{"id":"W4392361000","doi":"10.1186/s40536-024-00194-y","title":"An engagement-aware predictive model to evaluate problem-solving performance from the study of adult skills' (PIAAC 2012) process data","year":2024,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Scale (ratio); Process (computing); Learning analytics; Computer science; Test (biology); Analytics; Psychology; Artificial intelligence; Data science","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":[0.002938673,0.0006598384,0.0004864766,0.001320849,0.000273508,0.001104638,0.0007769424,0.0006946602,0.001225387],"category_scores_gemma":[0.0127836,0.0002710497,0.0005255385,0.0007698631,0.0003171875,0.000917747,0.001003882,0.001221411,0.0002710675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000898128,"about_ca_system_score_gemma":0.0007671429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009977049,"about_ca_topic_score_gemma":0.0107866,"domain_scores_codex":[0.9991871,0.0003724235,0.00004783318,0.0002146734,0.0001180486,0.00005986234],"domain_scores_gemma":[0.9943299,0.004075677,0.0004890602,0.000367885,0.0005362416,0.0002012273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005379864,0.001231124,0.1983843,0.0001145433,0.0002602345,0.000171971,0.0005695572,0.6491005,0.002676909,0.002800175,0.001581001,0.1425717],"study_design_scores_gemma":[0.000004397978,0.00005032614,0.009003429,0.000007812045,0.000008432805,0.000008440754,0.00002477152,0.9893956,0.0003175703,0.001063332,0.000109538,0.000006305564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7658622,0.000162197,0.2300134,0.000456516,0.00002570327,0.0001992301,0.001048147,0.0006433053,0.001589254],"genre_scores_gemma":[0.9794862,0.00003468672,0.01929,0.00002806917,0.000006543674,0.0001043748,0.0005732208,0.00000945408,0.0004675661],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009977049,"threshold_uncertainty_score":0.01983792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02761815327562231,"score_gpt":0.3969492216172661,"score_spread":0.3693310683416438,"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."}}