{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000756397,0.00009207622,0.0002284422,0.0003752764,0.0003057378,0.0002816468,0.001136535,0.00002912107,0.00001413833],"category_scores_gemma":[0.00002771691,0.00006193669,0.0001011183,0.002278642,0.00001512427,0.0002917996,0.0007437923,0.0001117544,0.000002339258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003999949,"about_ca_system_score_gemma":0.00004704846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0015846,"about_ca_topic_score_gemma":0.0001679741,"domain_scores_codex":[0.9989243,0.0001686455,0.0002846279,0.0002440681,0.0001953943,0.0001829211],"domain_scores_gemma":[0.9991087,0.0001279719,0.0001157625,0.0005025645,0.0001217551,0.0000232593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[9.817621e-7,0.00005459258,0.00205069,0.000006025736,0.0004719102,0.000002100983,0.003451564,0.2475307,0.001273053,0.7439471,0.00004605959,0.001165222],"study_design_scores_gemma":[0.00008688829,0.000008035648,0.002385641,0.00006873489,0.0001461259,6.775326e-7,0.002165149,0.992496,0.0007251122,0.0003091294,0.001525756,0.00008275079],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07761748,0.0001786336,0.915527,0.0001616354,0.0001065632,0.0001755874,0.000001155376,0.00006222166,0.006169762],"genre_scores_gemma":[0.9759579,0.00000386799,0.01258451,0.0001571495,0.00001372035,0.000006837937,0.00000107394,0.000004097156,0.01127083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9029425,"threshold_uncertainty_score":0.2715926,"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."}}