{"id":"W4408173758","doi":"10.1017/rsm.2024.6","title":"A practical guide to evaluating sensitivity of literature search strings for systematic reviews using relative recall","year":2025,"lang":"en","type":"article","venue":"Research Synthesis Methods","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Australian Research Council","keywords":"Recall; Systematic review; Sensitivity (control systems); Computer science; Research methodology; Information retrieval; Management science; Psychology; MEDLINE; Sociology; Political science; Cognitive psychology; Engineering","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","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.8823956,0.000414329,0.007851126,0.002241256,0.0004835147,0.001156638,0.001486714,0.0002612199,0.000430288],"category_scores_gemma":[0.9484475,0.0002108046,0.002454067,0.008500503,0.0001662714,0.0004775535,0.0007184611,0.0007422339,0.000190767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003419573,"about_ca_system_score_gemma":0.0007043548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003921185,"about_ca_topic_score_gemma":0.00001204814,"domain_scores_codex":[0.2837029,0.6787891,0.01981363,0.002828609,0.01354478,0.001320924],"domain_scores_gemma":[0.1974435,0.7713102,0.004875007,0.007643614,0.01817926,0.0005484218],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005615361,0.0007176453,0.001453115,0.1511838,0.004097297,0.00005589698,0.007617408,0.001185161,0.2179883,0.08473226,0.1100853,0.4203223],"study_design_scores_gemma":[0.0003805317,0.0003224991,0.0002984992,0.08045484,0.001842771,0.00005855913,0.004924526,0.8093637,0.0376718,0.02208678,0.0418838,0.0007117465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003857137,0.002181774,0.9781014,0.001994958,0.0001162281,0.0101966,0.0000287999,0.000006886175,0.003516207],"genre_scores_gemma":[0.007453151,0.00006085807,0.9818941,0.00008433569,0.00007132949,0.0008914482,0.000001272856,0.00002374905,0.009519768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8081785,"threshold_uncertainty_score":0.9998803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9529631762949683,"score_gpt":0.7824454287408193,"score_spread":0.1705177475541489,"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."}}