{"id":"W2895759360","doi":"10.1002/tesq.478","title":"The Error in Trial and Error: Exercises on Phrasal Verbs","year":2018,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":68,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Victoria University of Wellington","keywords":"Set (abstract data type); Error analysis; Psychology; Computer science; Linguistics; Mathematics","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":[0.0003322049,0.0001135062,0.0001350787,0.00007704373,0.0001623083,0.00005789474,0.0001353094,0.00008411219,0.01103269],"category_scores_gemma":[0.0000381681,0.00008137305,0.00003722198,0.00009897865,0.0001440561,0.00005225447,0.000007019531,0.0001992253,0.001345279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001459009,"about_ca_system_score_gemma":0.00001151762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001253175,"about_ca_topic_score_gemma":0.0001292117,"domain_scores_codex":[0.998989,0.0001907297,0.0002008437,0.0002421997,0.0001037654,0.0002734853],"domain_scores_gemma":[0.9992595,0.0003044627,0.00006161551,0.0003002734,0.00001904747,0.0000550913],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.04597285,0.0006838864,0.001014524,0.00001337822,0.0001053367,0.0002569056,0.1887312,7.272151e-7,0.0008035164,0.01200309,0.07376716,0.6766474],"study_design_scores_gemma":[0.1840532,0.04762235,0.2443373,0.0001976547,0.0001483083,0.0002035533,0.2496223,0.0007096152,0.0003283975,0.003915686,0.2669353,0.001926427],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9734452,0.0007750402,0.00001236616,0.0004688514,0.0009379627,0.0002604816,0.000002846112,0.00006183701,0.02403542],"genre_scores_gemma":[0.9945975,0.000001103203,0.0000208372,0.002237148,0.0006676042,0.00004654334,0.000003727157,0.00001601615,0.002409548],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6747209,"threshold_uncertainty_score":0.9994323,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02843696649528885,"score_gpt":0.3513409058437909,"score_spread":0.322903939348502,"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."}}