{"id":"W4409425199","doi":"10.1101/2025.04.10.25325555","title":"Agreeability testing of AMSTAR-PF, a tool for quality appraisal of systematic reviews of prognostic factor studies","year":2025,"lang":"en","type":"preprint","venue":"medRxiv","topic":"Healthcare Systems and Public Health","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Systematic review; Quality (philosophy); Computer science; Biology; MEDLINE; Philosophy; Epistemology","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","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.01454361,0.0004144872,0.005883474,0.0002341934,0.0000455436,0.00000583775,0.0003161928,0.0003787758,0.000010919],"category_scores_gemma":[0.1722062,0.0002889437,0.0006217822,0.0004354809,0.0001810017,0.00003380173,0.0002781838,0.0004994774,8.996681e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001800593,"about_ca_system_score_gemma":0.003076714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001992794,"about_ca_topic_score_gemma":0.0001406207,"domain_scores_codex":[0.9899958,0.00230342,0.005960329,0.000648153,0.0006803244,0.0004119375],"domain_scores_gemma":[0.9772879,0.01341081,0.004090141,0.001737299,0.003271696,0.0002021538],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"observational","study_design_scores_codex":[0.00004178285,0.0001734655,0.339255,0.6562948,0.00025564,6.524771e-7,0.001825558,0.00000119804,0.0001301146,0.0001922544,0.00005667799,0.001772862],"study_design_scores_gemma":[0.001881962,0.001646364,0.5419497,0.4470291,0.001330148,0.00001269008,0.00228695,0.0004486159,0.0008941867,0.0005526166,0.001325914,0.0006417612],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9647694,0.01263259,0.001589101,0.000642699,0.001000241,0.01829095,0.0007895305,0.0000511146,0.0002344332],"genre_scores_gemma":[0.990476,0.0003901418,0.007195503,0.00005030288,0.0001692232,0.001539004,0.00003703233,0.00002377331,0.0001189909],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2092657,"threshold_uncertainty_score":0.9999563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4143643606593443,"score_gpt":0.5154356560217342,"score_spread":0.1010712953623899,"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."}}