{"id":"W4211102397","doi":"10.5195/jmla.2022.1286","title":"Preliminary comparison of the performance of the National Library of Medicine’s systematic review publication type and the sensitive clinical queries filter for systematic reviews in PubMed","year":2022,"lang":"en","type":"article","venue":"Journal of the Medical Library Association JMLA","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Impact","funders":"","keywords":"Systematic review; Information retrieval; National library; Yield (engineering); Computer science; Recall; MEDLINE; Quality (philosophy); Medicine; Digital library; Precision and recall; Medical physics; Library science; Psychology; Materials science; Physics; Chemistry","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"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2055804,0.0001712095,0.004745797,0.0001485711,0.0001794739,0.00006900951,0.002721167,0.00009264187,0.0004950134],"category_scores_gemma":[0.3758596,0.00004902835,0.001429924,0.002205859,0.0003227894,0.0005743823,0.0005778772,0.000553177,0.000002514124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005608036,"about_ca_system_score_gemma":0.0004497158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001185962,"about_ca_topic_score_gemma":0.000001169594,"domain_scores_codex":[0.9087957,0.06395705,0.01830734,0.0002555456,0.008522041,0.0001623701],"domain_scores_gemma":[0.8691012,0.0627968,0.06385707,0.001831327,0.002276373,0.0001372705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0002804619,0.0002936805,0.2118464,0.1680055,0.0009538964,2.897934e-7,0.002370101,0.00006068913,0.000003157002,0.003687909,0.6121939,0.0003040232],"study_design_scores_gemma":[0.00496024,0.0008860222,0.5493832,0.362895,0.006770731,0.0001840241,0.004122606,0.04348624,0.0001213205,0.006361613,0.02038056,0.0004484203],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2562839,0.1566394,0.0002592544,0.5306287,0.006429325,0.04572422,0.0003186111,0.00001187281,0.00370479],"genre_scores_gemma":[0.9863631,0.002410221,0.0001388036,0.00596036,0.0001734868,0.0003157579,0.000008076829,0.00001424178,0.004615999],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7300792,"threshold_uncertainty_score":0.8180222,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4144119397708907,"score_gpt":0.4683835812984496,"score_spread":0.05397164152755884,"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."}}