{"id":"W4409818715","doi":"10.1017/rsm.2025.20","title":"Same, same, but different: A method to harmonise and deduplicate study records from WHO ICTRP and ClinicalTrials.gov prior to screening","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Medical Coding and Health Information","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Medicine; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06520426,0.0003160028,0.001346107,0.0009447437,0.002287761,0.0001293215,0.0005006873,0.0004420383,0.0003328122],"category_scores_gemma":[0.08523127,0.0002493617,0.00008401966,0.00106945,0.0001216306,0.0001447578,0.001309905,0.00208706,0.00008154166],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002372009,"about_ca_system_score_gemma":0.0005373308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006229592,"about_ca_topic_score_gemma":0.0004082742,"domain_scores_codex":[0.966646,0.02817448,0.001882652,0.0009803949,0.0009670879,0.001349357],"domain_scores_gemma":[0.8993722,0.09737686,0.0002603441,0.0009161402,0.0004965247,0.001577983],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001318744,0.0001027187,0.03050831,0.0005298037,0.0001078644,0.00000276111,0.00589814,0.000001267525,0.001015377,0.0004003991,0.006111812,0.9540028],"study_design_scores_gemma":[0.004021019,0.001448541,0.7855749,0.005692611,0.0003029736,0.000001254147,0.03039919,0.007852458,0.004181937,0.00731536,0.1523872,0.0008226307],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5359193,0.0003895722,0.4261629,0.03024775,0.0003719203,0.005127255,0.00008207643,0.0001432724,0.001555981],"genre_scores_gemma":[0.05497677,0.000854138,0.9298227,0.005832797,0.0006321758,0.00335687,0.000006015858,0.00006208775,0.004456478],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9531802,"threshold_uncertainty_score":0.9999959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6562454175277866,"score_gpt":0.683828765393392,"score_spread":0.02758334786560535,"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."}}