{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0141557,0.0006292165,0.0007881322,0.001039521,0.0002742441,0.0008055811,0.0007895752,0.0006668437,0.00294013],"category_scores_gemma":[0.1280327,0.0002482661,0.000472292,0.0005650567,0.0004671087,0.0008413013,0.0006222237,0.0008706719,0.0005867799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003478404,"about_ca_system_score_gemma":0.0003265973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000309366,"about_ca_topic_score_gemma":0.0005994645,"domain_scores_codex":[0.9871423,0.006973521,0.00140722,0.0008294986,0.003354869,0.0002927018],"domain_scores_gemma":[0.8722,0.09255017,0.01516956,0.007162328,0.0105122,0.002405738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01787244,0.005847201,0.3760779,0.0007765743,0.0004389978,0.000182703,0.002447721,0.002043404,0.03250176,0.001106317,0.002376833,0.5583282],"study_design_scores_gemma":[0.001209363,0.03661001,0.9208923,0.0002339528,0.0003910113,0.0006499619,0.0009704332,0.01226707,0.01795373,0.002404943,0.006187886,0.0002292047],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9814317,0.0003590477,0.01238205,0.0002269353,0.0002148355,0.0009707708,0.0001307669,0.0001310273,0.004152927],"genre_scores_gemma":[0.9792644,0.0001131404,0.01715364,0.00008158083,0.0000491687,0.0009108941,0.0001297963,0.00003578488,0.002261698],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0141557,"threshold_uncertainty_score":0.07486337,"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."}}