{"id":"W4404012066","doi":"10.1080/02602938.2024.2419604","title":"The paradox of inclusive assessment","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Higher Education Learning Practices","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Psychology; Pedagogy; Higher education; Mathematics education; Evaluation methods; Political science","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.007689833,0.0001220559,0.0001303496,0.0001904493,0.0005600943,0.0003870326,0.0003253153,0.00009628107,0.002860723],"category_scores_gemma":[0.0003078146,0.0001039543,0.00005689187,0.001102339,0.0001872805,0.000808847,0.00003996648,0.0003232301,0.00006946822],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001607902,"about_ca_system_score_gemma":0.009480536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001233681,"about_ca_topic_score_gemma":0.0003632747,"domain_scores_codex":[0.9954526,0.001981338,0.000518235,0.0003236255,0.001471936,0.0002522045],"domain_scores_gemma":[0.9968857,0.001829531,0.0002953807,0.0003164332,0.0006019811,0.00007097411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006071895,0.000427131,0.06372272,0.00004345373,0.00005450255,3.158986e-7,0.01909046,0.0004294134,0.000154137,0.8260987,0.01174059,0.07823253],"study_design_scores_gemma":[0.0001096119,0.00002626649,0.3964165,0.00008942908,0.00006165051,2.638427e-7,0.007643959,0.0006919176,0.000010284,0.01604071,0.5787998,0.0001095541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3258141,0.004708226,0.0002595627,0.2087306,0.02131283,0.002492737,0.000004018771,0.0001883808,0.4364895],"genre_scores_gemma":[0.9847703,0.000307661,0.001418607,0.0001577486,0.0006265626,0.0007412565,0.00003735895,0.00001717932,0.01192332],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8100579,"threshold_uncertainty_score":0.9980508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07941909821958311,"score_gpt":0.5416770865350428,"score_spread":0.4622579883154597,"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."}}