{"id":"W2125539455","doi":"10.1007/s11145-012-9370-y","title":"Measures of reading comprehension: do they measure different skills for children learning English as a second language?","year":2012,"lang":"en","type":"article","venue":"Reading and Writing","topic":"Reading and Literacy Development","field":"Psychology","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute for Christian Studies; University of Toronto; Wilfrid Laurier University","funders":"","keywords":"Reading comprehension; Psychology; Vocabulary; Language proficiency; Test (biology); Language assessment; Reading (process); Linguistics; 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":[0.001115621,0.0002570687,0.0004504405,0.0001684994,0.0002982363,0.00008224639,0.0001233553,0.0001508428,0.00009011485],"category_scores_gemma":[0.0003554801,0.0002219218,0.0001168131,0.00009017492,0.00004205355,0.0001409527,0.00005821272,0.0003236065,0.00001048456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004019299,"about_ca_system_score_gemma":0.00001286602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006350714,"about_ca_topic_score_gemma":0.000002350209,"domain_scores_codex":[0.9981467,0.0002073887,0.0004623792,0.0003576938,0.0002330613,0.0005927394],"domain_scores_gemma":[0.998534,0.0006928263,0.000236767,0.0002180703,0.0001375971,0.0001806978],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008893451,0.0001920647,0.6307336,0.0001674986,0.0003742346,0.000004287979,0.1524621,0.000005711211,0.006694945,0.004615289,0.0006844837,0.2039769],"study_design_scores_gemma":[0.005318417,0.0005362613,0.8942807,0.004133392,0.0003847876,0.0005719435,0.05869493,0.00005541331,0.01911892,0.0005260851,0.01453989,0.001839272],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9818621,0.002421143,0.0001412004,0.00002088222,0.0004175097,0.000294811,0.00001321931,0.000125511,0.01470359],"genre_scores_gemma":[0.9970471,0.00002849946,0.0006601502,0.00005499933,0.0006822918,0.00004365305,0.00003798158,0.00004936304,0.00139598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2635471,"threshold_uncertainty_score":0.9049709,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01835049771966362,"score_gpt":0.2942640379052278,"score_spread":0.2759135401855642,"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."}}