{"id":"W4411699008","doi":"10.1353/obs.2025.a963647","title":"A new four-arm within-study comparison: Design, implementation, and data","year":2025,"lang":"en","type":"article","venue":"Observational Studies","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Education and Early Childhood Development","funders":"University of Virginia","keywords":"Computer science","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":[0.3930631,0.00431538,0.009295423,0.006589409,0.004485037,0.006299852,0.006052107,0.01204974,0.01848224],"category_scores_gemma":[0.5912436,0.004539834,0.01022132,0.009218685,0.007241996,0.01169122,0.00931976,0.01118248,0.003545593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005076264,"about_ca_system_score_gemma":0.01236204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001023773,"about_ca_topic_score_gemma":0.001188549,"domain_scores_codex":[0.4026516,0.4904137,0.0447966,0.02676672,0.0322871,0.003084255],"domain_scores_gemma":[0.4054833,0.36037,0.03868833,0.1387331,0.05108681,0.005638547],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.1294183,0.01406246,0.02403788,0.03765072,0.03155931,0.0006950377,0.007278305,0.0189742,0.009543931,0.1520019,0.03536837,0.5394097],"study_design_scores_gemma":[0.1801614,0.09667128,0.03130766,0.007437414,0.02198353,0.0009410635,0.001414492,0.09758968,0.02039477,0.343233,0.1966188,0.002246893],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02223315,0.001597884,0.7264767,0.002247311,0.007454487,0.2263339,0.005207978,0.002205707,0.006242873],"genre_scores_gemma":[0.03065813,0.0001823138,0.5528226,0.0008442148,0.0003149637,0.4139265,0.0005182795,0.0001990092,0.0005340152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6069369,"threshold_uncertainty_score":0.7484613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8056678441780485,"score_gpt":0.5920920188067013,"score_spread":0.2135758253713472,"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."}}