{"id":"W2164521028","doi":"10.5539/hes.v2n4p68","title":"Using Potential Performance Theory to Assess How to Increase Student Consistency in Taking Exams","year":2012,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Consistency (knowledge bases); Test (biology); Mathematics education; Psychology; Computer science; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004215713,0.0001181875,0.0001736455,0.0002099622,0.0006912578,0.000133598,0.000198878,0.00004081143,0.0001764442],"category_scores_gemma":[0.0009735703,0.0001149662,0.00002791389,0.0004160416,0.0000889098,0.0009224124,0.0001275446,0.0001189739,0.0000780362],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004729224,"about_ca_system_score_gemma":0.0003004748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008257843,"about_ca_topic_score_gemma":0.0001980656,"domain_scores_codex":[0.9977186,0.0009656068,0.0002127358,0.0002092162,0.0005623476,0.0003314857],"domain_scores_gemma":[0.9987107,0.0004228459,0.0002106735,0.0001740188,0.0003203196,0.0001614636],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004557952,0.0008120227,0.7613125,0.00004966752,0.0001197751,7.687741e-7,0.1532782,0.0002962795,0.0005825249,0.06549803,0.003889715,0.01411497],"study_design_scores_gemma":[0.000114153,0.00002253839,0.8213452,0.0000985104,0.00005828835,7.988027e-7,0.1145731,0.000002033569,0.00003670465,0.0001557964,0.06339518,0.0001977657],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9775819,0.001515306,0.0001079756,0.008705204,0.003678672,0.0003750976,6.606779e-7,0.00004424309,0.00799098],"genre_scores_gemma":[0.9880142,0.00006428214,0.004517102,0.001223777,0.0009081326,0.000112983,9.569301e-7,0.00001142438,0.005147198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06534223,"threshold_uncertainty_score":0.5316666,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4184138131814865,"score_gpt":0.5502017197426945,"score_spread":0.131787906561208,"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."}}