{"id":"W3214027731","doi":"10.1177/02655322211052680","title":"Investigating and optimizing score dependability of a local ITA speaking test across language groups: A generalizability theory approach","year":2021,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalizability theory; Dependability; Language proficiency; Psychology; Variance (accounting); Test (biology); Construct (python library); Formative assessment; Computer science; Mathematics education; Developmental psychology; Accounting","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":[0.002905199,0.0001911051,0.0003354749,0.0000317507,0.0005742435,0.0001790089,0.0002677217,0.0001136641,0.00006458023],"category_scores_gemma":[0.006835991,0.0001870258,0.0000761772,0.0006511075,0.0007264764,0.0002795396,0.0003837637,0.0002698928,0.000001508345],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001011251,"about_ca_system_score_gemma":0.0001679251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003139915,"about_ca_topic_score_gemma":0.001562892,"domain_scores_codex":[0.997613,0.000506481,0.0003970895,0.0005083492,0.0004474028,0.0005277197],"domain_scores_gemma":[0.9972788,0.001854535,0.0002230849,0.0003255481,0.0001689809,0.0001490236],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000004317801,0.0001563806,0.6197887,0.0002300039,0.00002669257,0.00004828407,0.3206521,0.00007943944,0.02788865,0.001711013,0.000004185023,0.02941021],"study_design_scores_gemma":[0.0006748703,0.00004565737,0.09744235,0.0002598083,0.00006085772,0.00002414841,0.8915778,0.003956292,0.004598945,0.0008943815,0.000008816892,0.0004561183],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9803843,0.001152884,0.004781025,0.00004414874,0.00006582489,0.0002325634,0.00001666114,0.0001578173,0.01316473],"genre_scores_gemma":[0.9309824,0.000004254037,0.06854533,0.0001099143,0.0002212388,0.00001201781,0.00001568341,0.00002101095,0.00008821429],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5709257,"threshold_uncertainty_score":0.8183813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05086898553121055,"score_gpt":0.3497865942429446,"score_spread":0.2989176087117341,"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."}}