{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005934486,0.001063741,0.001070681,0.001249953,0.000556175,0.002786793,0.001578013,0.002224681,0.005433449],"category_scores_gemma":[0.04796838,0.0006355276,0.001336471,0.001674823,0.001117996,0.003592023,0.001604064,0.002800077,0.001849449],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002964994,"about_ca_system_score_gemma":0.001091171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005725375,"about_ca_topic_score_gemma":0.007143009,"domain_scores_codex":[0.9966979,0.001455858,0.0002040906,0.0007593776,0.0004971694,0.0003856954],"domain_scores_gemma":[0.9090673,0.06971075,0.008350044,0.006590242,0.002053875,0.004227795],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002931508,0.0003607487,0.9881213,0.00003838034,0.0004071398,0.0000495663,0.0003231793,0.00050281,0.0007028502,0.0003541739,0.0001770368,0.008669591],"study_design_scores_gemma":[0.00001122519,0.0002289416,0.9931225,0.00002763925,0.0001789324,0.00006314723,0.0001929539,0.004108434,0.0004495088,0.001333216,0.0002637939,0.00001972611],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9913844,0.0004435108,0.003861225,0.0007893552,0.00004340634,0.00002120989,0.0005124059,0.00006112053,0.002883233],"genre_scores_gemma":[0.9979087,0.0001032549,0.0007296852,0.0001314921,0.00002526599,0.00001915347,0.0003939934,0.0000259095,0.0006626633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005934486,"threshold_uncertainty_score":0.03138494,"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."}}