{"id":"W4416287994","doi":"10.2139/ssrn.5755162","title":"<p>Cheaper (and more effective) by the dozen: <span>Evidence from 12 randomized A/B tests optimizing tutoring for scale</span></p>","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Global Educational Reforms and Inequalities","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Impact","funders":"","keywords":"Test (biology); Scale (ratio); Identification (biology); Measure (data warehouse); Educational testing; Randomized controlled trial; Test score","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","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.02456118,0.002069265,0.003592967,0.0005192255,0.005536444,0.002456081,0.00346084,0.001458358,0.0003786747],"category_scores_gemma":[0.009872449,0.001513091,0.002424046,0.001006188,0.002258523,0.001974677,0.001202113,0.006657665,0.00004654372],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.008433732,"about_ca_system_score_gemma":0.01716589,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005406983,"about_ca_topic_score_gemma":0.01393066,"domain_scores_codex":[0.9807227,0.002988677,0.003234893,0.00244901,0.003229003,0.007375744],"domain_scores_gemma":[0.9829224,0.01001915,0.002860334,0.001287914,0.001906993,0.001003213],"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":[0.07351623,0.0026031,0.004155274,0.002040328,0.015813,0.00001609182,0.1663003,0.01093298,0.02876179,0.4611241,0.01962274,0.2151141],"study_design_scores_gemma":[0.08148893,0.001373823,0.003792895,0.01206052,0.006137157,0.0003655808,0.03255493,0.004900205,0.0008033928,0.5025931,0.3472224,0.006707136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6918524,0.2293057,0.02849152,0.01794364,0.01074315,0.01035808,0.0006509685,0.0002634753,0.01039112],"genre_scores_gemma":[0.7842553,0.1752541,0.002650966,0.0007187112,0.00578121,0.001770524,0.0001598434,0.0001851793,0.02922419],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3275996,"threshold_uncertainty_score":0.9998379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01887907877773646,"score_gpt":0.3183404506011464,"score_spread":0.2994613718234099,"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."}}