{"id":"W2259831407","doi":"10.14288/1.0055674","title":"The validity and applicability of two modified cloze procedures (beginning of the page procedure and \"instant\" beginning of the page procedure) measured against the Stanford Diagnostic Reading Test and equated with the cloze procedure and Fry Readability Graph","year":2010,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Instant; Test (biology); Reading (process); Computer science; Natural language processing; Linguistics; Philosophy","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":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.00785513,0.0001966227,0.0006799708,0.0000826605,0.001788965,0.0002905804,0.001358705,0.0001854651,0.00000271082],"category_scores_gemma":[0.0475274,0.0001644914,0.0001323928,0.002217615,0.005248041,0.0003418011,0.0007702673,0.000727437,4.737154e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002735274,"about_ca_system_score_gemma":0.0003679804,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003349871,"about_ca_topic_score_gemma":0.0400783,"domain_scores_codex":[0.9962002,0.0006575229,0.0006175485,0.0008727023,0.001227973,0.0004240776],"domain_scores_gemma":[0.9762089,0.02000066,0.001447932,0.001204783,0.0009966296,0.0001411163],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00009675244,0.0001158111,0.9482162,0.0005246807,0.00006268024,0.00000390243,0.00231374,0.00003462444,0.00557886,0.00005058598,0.000271936,0.04273022],"study_design_scores_gemma":[0.0008445109,0.0001438612,0.9767397,0.0004295011,0.0001248678,0.00010235,0.01489596,0.0008878584,0.0001075306,0.005497985,0.00002590633,0.0001999461],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957616,0.0006123165,0.0002324549,0.0009212591,0.0000657284,0.001875891,0.000146471,0.00003397178,0.0003503047],"genre_scores_gemma":[0.999079,0.0002745111,0.0005049171,0.00005223729,0.00001984811,0.00001181022,0.000001198551,0.00001806283,0.00003835275],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04253028,"threshold_uncertainty_score":0.9995106,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06321896158872539,"score_gpt":0.2728894748875346,"score_spread":0.2096705132988092,"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."}}