{"id":"W2171914249","doi":"10.1027/1614-2241/a000041","title":"An Improved Model for Evaluating Change in Randomized Pretest, Posttest, Follow-Up Designs","year":2011,"lang":"en","type":"article","venue":"Methodology","topic":"Advanced Causal Inference Techniques","field":"Mathematics","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Treatment and control groups; Research design; Monte Carlo method; Randomized controlled trial; Randomized experiment; Treatment effect; Computer science; Psychology; Mathematics education; Statistics; Mathematics; Medicine","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"],"consensus_categories":[],"category_scores_codex":[0.01341952,0.000268516,0.001163751,0.0002134146,0.00005633315,0.000009516426,0.0003468302,0.0002845224,0.00006018556],"category_scores_gemma":[0.01987813,0.0002341202,0.0001765244,0.0001364146,0.000133892,0.0002811415,0.00007115976,0.0002329191,0.000001713988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006853769,"about_ca_system_score_gemma":0.00007013648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001574973,"about_ca_topic_score_gemma":0.000203963,"domain_scores_codex":[0.9951114,0.003105678,0.0006955754,0.0004575245,0.0001101808,0.000519657],"domain_scores_gemma":[0.9880812,0.01072997,0.0003557896,0.0005433143,0.0002067873,0.00008291464],"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":[0.07496352,0.0005553251,0.0005048416,0.000401363,0.0001853938,0.00001108241,0.05416607,0.00006615729,0.3947743,0.4008765,0.00009144522,0.07340399],"study_design_scores_gemma":[0.01724038,0.0003936907,0.00001427324,0.00002248481,0.00007411285,0.000004155736,0.00005906547,0.3422239,0.01857825,0.6212115,5.773113e-7,0.0001776332],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05823003,0.00005689427,0.9377424,0.00004235371,0.0001214547,0.003163896,0.00001032868,0.0003344858,0.0002981564],"genre_scores_gemma":[0.1389509,0.000009193798,0.8572371,0.0002578579,0.00004572423,0.003312486,0.000007613034,0.00006189768,0.0001172628],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3761961,"threshold_uncertainty_score":0.9883779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8674030637400533,"score_gpt":0.5803188037493868,"score_spread":0.2870842599906664,"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."}}