{"id":"W1487234737","doi":"10.1023/a:1015023512975","title":"Explanation and Argumentation Capabilities:Towards the Creation of More Persuasive Agents","year":2002,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":false,"ca_institutions":"Department of National Defence; Université Laval","funders":"","keywords":"Argumentative; Computer science; Argumentation theory; Argument (complex analysis); Credibility; Field (mathematics); Domain knowledge; Data science; Set (abstract data type); Management science; Knowledge management; Artificial intelligence; Epistemology","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":[0.009385414,0.0008705196,0.001066133,0.002554574,0.0005387497,0.005857625,0.002793686,0.005246242,0.006679455],"category_scores_gemma":[0.02469731,0.0004771918,0.0008719338,0.001668187,0.003868669,0.01348436,0.002989595,0.002805946,0.001762066],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008584486,"about_ca_system_score_gemma":0.001488236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004762085,"about_ca_topic_score_gemma":0.0003759086,"domain_scores_codex":[0.9944046,0.003226379,0.0003263376,0.0004792456,0.001408611,0.0001548581],"domain_scores_gemma":[0.9636522,0.03063169,0.001487849,0.001794592,0.001910654,0.000522961],"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":[0.0001159165,0.000219906,0.0009796264,0.005036015,0.0001479487,0.0002361272,0.002565901,0.003748141,0.003275191,0.4431724,0.005750322,0.5347524],"study_design_scores_gemma":[0.000189309,0.0002317098,0.001230856,0.00205666,0.0001864511,0.001156659,0.0009392768,0.02006656,0.003829348,0.7182906,0.251725,0.00009757083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02371243,0.3407732,0.5112689,0.03475128,0.001480008,0.0003212616,0.00009851899,0.0007700608,0.0868245],"genre_scores_gemma":[0.3835415,0.1388171,0.4517654,0.003804585,0.002976405,0.0005387393,0.0003268663,0.0002559509,0.01797344],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009385414,"threshold_uncertainty_score":0.04963547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1331654687198182,"score_gpt":0.3481229975697713,"score_spread":0.2149575288499532,"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."}}