{"id":"W2306465874","doi":"10.1080/17405629.2016.1152175","title":"Language sample analysis: development of a valid language assessment tool and determining the reliability of outcome measures for Farsi-speaking children","year":2016,"lang":"en","type":"article","venue":"European Journal of Developmental Psychology","topic":"Language Development and Disorders","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Bộ Giáo dục và Ðào tạo","keywords":"Psychology; Reliability (semiconductor); Developmental psychology; Test (biology); Sample (material); Language development; Consistency (knowledge bases); Language assessment; Correlation; Statistics; Computer science; Artificial intelligence; Mathematics; 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":[],"consensus_categories":[],"category_scores_codex":[0.003406261,0.0002601748,0.0006206545,0.0003905732,0.0001155591,0.0000182714,0.0005542222,0.00005996893,0.0002663494],"category_scores_gemma":[0.0004500348,0.0001523034,0.0002345535,0.0003252708,0.0002098899,0.0001185715,0.0001385762,0.0001697523,0.000006629977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006874784,"about_ca_system_score_gemma":0.00009810184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001160351,"about_ca_topic_score_gemma":0.0000331163,"domain_scores_codex":[0.9967565,0.0005589976,0.001628848,0.0003524341,0.00034683,0.0003564002],"domain_scores_gemma":[0.9977772,0.0004987188,0.001121884,0.0003111787,0.0002050966,0.00008587097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002791575,0.0002400548,0.7914968,0.00002508345,0.001295183,0.00001928209,0.0285928,0.000001346578,0.004010193,0.00004430713,0.0003235571,0.1736723],"study_design_scores_gemma":[0.003429126,0.0001958805,0.9897582,0.00005862634,0.0002286282,0.00005277149,0.004068575,5.697548e-7,0.000925027,0.00002060372,0.001029225,0.0002327695],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9669754,0.0003171702,0.02982825,0.0001677618,0.0003029375,0.0003090563,0.00003860042,0.00001488872,0.002045971],"genre_scores_gemma":[0.9362154,0.00001261451,0.06333958,0.0002300397,0.00004933147,0.00000789861,0.00001572961,0.0000330834,0.00009630415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1982615,"threshold_uncertainty_score":0.6210752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04182047617899476,"score_gpt":0.3645352395741077,"score_spread":0.3227147633951129,"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."}}