{"id":"W4307244303","doi":"10.1075/itl.22008.rob","title":"3K-LEx-MC","year":2022,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rasch model; Coursework; Test (biology); Vocabulary; Reliability (semiconductor); Mathematics education; Psychology; Item analysis; Curse of dimensionality; Item response theory; Polytomous Rasch model; English as a foreign language; Natural language processing; Computer science; Statistics; Mathematics; Linguistics; Psychometrics","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":[0.0005942946,0.0001165687,0.0003162982,0.00006380121,0.0001146959,0.000005338046,0.000256522,0.00003337443,0.1638821],"category_scores_gemma":[0.0004733918,0.0001192299,0.0001001272,0.0002389161,0.00003925458,0.000002123729,0.0001006818,0.0003323356,0.0004154997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002883899,"about_ca_system_score_gemma":0.00003517386,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001060087,"about_ca_topic_score_gemma":1.683784e-7,"domain_scores_codex":[0.9988395,0.0000873309,0.0004112987,0.0002266013,0.0002396651,0.0001956127],"domain_scores_gemma":[0.9990296,0.0001406445,0.0002529329,0.0004399091,0.000078952,0.00005793231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006878004,0.0002518424,0.00002721723,0.002515494,0.000114681,0.0001183118,0.002488685,0.00003676484,0.0001142112,0.7750891,0.1673112,0.05186367],"study_design_scores_gemma":[0.0002563629,0.00004955083,0.00007535984,0.0001757743,0.00005889246,0.00001149369,0.0008559735,0.000006847406,0.00002715626,0.0004888464,0.9978611,0.0001326562],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0005529996,0.1153121,0.00008061261,0.00008144835,0.001352239,0.0003115216,0.00003684311,0.00007278652,0.8821994],"genre_scores_gemma":[0.9049552,0.00260999,0.00323057,0.08070447,0.002113535,0.0003463925,0.0003159364,0.0001045307,0.005619362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9044022,"threshold_uncertainty_score":0.8368822,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0166220771278062,"score_gpt":0.3283745859540633,"score_spread":0.311752508826257,"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."}}