{"id":"W4389628000","doi":"10.1075/itl.23002.iwa","title":"The effect of test format on productive recall of derivatives","year":2023,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Recall; Test (biology); Psychology; Vocabulary; Free recall; Cognitive psychology; Security token; Recall test; Logistic regression; Social psychology; Computer science; Linguistics; 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":[],"consensus_categories":[],"category_scores_codex":[0.001036043,0.0001146908,0.0003920208,0.00005752051,0.00004584172,0.000002814453,0.0001877046,0.00004570709,0.0005894321],"category_scores_gemma":[0.00737455,0.00007278936,0.00008907108,0.0003424643,0.0001357771,0.000003112856,0.00003545742,0.0001567072,0.0001048163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008370932,"about_ca_system_score_gemma":0.00001463196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003035739,"about_ca_topic_score_gemma":1.911685e-7,"domain_scores_codex":[0.9989592,0.0001039194,0.0004675549,0.0001512943,0.0001697456,0.0001483218],"domain_scores_gemma":[0.9966938,0.002260311,0.0004516169,0.0004133698,0.0001556727,0.00002520458],"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":[0.001455775,0.0004707251,0.0008267754,0.04538022,0.0008705567,0.00004078345,0.01890243,0.00008074285,0.00633783,0.3872176,0.1056516,0.4327649],"study_design_scores_gemma":[0.001766926,0.002693668,0.00483189,0.009845065,0.0003754608,0.000006177524,0.002917513,0.00004942718,0.06935375,0.001360597,0.9063309,0.0004686241],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.06250896,0.09028766,0.00006610567,0.0003058997,0.001883624,0.002937367,0.0001031309,0.0001672541,0.84174],"genre_scores_gemma":[0.9943416,0.003754262,0.0002298893,0.0007028843,0.0003980091,0.00008409272,0.00004452132,0.00003173594,0.000412995],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9318327,"threshold_uncertainty_score":0.8828558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0136442804867993,"score_gpt":0.3388036752652264,"score_spread":0.3251593947784271,"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."}}