{"id":"W3161217840","doi":"10.1037/cbs0000257","title":"Determining the appropriateness of extended time accommodations in standardized cognitive ability testing.","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Behavioural Science/Revue canadienne des sciences du comportement","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Psychology; Standardized test; Cognition; Cognitive psychology; Cognitive test; Mathematics education; Neuroscience","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003874742,0.0001469377,0.000308609,0.0003800227,0.0008523116,0.000134786,0.000934001,0.00004490037,0.001181039],"category_scores_gemma":[0.0009490437,0.0001063475,0.00009048748,0.002240418,0.00355109,0.0003532173,0.00004635519,0.000234147,0.000004827173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007202365,"about_ca_system_score_gemma":0.003748951,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01731882,"about_ca_topic_score_gemma":0.09229019,"domain_scores_codex":[0.997633,0.0002247112,0.0007821681,0.0003732687,0.0003079696,0.0006788949],"domain_scores_gemma":[0.996595,0.0004227128,0.0005212667,0.0002119787,0.001571317,0.0006777803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000008768454,0.0001834504,0.9844277,0.000004775839,0.00001253416,0.0001283168,0.003617672,0.00004866713,0.0004253135,0.001234107,0.00005249655,0.009856185],"study_design_scores_gemma":[0.0005576003,0.0003095783,0.9903183,0.0001181492,0.00003198294,0.0002403457,0.005707743,0.00008249474,0.0000934534,0.002307546,0.00009794525,0.0001348537],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.993445,0.00008500082,0.00004642444,0.001143646,0.0009596258,0.0002088592,0.00006687699,0.000003021696,0.004041487],"genre_scores_gemma":[0.9985154,0.000001300621,0.001178946,0.0001607282,0.00005091647,0.00001392006,0.000006546494,0.00000491423,0.0000673695],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07497137,"threshold_uncertainty_score":0.999732,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2141996230441462,"score_gpt":0.3624301815455119,"score_spread":0.1482305585013658,"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."}}