{"id":"W2923725345","doi":"10.3389/feduc.2019.00020","title":"Development and Examination of a Tool to Assess Score Report Quality","year":2019,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Scale (ratio); Quality (philosophy); Stakeholder; Rating scale; Standards for Educational and Psychological Testing; Psychology; Sample (material); Applied psychology; Accountability; Medical education; Medicine; Political science; Higher education; Public relations; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.1408351,0.0009909123,0.001471125,0.01070416,0.001195369,0.004350089,0.002735447,0.001065198,0.002535958],"category_scores_gemma":[0.2409908,0.0008748181,0.002608898,0.006861562,0.001082994,0.004342023,0.003129284,0.002156511,0.00125259],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003032061,"about_ca_system_score_gemma":0.007739463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002562942,"about_ca_topic_score_gemma":0.003686425,"domain_scores_codex":[0.8855933,0.04244329,0.02609362,0.003197715,0.04080651,0.001865538],"domain_scores_gemma":[0.6279126,0.1785473,0.03063251,0.01805181,0.1418437,0.003012176],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005277101,0.001482146,0.2305211,0.00140271,0.0003941546,0.0001547289,0.005654799,0.001942296,0.003891857,0.006577004,0.01423201,0.7332196],"study_design_scores_gemma":[0.0007735639,0.009278345,0.7139939,0.004583483,0.0008307126,0.001547587,0.01489895,0.07046923,0.03241438,0.0158089,0.1344978,0.0009032103],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3614253,0.001211185,0.550996,0.004279358,0.001294281,0.03103924,0.006294576,0.005105795,0.03835417],"genre_scores_gemma":[0.3288707,0.0005886462,0.6436798,0.0005062788,0.0001560602,0.01980866,0.003446023,0.0002717504,0.00267201],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8591648,"threshold_uncertainty_score":0.7448163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2202473128127325,"score_gpt":0.5037553939418976,"score_spread":0.2835080811291651,"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."}}