{"id":"W7084152648","doi":"10.64628/aai.dwg6r3ctf","title":"Texas’ annual reading test adjusted its difficulty every year, masking whether students are improving","year":2025,"lang":"en","type":"article","venue":"","topic":"Retinal Diseases and Treatments","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Test (biology); Masking (illustration); Reading (process); Noise (video)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003907699,0.0007373281,0.0005991283,0.001826399,0.001105527,0.002284253,0.001065377,0.001020083,0.01075718],"category_scores_gemma":[0.02412105,0.0003387597,0.0009351911,0.001600582,0.0006315332,0.00170305,0.001400493,0.002423655,0.003082505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001427202,"about_ca_system_score_gemma":0.00284831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0276694,"about_ca_topic_score_gemma":0.04056684,"domain_scores_codex":[0.995339,0.00082905,0.0009875993,0.0009370652,0.001216166,0.0006911394],"domain_scores_gemma":[0.9746912,0.002846492,0.00515378,0.00210593,0.01344611,0.001756443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001134215,0.0009880764,0.8539287,0.0003027214,0.0003812863,0.0001477909,0.001557107,0.0004892327,0.00162278,0.001990643,0.06513971,0.07231777],"study_design_scores_gemma":[0.000101744,0.0009379184,0.9423976,0.0001735241,0.0002951029,0.0002520334,0.00146254,0.001206212,0.005265191,0.0008677902,0.04697175,0.00006851897],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9002891,0.0009554351,0.005056346,0.0135814,0.00318918,0.000457253,0.01672472,0.0008812089,0.05886538],"genre_scores_gemma":[0.9626829,0.0002512485,0.004479299,0.003183386,0.0003831715,0.0003536965,0.005984977,0.0001817918,0.02249948],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0276694,"threshold_uncertainty_score":0.0550167,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0131920993001541,"score_gpt":0.3005895090892626,"score_spread":0.2873974097891085,"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."}}