{"id":"W4399443232","doi":"10.1080/15434303.2024.2364172","title":"Adapting to a New Normal: A Review of <i>Technology Assisted Language Assessment in Diverse Contexts</i>","year":2024,"lang":"en","type":"review","venue":"Language Assessment Quarterly","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Language assessment; Psychology; Computer science; Linguistics; Mathematics education","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001219577,0.0009945481,0.00318065,0.00120721,0.00005701721,0.00008725081,0.001265385,0.0006757113,0.005208087],"category_scores_gemma":[0.00005081854,0.0007797022,0.0008569763,0.002627925,0.00008206622,0.0001396408,0.0001992962,0.001857733,0.0009801629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004264192,"about_ca_system_score_gemma":0.0009391439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001096198,"about_ca_topic_score_gemma":0.000255758,"domain_scores_codex":[0.9937788,0.000838128,0.002273635,0.001448543,0.0007373664,0.0009235708],"domain_scores_gemma":[0.9966918,0.0004179949,0.0009867125,0.001429248,0.0001127428,0.0003615312],"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":[0.00001018197,0.0007659027,0.00007668431,0.02602696,0.0005116272,0.0007819039,0.003198119,5.286821e-8,0.00001203882,0.003031937,0.02528999,0.9402946],"study_design_scores_gemma":[0.001004525,0.001543324,0.0008703185,0.141155,0.00191417,0.0002414291,0.01584509,9.595494e-7,3.777366e-7,0.0001956572,0.8359751,0.001254094],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0002474536,0.9700064,0.0003376279,0.001013495,0.001764538,0.00266862,0.0003326955,0.0002344303,0.02339474],"genre_scores_gemma":[0.0007106119,0.9723353,0.008967584,0.002149634,0.0005942453,0.001815903,0.000927054,0.0001885249,0.01231116],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9390405,"threshold_uncertainty_score":0.9997977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05299991408977252,"score_gpt":0.4712575397084361,"score_spread":0.4182576256186636,"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."}}