{"id":"W4410496288","doi":"10.1080/2330443x.2025.2505485","title":"Designing Randomized Experiments to Predict Unit-Specific Treatment Effects","year":2025,"lang":"en","type":"article","venue":"Statistics and Public Policy","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada); Science North","funders":"Institute of Education Sciences","keywords":"Randomized controlled trial; Randomized experiment; Unit (ring theory); Statistics; Environmental science; Econometrics; Mathematics; Medicine; Internal medicine; Mathematics education","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":[],"consensus_categories":[],"category_scores_codex":[0.0002930746,0.0002227965,0.0004989494,0.0003682057,0.0001359133,0.0001240196,0.000122126,0.00006538209,0.00002623956],"category_scores_gemma":[0.002039694,0.0001795679,0.0000393846,0.0003220188,0.0001192533,0.00007903524,0.00008722576,0.00007552339,0.000006023404],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000161132,"about_ca_system_score_gemma":0.0001874051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001842569,"about_ca_topic_score_gemma":0.00001285803,"domain_scores_codex":[0.9987453,0.0001932443,0.0003170801,0.0002441366,0.0001383943,0.0003618553],"domain_scores_gemma":[0.9970994,0.002244949,0.00008307575,0.000285165,0.00009903899,0.0001883715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003942347,0.00008234305,0.00005559854,0.00004774515,0.00007807282,0.000005532827,0.0004315811,4.74194e-7,0.0006858857,0.9556571,0.005221601,0.0373398],"study_design_scores_gemma":[0.01753044,0.0002312331,0.000071469,0.0001013314,0.00004616789,0.000002294743,0.00008317687,0.0001842168,0.008543748,0.9605782,0.01240998,0.0002177498],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004270703,0.0002212181,0.9844805,0.0004384272,0.0000865065,0.00115745,0.0001174513,0.0002190384,0.00900868],"genre_scores_gemma":[0.3791264,0.0005584948,0.6162775,0.0005260271,0.0001171818,0.0008063606,0.00003779846,0.00003903095,0.002511266],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3748557,"threshold_uncertainty_score":0.7322567,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1037738445520644,"score_gpt":0.4309174257674586,"score_spread":0.3271435812153942,"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."}}