{"id":"W2470750097","doi":"","title":"Enhancing retrieval of best evidence for health care from bibliographic databases: calibration of the hand search of the literature.","year":2001,"lang":"en","type":"article","venue":"PubMed","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Hamilton Health Sciences","funders":"","keywords":"Cohen's kappa; Statistic; Information retrieval; Reliability (semiconductor); Computer science; MEDLINE; Health care; Test (biology); Medical education; Database; Medicine; Statistics; Machine learning; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00624426,0.00008429028,0.0002416047,0.0003813077,0.0001774336,0.00009243298,0.0008583294,0.00003946256,0.00001692839],"category_scores_gemma":[0.00499357,0.00004140383,0.0001949498,0.005210837,0.0002331401,0.0003498762,0.000169196,0.0001131711,2.263711e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003019228,"about_ca_system_score_gemma":0.0001593642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004008315,"about_ca_topic_score_gemma":0.001000766,"domain_scores_codex":[0.9962166,0.0005633832,0.0007905021,0.0002990311,0.001914658,0.0002158298],"domain_scores_gemma":[0.9963071,0.001481035,0.0004735831,0.000929822,0.0007513001,0.00005715108],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001087706,0.0004057723,0.9126067,0.0006913567,0.00008460243,3.445851e-7,0.01351191,0.0005203877,0.02722429,0.0002764221,0.00419822,0.03939233],"study_design_scores_gemma":[0.0005340591,0.0001128118,0.7333352,0.0008832099,0.00003812107,5.043844e-7,0.002758601,0.0001789597,0.2592857,0.001447282,0.001329144,0.00009647669],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9879133,0.004823403,0.002388302,0.002592412,0.0003742858,0.001579554,0.0002995568,0.000002784444,0.00002644639],"genre_scores_gemma":[0.9990651,0.0004075948,0.0002116443,0.0001325316,0.00005629508,0.00005969403,0.000006563852,0.000003773233,0.00005678141],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2320614,"threshold_uncertainty_score":0.597813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.267435042832476,"score_gpt":0.4016326631986881,"score_spread":0.1341976203662121,"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."}}