{"id":"W4286697650","doi":"10.3389/fcomm.2022.798196","title":"Exploring the validity and reliability of online assessment for conversational, narrative, and expository discourse measures in school-aged children","year":2022,"lang":"en","type":"article","venue":"Frontiers in Communication","topic":"Language Development and Disorders","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University; University of Alberta; Université de Montréal; Institute for Christian Studies; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Narrative; Psychology; Vocabulary; Test (biology); Reliability (semiconductor); Validity; Linguistics; Developmental psychology; Psychometrics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001027348,0.00006477154,0.0001202127,0.00007129933,0.0001951351,0.000009326743,0.000205495,0.00001963145,0.00002561021],"category_scores_gemma":[0.00008983925,0.00005706249,0.00001719226,0.0001127211,0.0001325808,0.0001378519,0.0001299024,0.0002107597,4.112365e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009857715,"about_ca_system_score_gemma":0.00004973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003528765,"about_ca_topic_score_gemma":0.0002232823,"domain_scores_codex":[0.9988313,0.000612623,0.0002143948,0.0001436063,0.0001146628,0.0000834087],"domain_scores_gemma":[0.9993326,0.0001938576,0.00009651716,0.0003352186,0.00002474068,0.0000170858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009452009,0.0001787102,0.9626441,0.000006543231,0.00001580456,9.544477e-8,0.0327887,0.00008014306,0.0000198707,0.0000925526,0.001751528,0.002327411],"study_design_scores_gemma":[0.0009604513,0.00003395581,0.9155852,0.000007927696,0.000007922091,4.184527e-7,0.08205785,0.0001883404,0.00000658859,0.0009565011,0.000134868,0.00006003361],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959323,0.000903411,0.0008808602,0.001396644,0.0002154173,0.0005271812,0.00002867551,0.000007414424,0.0001080743],"genre_scores_gemma":[0.9914957,0.000225448,0.007574579,0.00005255972,0.000008125202,0.000422686,0.0001832684,0.000006070321,0.0000315812],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04926915,"threshold_uncertainty_score":0.2326941,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06338947467737487,"score_gpt":0.3357645474478133,"score_spread":0.2723750727704384,"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."}}