{"id":"W2969964033","doi":"10.1111/jedm.12237","title":"Students’ Interpretation of Formative Assessment Feedback: Three Claims for Why We Know So Little About Something So Important","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Formative assessment; Psychology; Interpretation (philosophy); Cognition; Process (computing); Mathematics education; Cognitive psychology; Computer science","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.006115943,0.000168122,0.0003868715,0.0002487875,0.000355028,0.0002466688,0.0005827642,0.00008322528,0.0004700358],"category_scores_gemma":[0.0003544473,0.0001449626,0.0002924267,0.000239251,0.0001271632,0.0007422632,0.00005117879,0.000251736,0.00001246446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001070672,"about_ca_system_score_gemma":0.002848503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001087722,"about_ca_topic_score_gemma":0.0004748238,"domain_scores_codex":[0.995474,0.0001820447,0.001095565,0.000172083,0.002752556,0.0003237982],"domain_scores_gemma":[0.9954891,0.0004965866,0.001549905,0.0001456254,0.002182166,0.0001365984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003848315,0.002420381,0.8234078,0.0002676347,0.001319487,4.463347e-7,0.08745815,0.0001834305,0.003449654,0.05331847,0.01073874,0.01705095],"study_design_scores_gemma":[0.003961822,0.001385762,0.7998704,0.002154008,0.0004413656,0.000004275848,0.06936435,0.0004430992,0.0004683149,0.05751652,0.06378975,0.0006003206],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9360783,0.006732543,0.01412554,0.02709391,0.008364882,0.002444989,0.00002459211,0.00001584727,0.005119411],"genre_scores_gemma":[0.9927164,0.0007210757,0.005298373,0.0002120163,0.0006573194,0.0000393593,0.000006514173,0.00001551615,0.0003334492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05663809,"threshold_uncertainty_score":0.5911402,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04422115994093499,"score_gpt":0.3915110005329427,"score_spread":0.3472898405920077,"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."}}