{"id":"W4385613436","doi":"10.20944/preprints202308.0366.v1","title":"Learning Analytics in the Era of Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Learning analytics; Interpretability; Personalization; Computer science; Usability; Analytics; Process (computing); Data science; Empowerment; Knowledge management; Artificial intelligence; World Wide Web; Human–computer interaction; Political 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":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00262848,0.0002621229,0.0004464836,0.0002383597,0.000083297,0.00006199358,0.002693725,0.0002372498,0.00002266662],"category_scores_gemma":[0.0004887051,0.0002195669,0.0002384866,0.0006623325,0.00004824268,0.0001309437,0.003584812,0.00282156,0.0002902926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005141511,"about_ca_system_score_gemma":0.0001804839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003682107,"about_ca_topic_score_gemma":0.00006902852,"domain_scores_codex":[0.9972355,0.0004255866,0.0005650275,0.000773647,0.0005778639,0.000422378],"domain_scores_gemma":[0.9973776,0.0002759313,0.0003830171,0.001793591,0.0001107039,0.00005912972],"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":[0.000005557516,0.0002442367,0.2881682,0.0002380798,0.0001014849,0.0001160843,0.02557387,0.6694448,0.0002265078,0.01459211,0.00004747608,0.00124159],"study_design_scores_gemma":[0.0002338856,0.00002109061,0.07333054,0.0003053833,0.00003284892,0.000003934561,0.001200952,0.9068729,0.0003809585,0.01706155,0.0002525936,0.0003033448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9606894,0.0001219787,0.03129696,0.00449216,0.0002925871,0.0002572322,0.00001190014,0.0003401374,0.002497623],"genre_scores_gemma":[0.996317,0.0001487701,0.001662393,0.0001341585,0.0001071157,0.00001816659,0.00002712958,0.00002815708,0.001557076],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2374281,"threshold_uncertainty_score":0.999479,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1090935120277306,"score_gpt":0.3731757682263504,"score_spread":0.2640822561986197,"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."}}