{"id":"W7130598143","doi":"10.1109/icetc66579.2025.11387706","title":"Building Trust in Educational AI: Designing Effective Human-AI Interfaces for Students and Instructors","year":2025,"lang":"","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; Kelowna General Hospital","funders":"","keywords":"Asynchronous communication; Workflow; Software deployment; Trustworthiness; Cognition; Cognitive load","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00120585,0.0003615126,0.0004578255,0.0006526231,0.0006158433,0.001140222,0.0008038172,0.0001465341,0.00002395627],"category_scores_gemma":[0.0002615746,0.0003619254,0.00009111213,0.00057749,0.0001028526,0.0007833297,0.0005890981,0.0004731142,0.000004873871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003945277,"about_ca_system_score_gemma":0.0002085113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000415491,"about_ca_topic_score_gemma":0.00004781396,"domain_scores_codex":[0.997258,0.0002719707,0.0006821469,0.0009282163,0.000326673,0.0005329926],"domain_scores_gemma":[0.998443,0.0007650691,0.0001901467,0.000252856,0.0002599832,0.00008896353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0000340463,0.0001458208,0.261168,0.0003066504,0.0001481614,0.000001955615,0.004146421,0.0009885761,0.005783152,0.693671,0.0001106504,0.0334956],"study_design_scores_gemma":[0.005999137,0.001862849,0.686336,0.01385203,0.0001606647,0.00002691501,0.005575371,0.09537483,0.1190494,0.0554272,0.01381354,0.002521954],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.50374,0.0003609187,0.492514,0.0003790553,0.00163835,0.0009359404,0.000001089213,0.00002668425,0.0004038704],"genre_scores_gemma":[0.9750583,0.000006981031,0.014289,0.0002790364,0.0001938755,0.0001669042,8.526408e-7,0.00001634359,0.009988693],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6382438,"threshold_uncertainty_score":0.9998967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02349902814559026,"score_gpt":0.3731841641288228,"score_spread":0.3496851359832325,"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."}}