{"id":"W2171762906","doi":"10.1016/j.jclinepi.2010.02.006","title":"The COSMIN study reached international consensus on taxonomy, terminology, and definitions of measurement properties for health-related patient-reported outcomes","year":2010,"lang":"en","type":"article","venue":"Journal of Clinical Epidemiology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":4442,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Terminology; Taxonomy (biology); Delphi method; Confusion; Delphi; Consistency (knowledge bases); Management science; Medicine; Psychology; Applied psychology; Computer science; Artificial intelligence; Engineering; Linguistics; Ecology","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":"methods","study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2813033,0.001493887,0.003498483,0.008357699,0.002191629,0.005102483,0.003100543,0.00281847,0.001560173],"category_scores_gemma":[0.3131618,0.000711666,0.005177767,0.006007873,0.003761618,0.004468815,0.006231625,0.004497453,0.000485872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004561922,"about_ca_system_score_gemma":0.008228051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00585506,"about_ca_topic_score_gemma":0.01149089,"domain_scores_codex":[0.8946426,0.0623839,0.01688793,0.003991054,0.02039902,0.001695503],"domain_scores_gemma":[0.5667956,0.3284065,0.02480311,0.02638038,0.05180538,0.001808936],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.003311554,0.0007719955,0.5408508,0.005940793,0.003658373,0.0001882514,0.007703631,0.002518183,0.001409793,0.06089389,0.03448363,0.3382691],"study_design_scores_gemma":[0.001143946,0.003004629,0.7562182,0.01679817,0.007136582,0.0008386612,0.005830916,0.009937531,0.007730737,0.05284488,0.1378645,0.000651343],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3998616,0.05336991,0.4250203,0.02603535,0.003849854,0.011062,0.01748245,0.000911582,0.06240701],"genre_scores_gemma":[0.7377546,0.008070105,0.2156433,0.007647018,0.0007171867,0.01766471,0.009429741,0.0007581672,0.002315211],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7186967,"threshold_uncertainty_score":0.886281,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8170932433584581,"score_gpt":0.5349041107663476,"score_spread":0.2821891325921105,"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."}}