{"id":"W4416677822","doi":"10.1109/iccams65118.2025.11234017","title":"Mind Duel: Offline AI for Structured Debates","year":2025,"lang":"","type":"article","venue":"","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Chatbot; Dialog box; Argumentation theory; Language understanding; Creativity; Tone (literature); Inference","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":[0.002489039,0.0007611953,0.0005771847,0.0009204649,0.001412016,0.00373709,0.003158397,0.001608266,0.03538174],"category_scores_gemma":[0.009175685,0.0004754202,0.0007202506,0.0004184886,0.001873284,0.006096588,0.006389223,0.002560548,0.00825775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009767537,"about_ca_system_score_gemma":0.001271367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009325115,"about_ca_topic_score_gemma":0.001376824,"domain_scores_codex":[0.998166,0.0008915313,0.00007337223,0.0003599509,0.0003664111,0.0001426857],"domain_scores_gemma":[0.9969966,0.001788301,0.00009172262,0.000563343,0.000215591,0.0003443538],"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":[0.001543514,0.0006020821,0.001718302,0.001247474,0.00009710696,0.000943701,0.009326132,0.01571729,0.03979609,0.446838,0.0660817,0.4160886],"study_design_scores_gemma":[0.0002845135,0.0002879291,0.0006630878,0.0002315752,0.00004732532,0.0004743579,0.0009877248,0.245706,0.02348424,0.3081628,0.4195407,0.0001296265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01070863,0.0004302576,0.912316,0.0008378114,0.0003286588,0.000342965,0.0005137815,0.03809095,0.0364309],"genre_scores_gemma":[0.3068726,0.0003600817,0.6335663,0.0008218013,0.0002390716,0.000874569,0.002092947,0.005427757,0.04974494],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03538174,"threshold_uncertainty_score":0.1183637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01372518046008837,"score_gpt":0.326086729247081,"score_spread":0.3123615487869926,"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."}}