001086023,0.00002622283],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020834,"about_ca_system_score_gemma":0.002677031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005975337,"about_ca_topic_score_gemma":0.0000115688,"domain_scores_codex":[0.9782745,0.002403813,0.01705474,0.001002671,0.0009029506,0.0003612791],"domain_scores_gemma":[0.6909024,0.2597135,0.04539,0.002569205,0.0005394258,0.0008855058],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001970087,0.000949292,0.00003543244,0.007079599,0.0002588808,0.000006947449,0.0002519503,3.582346e-7,9.819821e-7,0.09904262,0.01986966,0.8705342],"study_design_scores_gemma":[0.0269899,0.0001985921,0.00001125409,0.009344024,0.0007175939,0.000006371154,0.00001642577,0.0000346979,0.000004929678,0.645699,0.3166168,0.0003604684],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0005908707,0.9701888,0.00273211,0.004092772,0.003344806,0.01047743,0.002028564,0.0002448969,0.006299754],"genre_scores_gemma":[0.00003150353,0.4421112,0.5545357,0.00004520732,0.001740661,0.0002559948,0.0002025971,0.00008220314,0.000994864],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.8701737,"threshold_uncertainty_score":0.9998204,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9371062626576229,"score_gpt":0.7366516816469256,"score_spread":0.2004545810106972,"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."}}