{"id":"W4410250207","doi":"10.1186/s12874-025-02581-7","title":"Critically appraising the cass report: methodological flaws and unsupported claims","year":2025,"lang":"en","type":"article","venue":"BMC Medical Research Methodology","topic":"Sex and Gender in Healthcare","field":"Medicine","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"MEDLINE; Medicine; Computer science; Data science; Psychology; Actuarial science; Political science; Law; Business","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","sts","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.107652,0.0002343484,0.001012054,0.0003984373,0.0005378458,0.00004306054,0.0004785667,0.0009178251,0.0008407409],"category_scores_gemma":[0.4591711,0.0001389681,0.0001686154,0.001049457,0.002884418,0.00003745051,0.0006429349,0.003037381,0.0000235016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009996869,"about_ca_system_score_gemma":0.003556721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004062245,"about_ca_topic_score_gemma":0.0003358176,"domain_scores_codex":[0.9579402,0.03628965,0.00111211,0.00116508,0.002119921,0.001373074],"domain_scores_gemma":[0.759724,0.2355942,0.0001037999,0.001576529,0.00156669,0.00143476],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002344586,0.0003520093,0.04834314,0.002420532,0.0003770721,0.009457012,0.001254496,0.00000103423,0.003459027,0.1311349,0.02954729,0.7713088],"study_design_scores_gemma":[0.005882678,0.002314653,0.2997829,0.00116234,0.0003937525,0.02603271,0.01771855,0.004692676,0.003358016,0.3151914,0.3228055,0.000664878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1630988,0.00638859,0.6238983,0.1841998,0.001643218,0.001763067,0.000005513325,0.0002113099,0.01879135],"genre_scores_gemma":[0.3588415,0.002022409,0.6010165,0.02675607,0.002268304,0.0004939937,0.00006910595,0.0000722438,0.00845987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.770644,"threshold_uncertainty_score":0.9998292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8157749592780283,"score_gpt":0.6809390048541768,"score_spread":0.1348359544238515,"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."}}