{"id":"W4414008064","doi":"10.1101/2025.09.03.25334905","title":"INSPECT-SR: a tool for assessing trustworthiness of randomised controlled trials","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nova Scotia Health Authority; Dalhousie University","funders":"National Institute for Health and Care Research; Queensland University of Technology; Neuroscience Research Australia","keywords":"Trustworthiness; Psychology; Computer science; Social psychology","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":[0.5287825,0.006566423,0.01190926,0.04279414,0.003615634,0.01723905,0.008013002,0.008228066,0.08556894],"category_scores_gemma":[0.8766453,0.007806118,0.02155281,0.03092024,0.006687186,0.01514622,0.02054182,0.01211863,0.01898891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007491553,"about_ca_system_score_gemma":0.04304251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003046191,"about_ca_topic_score_gemma":0.005795135,"domain_scores_codex":[0.3175602,0.4745372,0.1476908,0.01194116,0.04638667,0.001884034],"domain_scores_gemma":[0.0389481,0.8560978,0.03909518,0.03355171,0.03087133,0.00143595],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.005670681,0.0002605535,0.006154586,0.2001504,0.01687043,0.0007650953,0.008903895,0.005039437,0.001699116,0.05249447,0.2726126,0.4293788],"study_design_scores_gemma":[0.01701428,0.001426085,0.01066962,0.1043574,0.02004252,0.00191618,0.002034599,0.04156776,0.007557665,0.2314199,0.5598044,0.00218975],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00391995,0.01128767,0.7667996,0.009950913,0.004164002,0.07618069,0.06133358,0.04849761,0.01786595],"genre_scores_gemma":[0.01257832,0.002154379,0.8560063,0.001355829,0.0004519475,0.1143656,0.006303451,0.004604706,0.00217935],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4712175,"threshold_uncertainty_score":0.581095,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6793051329169049,"score_gpt":0.5562413940769169,"score_spread":0.123063738839988,"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."}}