{"id":"W2976812174","doi":"10.1145/3349266.3351369","title":"How Selective True-False Questions Reward Student Recognition","year":2019,"lang":"en","type":"article","venue":"","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Ignorance; Set (abstract data type); Class (philosophy); Psychology; Mathematics education; Selection (genetic algorithm); Correlation; Computer science; Test (biology); Artificial intelligence; Social psychology; Cognitive psychology; Mathematics; Epistemology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02062713,0.0006270751,0.0008305451,0.00106396,0.0007456949,0.003043601,0.001077032,0.001879514,0.006252013],"category_scores_gemma":[0.2020783,0.0003612171,0.0006295375,0.0007566359,0.001389329,0.003992191,0.002213395,0.00220176,0.001742523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00121605,"about_ca_system_score_gemma":0.00125938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001402585,"about_ca_topic_score_gemma":0.001639761,"domain_scores_codex":[0.9820595,0.009544584,0.001056757,0.002164177,0.003513224,0.001661771],"domain_scores_gemma":[0.6125084,0.3064854,0.0355839,0.02390033,0.01229245,0.00922951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.005852993,0.002032842,0.6928547,0.0003199986,0.0004214566,0.000251527,0.001769959,0.02227263,0.01477807,0.01046844,0.005050963,0.2439265],"study_design_scores_gemma":[0.0003582055,0.007307902,0.7684006,0.0001049209,0.0004563827,0.0008619298,0.00192522,0.1260706,0.0491432,0.03799782,0.00713616,0.0002369548],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9827752,0.0002535107,0.009509244,0.001347701,0.00005262402,0.00007421438,0.0001856936,0.0002968338,0.005505214],"genre_scores_gemma":[0.9963152,0.00003837556,0.002415252,0.0001092654,0.00002279575,0.00002786303,0.0001113608,0.00003775754,0.000922169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02062713,"threshold_uncertainty_score":0.1090879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02551812639683474,"score_gpt":0.3180622042319841,"score_spread":0.2925440778351493,"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."}}