{"id":"W4413389950","doi":"10.18260/1-2--56216","title":"Democratizing the Analysis of Unprompted Student Questions Using Open-Source Large Language Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Open source; World Wide Web; Natural language processing; Programming language; Software","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":[0.00251592,0.00077109,0.0005167873,0.00112092,0.0004493465,0.002579645,0.0014771,0.001227889,0.003567628],"category_scores_gemma":[0.02026722,0.0003124469,0.000911682,0.0005453159,0.0006391482,0.003158492,0.002678037,0.00197289,0.002153403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007310281,"about_ca_system_score_gemma":0.001331834,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002005312,"about_ca_topic_score_gemma":0.004029199,"domain_scores_codex":[0.9967019,0.001788706,0.0001430656,0.0004952648,0.0007219608,0.0001491793],"domain_scores_gemma":[0.9863908,0.009506875,0.0004575569,0.001646905,0.001741306,0.0002564531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001142387,0.001098956,0.01735317,0.000528703,0.0002449649,0.0009013701,0.003905016,0.1466552,0.08341727,0.02052142,0.0151117,0.7091199],"study_design_scores_gemma":[0.00002444503,0.00008685794,0.001638563,0.00001456089,0.0000222089,0.00008688065,0.0004364411,0.9567543,0.01683378,0.01891036,0.005168781,0.00002283304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1645087,0.0002069286,0.8173192,0.0009007574,0.000105322,0.0001777871,0.0007941019,0.01322293,0.002764338],"genre_scores_gemma":[0.7947926,0.00009398584,0.1970724,0.0002011108,0.00006906495,0.0001464491,0.002405102,0.001399175,0.003820066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003567628,"threshold_uncertainty_score":0.01330566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03239173291147063,"score_gpt":0.3406709322924878,"score_spread":0.3082791993810172,"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."}}