{"id":"W2889038510","doi":"10.3389/feduc.2018.00068","title":"Validity Evidence for Progress Monitoring With Star Reading: Slope Estimates, Administration Frequency, and Number of Data Points","year":2018,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Reading and Literacy Development","field":"Psychology","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Star (game theory); Data collection; Computer science; Outlier; Estimator; Psychology; Statistics; Mathematics; Artificial intelligence","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3070572,0.0009961363,0.001567951,0.003687792,0.001716242,0.005532535,0.003731128,0.003130416,0.003266175],"category_scores_gemma":[0.7179549,0.001414453,0.004434395,0.005586388,0.006108296,0.00803673,0.004654564,0.003537278,0.001251609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002609184,"about_ca_system_score_gemma":0.004781047,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007290993,"about_ca_topic_score_gemma":0.005430514,"domain_scores_codex":[0.6337258,0.2639587,0.02568038,0.02329987,0.05175463,0.001580731],"domain_scores_gemma":[0.09696386,0.7729615,0.0617649,0.04192803,0.02521329,0.001168512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002357209,0.0004521307,0.8617611,0.001634447,0.003055071,0.00007405614,0.004987918,0.004024934,0.0005232453,0.005720569,0.001622099,0.1137872],"study_design_scores_gemma":[0.000495437,0.003395027,0.9222145,0.003934357,0.002249475,0.0004853672,0.003541678,0.03812565,0.004517067,0.01089093,0.009836226,0.0003142514],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7621611,0.01307268,0.1801261,0.007705856,0.0008146573,0.002048952,0.002157078,0.0006828749,0.03123077],"genre_scores_gemma":[0.9494652,0.001299732,0.04566551,0.0006454195,0.0001265775,0.0008392767,0.0009667776,0.0001970202,0.0007945764],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3070572,"threshold_uncertainty_score":0.8545218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09735874007776728,"score_gpt":0.4260005749852975,"score_spread":0.3286418349075302,"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."}}