{"id":"W2043035035","doi":"10.3200/jexe.77.4.311-338","title":"Grading Scheme, Test Difficulty, and the Immediate Feedback Assessment Technique","year":2009,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Grading (engineering); Scheme (mathematics); Multiple choice; Test (biology); Classification scheme; Mathematics education; Psychology; Machine learning; Computer science; Significant difference; Mathematics; Statistics; Engineering","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":[0.001556055,0.00009211191,0.000134782,0.00005019953,0.0005648315,0.0001291549,0.00032022,0.00003726952,0.00005777784],"category_scores_gemma":[0.00009085482,0.00004988147,0.00006116223,0.0001720111,0.0002845362,0.0002760932,0.00002999275,0.000196838,0.000002893159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000181325,"about_ca_system_score_gemma":0.0002429966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001063044,"about_ca_topic_score_gemma":0.000004934454,"domain_scores_codex":[0.998884,0.0002196904,0.00026454,0.00006656718,0.0004128201,0.0001524031],"domain_scores_gemma":[0.999148,0.0002686538,0.0003162761,0.00009860756,0.00009647806,0.00007205392],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"qualitative","study_design_scores_codex":[0.000293551,0.002368676,0.01589164,0.000006346241,0.00009150386,0.000001654085,0.1354458,0.000002060193,0.7497276,0.06706474,0.01870096,0.01040548],"study_design_scores_gemma":[0.005598745,0.001231506,0.3095335,0.000318343,0.0002570171,0.0001390519,0.5796353,0.00007311132,0.07442816,0.01421256,0.01390829,0.0006644456],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.946436,0.002724805,0.00009852963,0.01908639,0.0008155393,0.000664401,5.126671e-7,0.00001657283,0.03015728],"genre_scores_gemma":[0.9969073,0.0006223869,0.001133625,0.0004100755,0.0005295275,0.00001245677,8.62586e-7,0.000004969049,0.0003787901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6752995,"threshold_uncertainty_score":0.4344284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01557128346648528,"score_gpt":0.3774555524268169,"score_spread":0.3618842689603316,"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."}}