{"id":"W4367323229","doi":"10.31219/osf.io/v7m9y","title":"Benchmarking Librarian Support of Systematic Reviews in the Sciences, Humanities, and Social Sciences","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Association of Research Libraries; University of Manitoba; Association of Research Libraries","keywords":"Systematic review; Benchmarking; Workload; Knowledge management; Library science; Sociology; Psychology; MEDLINE; Computer science; Political science; Management","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5581591,0.001801783,0.006493574,0.03533693,0.00326421,0.02232557,0.005662668,0.003864746,0.0124526],"category_scores_gemma":[0.881498,0.001748253,0.003018776,0.06051059,0.002797993,0.01595577,0.01523944,0.002878893,0.005421132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01369815,"about_ca_system_score_gemma":0.06093431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00580371,"about_ca_topic_score_gemma":0.006608321,"domain_scores_codex":[0.1226763,0.6961982,0.1028307,0.00853064,0.06502408,0.004740166],"domain_scores_gemma":[0.04666612,0.7088261,0.06372766,0.0552117,0.1167427,0.008825727],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001862818,0.000545844,0.06440452,0.02328063,0.002869332,0.0003529083,0.01131729,0.002705663,0.002160653,0.01385563,0.04534137,0.8313034],"study_design_scores_gemma":[0.003292467,0.003626983,0.2177874,0.06540043,0.007156313,0.001858115,0.02548905,0.02086082,0.01411052,0.04235802,0.5970301,0.001029767],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.2452421,0.146373,0.1347824,0.2239074,0.005965255,0.01355182,0.01436837,0.008131714,0.207678],"genre_scores_gemma":[0.6968819,0.04576395,0.2004797,0.01625849,0.003336946,0.01603119,0.01122566,0.002514256,0.007507899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9776744,"threshold_uncertainty_score":0.5448686,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9341591597052916,"score_gpt":0.5567727092811271,"score_spread":0.3773864504241645,"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."}}