{"id":"W2967888896","doi":"10.1186/s40468-019-0089-4","title":"Critical review of validation models and practices in language testing: their limitations and future directions for validation research","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Empirical research; Construct (python library); Computer science; Test (biology); Construct validity; Language assessment; Management science; Psychology; Data science; Psychometrics; Statistics; Mathematics education; Mathematics; Engineering","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002735364,0.00006949196,0.0001502008,0.0001527026,0.0001499818,0.00008018706,0.00009263175,0.00006174558,0.0000160549],"category_scores_gemma":[0.01415882,0.00006526084,0.00001480205,0.0007933145,0.00008805448,0.000451443,0.00003817369,0.0001685078,0.000001404285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004227183,"about_ca_system_score_gemma":0.00008187256,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001162787,"about_ca_topic_score_gemma":0.0006360557,"domain_scores_codex":[0.9987629,0.0003636256,0.0002224989,0.0002051008,0.0002461404,0.0001997506],"domain_scores_gemma":[0.9934998,0.005968047,0.0001359382,0.0001049516,0.0002546,0.00003669989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00003628138,0.0004542522,0.5374438,0.004326604,0.00002693351,0.00001091504,0.2725309,0.00004047256,0.0113778,0.03678451,0.0002439781,0.1367236],"study_design_scores_gemma":[0.001971348,0.0006180754,0.3427038,0.01084864,0.0001250269,0.00001389455,0.6132694,0.01257004,0.0007303106,0.01276918,0.003591396,0.0007888534],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.950391,0.009614783,0.00003289545,0.002890097,0.000101035,0.001037774,0.000009458484,0.00004831866,0.03587464],"genre_scores_gemma":[0.9844843,0.001522727,0.01356802,0.00003832878,0.0001552732,0.00007539793,0.00001775307,0.00001002022,0.0001281946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3407385,"threshold_uncertainty_score":0.9941453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2871225134574545,"score_gpt":0.4973541369068704,"score_spread":0.2102316234494159,"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."}}