{"id":"W4390952982","doi":"10.35542/osf.io/d5qsy","title":"A Methodological Review on Dynamic Assessment of Reading Comprehension: An Appraisal of the Construct, Consequential and Social Validity","year":2024,"lang":"en","type":"review","venue":"","topic":"Educational and Psychological Assessments","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Operationalization; Construct (python library); Construct validity; Psychology; Comprehension; Reading comprehension; Reading (process); Relevance (law); Content validity; Dynamic assessment; Empirical research; Applied psychology; Cognitive psychology; Computer science; Developmental psychology; Psychometrics; Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09428213,0.002013928,0.00681214,0.03410512,0.001703336,0.005924331,0.003670885,0.002927365,0.002751552],"category_scores_gemma":[0.2754945,0.002281419,0.008157966,0.02615422,0.003223387,0.006151188,0.005311129,0.002988755,0.0007474889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007961072,"about_ca_system_score_gemma":0.03746848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008046844,"about_ca_topic_score_gemma":0.01857661,"domain_scores_codex":[0.9110081,0.03726435,0.03397185,0.003205977,0.01365959,0.0008902058],"domain_scores_gemma":[0.7141442,0.2070502,0.03171146,0.006740199,0.03894289,0.001411116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002578921,0.00004303858,0.001850579,0.6836096,0.004335373,0.000169737,0.001438486,0.0002834364,0.000487882,0.002218779,0.004698715,0.3006065],"study_design_scores_gemma":[0.0000944388,0.0002153392,0.004128363,0.9078664,0.01460865,0.0003336189,0.0008916512,0.0001338046,0.0003180252,0.001668471,0.0696914,0.00004991329],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0005526784,0.9957145,0.001328148,0.00106639,0.000333179,0.0003473857,0.000136697,0.00001104691,0.0005099787],"genre_scores_gemma":[0.0062325,0.9854879,0.00540824,0.0008902812,0.0001711346,0.001377138,0.0002690123,0.00001722118,0.0001466554],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.09428213,"threshold_uncertainty_score":0.4986175,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5605516196272393,"score_gpt":0.6228712514318672,"score_spread":0.06231963180462785,"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."}}