{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2069122,0.004030366,0.004928393,0.02318139,0.001485766,0.007219002,0.006428093,0.006622224,0.09145456],"category_scores_gemma":[0.5659015,0.004858485,0.007933688,0.0232208,0.002816246,0.007968167,0.005953002,0.007971635,0.03482619],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004182581,"about_ca_system_score_gemma":0.0215592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005548057,"about_ca_topic_score_gemma":0.008977717,"domain_scores_codex":[0.7457487,0.1835331,0.04912388,0.003660827,0.01703334,0.0009001552],"domain_scores_gemma":[0.3614536,0.5604676,0.02057807,0.01684848,0.03922993,0.001422261],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009898929,0.0002192159,0.001246422,0.07038168,0.001083806,0.0003535285,0.003957318,0.003847441,0.00136846,0.05891412,0.3600412,0.4975969],"study_design_scores_gemma":[0.002434638,0.0008064774,0.003332279,0.06708393,0.001317821,0.0009607335,0.00169884,0.01157009,0.002663578,0.1264442,0.7809343,0.0007529939],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001844993,0.01815739,0.8146431,0.0146927,0.003466916,0.06315902,0.03772911,0.01342744,0.03287937],"genre_scores_gemma":[0.002969892,0.005074061,0.9319572,0.002201571,0.0002963864,0.04981779,0.0028028,0.001305433,0.003574925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7930877,"threshold_uncertainty_score":0.9780184,"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."}}