{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001158872,0.0001650356,0.0001661493,0.0001374282,0.000165465,0.0002460766,0.00178163,0.00004685417,0.000008685558],"category_scores_gemma":[0.00005151491,0.0001277997,0.00001906192,0.0007377678,0.00001517844,0.001898885,0.0004461366,0.0003927723,0.000009360037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009698761,"about_ca_system_score_gemma":0.0007924633,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255018,"about_ca_topic_score_gemma":0.0002109537,"domain_scores_codex":[0.9977825,0.0002679602,0.0003803789,0.0007231162,0.0005759831,0.0002700163],"domain_scores_gemma":[0.9981644,0.0001067963,0.0001229663,0.00127415,0.0002600917,0.00007155884],"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":[0.00002845836,0.0119956,0.3208501,0.0003288537,0.0002119502,0.000002241656,0.1481641,0.3835073,0.0001029253,0.0006849325,0.002966619,0.1311569],"study_design_scores_gemma":[0.0002283154,0.0002441025,0.04947307,0.0003608333,0.00004781389,3.133714e-7,0.01018419,0.9381561,0.00002029974,0.001068809,0.00008142804,0.0001347107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8527056,0.00006749991,0.14421,0.001468631,0.0005153617,0.0007110896,0.00006337158,0.00009212965,0.0001663468],"genre_scores_gemma":[0.9721726,0.00003178727,0.02697886,0.0001701772,0.0001480263,0.0001152834,0.0001679701,0.00001820146,0.0001970595],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5546488,"threshold_uncertainty_score":0.5211522,"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."}}