{"id":"W4414480124","doi":"10.1016/j.jval.2025.09.008","title":"Validating Loon Lens 1.0 for Autonomous Abstract Screening and Confidence-Guided Human-in-the-Loop Workflows in Systematic Reviews","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Ottawa Public Health; University of Ottawa; Dalhousie University; Ottawa Hospital; Life Prediction Technologies (Canada)","funders":"","keywords":"Workflow; False positive paradox; Sensitivity (control systems); Lens (geology); True positive rate; Through-the-lens metering","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":[0.3036532,0.003167564,0.004370851,0.01059183,0.002179618,0.0174965,0.004236467,0.004028996,0.01592209],"category_scores_gemma":[0.7048997,0.003668758,0.007796909,0.007122315,0.002051927,0.009288698,0.01176016,0.003744236,0.005011242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004512846,"about_ca_system_score_gemma":0.02818902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006893819,"about_ca_topic_score_gemma":0.01474937,"domain_scores_codex":[0.6884773,0.2469843,0.03699051,0.01182606,0.01408051,0.001641284],"domain_scores_gemma":[0.1565215,0.7737933,0.02069087,0.02842413,0.01895343,0.001616722],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0156496,0.0006227821,0.04206232,0.1046463,0.02135119,0.0006005291,0.01407761,0.02070738,0.006366611,0.04469352,0.1343897,0.5948325],"study_design_scores_gemma":[0.01391684,0.00321558,0.03657016,0.04810906,0.0228281,0.001135421,0.004087805,0.2659246,0.03006626,0.2422766,0.3291028,0.002766783],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04657653,0.02381942,0.6859016,0.01698714,0.002190739,0.01458442,0.03925475,0.1508429,0.01984253],"genre_scores_gemma":[0.1021244,0.001650301,0.8723618,0.002154049,0.0001870934,0.009364565,0.005307958,0.005884411,0.0009654584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6963468,"threshold_uncertainty_score":0.8587195,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8436006557405845,"score_gpt":0.572996590528697,"score_spread":0.2706040652118875,"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."}}