{"id":"W2751665091","doi":"10.1177/0265532217725776","title":"Developing and evaluating a computerized adaptive testing version of the Word Part Levels Test","year":2017,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Affix; Test (biology); Vocabulary; Computerized adaptive testing; Natural language processing; Computer science; Strengths and weaknesses; Word (group theory); Vocabulary development; Psychology; Artificial intelligence; Linguistics; Psychometrics; Social psychology","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":[],"category_scores_codex":[0.000790643,0.000162312,0.0002278304,0.00005119954,0.0008287188,0.0001021234,0.0003649237,0.00007422241,0.0009806536],"category_scores_gemma":[0.006763358,0.000129223,0.00004254717,0.0001616689,0.0001406091,0.0001251,0.0003329338,0.0002690206,0.00002311434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003465663,"about_ca_system_score_gemma":0.00005882418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004465764,"about_ca_topic_score_gemma":0.000009796505,"domain_scores_codex":[0.9987025,0.0001930062,0.000304242,0.0003162948,0.0001861042,0.0002978563],"domain_scores_gemma":[0.9969165,0.001758629,0.0005989927,0.0005382026,0.0001361888,0.00005146461],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00005352444,0.0000640029,0.1665237,0.0001040353,0.00009121967,0.0001821852,0.03009133,0.00004992958,0.08650853,0.0005274448,0.0001435773,0.7156605],"study_design_scores_gemma":[0.001919582,0.0001703422,0.9700329,0.001293133,0.0000598167,0.0001388607,0.01479074,0.009332729,0.001687327,0.0001035056,0.0001032619,0.0003677672],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.985706,0.0006465132,0.0005732497,0.0001113346,0.0003308207,0.0002103145,0.00001156913,0.0001019624,0.01230828],"genre_scores_gemma":[0.9532248,1.43564e-7,0.04534487,0.0007049604,0.0002424073,0.00001027271,0.000002501944,0.00002430771,0.0004456935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8035092,"threshold_uncertainty_score":0.9999326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1617082178408199,"score_gpt":0.3865890369439115,"score_spread":0.2248808191030916,"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."}}