{"id":"W4384928612","doi":"10.1002/tesq.3248","title":"Evaluating the Application of a Gap‐Fill Exercise on the Learning of Phrasal Verbs: Do Errors Help or Hinder Learning?","year":2023,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Recall; Mainstream; Logistic regression; Psychology; Key (lock); Computer science; Cognitive psychology; Natural language processing; Machine learning","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00174328,0.0001752211,0.0002573089,0.0001539383,0.0002594837,0.00002935872,0.0003466854,0.0001132452,0.01136838],"category_scores_gemma":[0.0002806895,0.0001041664,0.0001270581,0.0006075276,0.0001215465,0.00005491546,0.00002376273,0.0006053993,0.0009597169],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001979184,"about_ca_system_score_gemma":0.00003260385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001515575,"about_ca_topic_score_gemma":0.000004921702,"domain_scores_codex":[0.997784,0.0007440964,0.0004320375,0.0003275975,0.0003947551,0.0003175185],"domain_scores_gemma":[0.9975152,0.001376822,0.0004364497,0.0005231954,0.0001056051,0.00004271379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.001442955,0.0003369934,0.003915398,0.0001275228,0.000266591,0.00002927937,0.3770627,0.005724615,0.02211544,0.007638962,0.004588509,0.576751],"study_design_scores_gemma":[0.005127294,0.01333908,0.08427557,0.0006717237,0.000380907,0.00006394055,0.7910175,0.09042674,0.001649338,0.001590027,0.01039961,0.001058212],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9932408,0.000422529,0.0004299527,0.0004828839,0.0001650759,0.0005211547,0.000003712734,0.0001966086,0.004537222],"genre_scores_gemma":[0.9955043,0.000002905883,0.00004102213,0.0005272299,0.0001245835,0.0001706346,0.00002488117,0.00004149205,0.003562995],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5756928,"threshold_uncertainty_score":0.9998181,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07196302325841941,"score_gpt":0.3995371549854314,"score_spread":0.327574131727012,"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."}}