{"id":"W7115714437","doi":"10.48448/s1j9-wp94","title":"Domain-specific Pretrained Encoder Transformers for the Identification of Methodologically Rigorous Systematic Reviews: A Retrospective Modeling Study","year":2025,"lang":"","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Systematic review; Transformer; Identification (biology); Data extraction; Encoder; Narrative; Ground truth","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","open_science"],"consensus_categories":["metaresearch","metaepi_narrow","sts"],"category_scores_codex":[0.09596154,0.001891779,0.005291003,0.002837664,0.002418246,0.0008639632,0.005832032,0.000754529,0.0005246567],"category_scores_gemma":[0.00915058,0.001209515,0.001276498,0.009280412,0.004939819,0.0008595447,0.0003909511,0.001396639,0.0002860048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002844369,"about_ca_system_score_gemma":0.002782812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001192657,"about_ca_topic_score_gemma":0.0003477217,"domain_scores_codex":[0.9745085,0.005251772,0.009187317,0.004395473,0.004613609,0.002043359],"domain_scores_gemma":[0.978887,0.005534076,0.006993287,0.003480171,0.004732367,0.0003730553],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004696858,0.02168443,0.0002955579,0.2223164,0.0124026,0.0000405186,0.1181636,0.08276307,0.2439638,0.2474119,0.003294247,0.04296703],"study_design_scores_gemma":[0.005383912,0.002894488,0.0001583112,0.02589942,0.00659833,0.00003399568,0.06215001,0.8684712,0.0005968072,0.02248098,0.002513118,0.002819451],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005018159,0.01484143,0.9138129,0.0002038338,0.001746293,0.06218755,0.0005956861,0.0001838929,0.005926599],"genre_scores_gemma":[0.7398762,0.008615388,0.2157841,0.0001725612,0.0006831637,0.01231985,0.00008996697,0.001081781,0.02137701],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7857081,"threshold_uncertainty_score":0.9995469,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1202096400569525,"score_gpt":0.3808638434936585,"score_spread":0.260654203436706,"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."}}