{"id":"W4412889266","doi":"10.18653/v1/2025.bea-1.63","title":"Intent Matters: Enhancing AI Tutoring with Fine-Grained Pedagogical Intent Annotation","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":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Annotation; Computer science; Multimedia; World Wide Web; Artificial intelligence","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":[0.0003408806,0.0001812016,0.0001994463,0.0001890747,0.0001595725,0.000322215,0.0004218293,0.00004617816,0.00002553693],"category_scores_gemma":[0.00006253126,0.000130973,0.00006852935,0.0003859092,0.00002265308,0.0004121334,0.0002053179,0.0002452137,0.0000653064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001392441,"about_ca_system_score_gemma":0.0000651943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001312734,"about_ca_topic_score_gemma":0.00003357751,"domain_scores_codex":[0.9985652,0.00006366834,0.0003294773,0.0004434685,0.0002720238,0.0003261584],"domain_scores_gemma":[0.9991892,0.00009498796,0.00008390628,0.0003241679,0.0002462192,0.00006153271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002848375,0.00007016353,0.003842679,0.00009165068,0.00007777676,0.00004449327,0.003410311,0.001804187,0.009937117,0.9644081,0.00116034,0.01512472],"study_design_scores_gemma":[0.002603587,0.001618597,0.01361813,0.005566642,0.00008259394,0.0001414526,0.01363198,0.1748935,0.1590415,0.003295242,0.6230775,0.002429272],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01534635,0.00003731404,0.9742407,0.004723646,0.0006963566,0.0001761595,1.839235e-7,0.0002912793,0.004488042],"genre_scores_gemma":[0.9207451,0.000001566316,0.01736425,0.002083625,0.0001223393,0.00003335885,0.000001786169,0.00001012708,0.05963787],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9611129,"threshold_uncertainty_score":0.5340924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03253506186077187,"score_gpt":0.3006040241663466,"score_spread":0.2680689623055747,"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."}}