{"id":"W1540816673","doi":"10.1186/1471-2288-6-33","title":"An alternative to the hand searching gold standard: validating methodological search filters using relative recall","year":2006,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":135,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University; University of Ottawa; Canadian Agency for Drugs and Technologies in Health; University of Alberta; University of Saskatchewan; McGill University; Children's Hospital of Eastern Ontario","funders":"","keywords":"Recall; Gold standard (test); MEDLINE; Systematic review; Information retrieval; Randomized controlled trial; Computer science; Medicine; Medical physics; Psychology; Cognitive psychology; Surgery","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","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.8495484,0.0004835408,0.004433924,0.001435927,0.001256148,0.001702109,0.007106004,0.0004675251,0.01203458],"category_scores_gemma":[0.7982743,0.0002099343,0.001266473,0.004475316,0.00174242,0.000429027,0.001796922,0.002875154,0.001070932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003058246,"about_ca_system_score_gemma":0.001423066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002134492,"about_ca_topic_score_gemma":0.001740123,"domain_scores_codex":[0.2719673,0.6837581,0.008690671,0.003010397,0.03051772,0.002055829],"domain_scores_gemma":[0.2640494,0.7172171,0.002359892,0.007166168,0.006905403,0.002301949],"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":[0.002016602,0.0005876626,0.03612406,0.0003491118,0.001154702,0.0007119646,0.02225753,0.05258331,0.03397582,0.1557442,0.08959498,0.6049],"study_design_scores_gemma":[0.001750821,0.002228586,0.01123045,0.0004955764,0.0002572198,0.0003510556,0.02098431,0.5428141,0.006962657,0.3115436,0.1002563,0.001125313],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2521131,0.0002596586,0.7389576,0.004101774,0.0003117267,0.001244925,0.00002837099,0.00001171283,0.00297113],"genre_scores_gemma":[0.1928218,0.000023984,0.801646,0.0006123479,0.001065968,0.0001184737,0.00001428235,0.00003988696,0.003657206],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6037747,"threshold_uncertainty_score":0.9997069,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9791445577134705,"score_gpt":0.7440587898908313,"score_spread":0.2350857678226392,"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."}}