{"id":"W4407384694","doi":"10.3102/01623737241311537","title":"Measuring Grading Standards at High Schools: A Methodological Contribution, an Example, and Some Policy Implications","year":2025,"lang":"en","type":"article","venue":"Educational Evaluation and Policy Analysis","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Wilfrid Laurier University","funders":"Canadian Institutes of Health Research; University of Alberta","keywords":"Grading (engineering); Academic standards; Mathematics education; Policy analysis; Higher education; Econometrics; Psychology; Political science; Economics; Economic growth; Public administration; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.1796068,0.001322268,0.0009950617,0.005620823,0.006129848,0.005798927,0.005487874,0.003682861,0.001369215],"category_scores_gemma":[0.3328149,0.0008652242,0.001020097,0.01695175,0.009230321,0.003834601,0.004735205,0.003123393,0.0003538526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01415679,"about_ca_system_score_gemma":0.02172728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.1647845,"about_ca_topic_score_gemma":0.210035,"domain_scores_codex":[0.6873401,0.2623847,0.01288765,0.008039678,0.02712839,0.002219548],"domain_scores_gemma":[0.5959744,0.2640416,0.0376239,0.03943378,0.06116933,0.001757047],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003167406,0.001717795,0.5035846,0.002421131,0.000688808,0.0008925075,0.02744992,0.007343292,0.002009349,0.2383397,0.02108605,0.1941501],"study_design_scores_gemma":[0.0006088793,0.001319707,0.432938,0.006716062,0.001288073,0.001764183,0.06831056,0.03182545,0.01047529,0.298472,0.1453036,0.0009781318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2619008,0.01260074,0.5255494,0.1308374,0.002842539,0.008584947,0.002845983,0.0002364733,0.05460172],"genre_scores_gemma":[0.6648045,0.00274859,0.310485,0.008142317,0.0008160557,0.007279728,0.0007280841,0.00009947094,0.00489619],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1796068,"threshold_uncertainty_score":0.9498628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2785140261361238,"score_gpt":0.5528497145082416,"score_spread":0.2743356883721178,"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."}}