{"id":"W4405820110","doi":"10.1007/s10758-024-09810-w","title":"Disentangling the Relationship Between Ability and Test-Taking Effort: To What Extent the Ability Levels Can Be Predicted from Response Behavior?","year":2024,"lang":"en","type":"article","venue":"Technology Knowledge and Learning","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta; Concordia University of Edmonton","funders":"","keywords":"Test (biology); Psychology; Mathematics education; Applied psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001963808,0.00018959,0.0002096907,0.0002040767,0.0009593549,0.0004764537,0.000543473,0.0001941525,0.000004809426],"category_scores_gemma":[0.004859104,0.000123474,0.00005308922,0.0009557498,0.0003443868,0.0002393112,0.0006153935,0.001494494,0.000007154729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000715842,"about_ca_system_score_gemma":0.0000969125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002874304,"about_ca_topic_score_gemma":0.00005791891,"domain_scores_codex":[0.9982247,0.000395103,0.0003015698,0.000618313,0.0001518486,0.0003085081],"domain_scores_gemma":[0.9922892,0.006851388,0.00008873329,0.0006097209,0.00007454252,0.00008638109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000516925,0.00002087608,0.8863698,0.00001526949,0.00001624919,0.000008980258,0.006041811,0.0000269487,0.0002137337,0.001335081,0.00001269953,0.1059334],"study_design_scores_gemma":[0.0001196104,0.0001350349,0.9653514,0.0002221648,0.00008265868,0.00001435078,0.001956252,0.02521982,0.00009484938,0.004041621,0.002592312,0.0001699035],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.962123,0.002831436,0.002527762,0.03140743,0.0001490082,0.0002527276,0.00001175602,0.0006805036,0.0000164032],"genre_scores_gemma":[0.9985251,0.00002118959,0.001063018,0.00005938787,0.0001100712,0.00003705359,0.000005669978,0.00001574615,0.0001627095],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1057635,"threshold_uncertainty_score":0.737868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04228390643791003,"score_gpt":0.330098788000441,"score_spread":0.287814881562531,"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."}}