{"id":"W1507874144","doi":"10.1007/3-540-70657-7_4","title":"Bringing Coherence to Agent Conversations","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Multi-Agent Systems and Negotiation","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Conversation; Computer science; Coherence (philosophical gambling strategy); Cornerstone; Negotiation; Action (physics); Software agent; Identity (music); Human–computer interaction; Artificial intelligence; Cognitive science; Communication; Sociology; Psychology","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"],"consensus_categories":[],"category_scores_codex":[0.0005925337,0.0004121971,0.000398616,0.0008355781,0.000287464,0.0005455064,0.002370595,0.000195255,0.0001021986],"category_scores_gemma":[0.0000751408,0.0004064089,0.0001073337,0.0006365597,0.0001625651,0.0005298182,0.0008878112,0.0004172162,0.0004311273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004225593,"about_ca_system_score_gemma":0.0001893664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006824491,"about_ca_topic_score_gemma":0.00006217344,"domain_scores_codex":[0.9965287,0.00003036469,0.0005178852,0.001373477,0.0009735408,0.0005760102],"domain_scores_gemma":[0.9978014,0.0002397145,0.0002580399,0.001231777,0.0002125909,0.0002565395],"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":[0.000003337802,0.00006529965,0.0004220232,0.0001019403,0.00002875541,0.000148248,0.006790695,0.1023426,0.0008205621,0.03946411,0.0006085361,0.8492039],"study_design_scores_gemma":[0.0002800318,0.0001288146,0.0009649546,0.0006695376,0.000008034589,0.00005193186,2.421571e-7,0.9774702,0.001320752,0.00931361,0.008886288,0.00090566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001252147,0.0001385425,0.9902548,0.0009000122,0.002452566,0.0005956345,0.000004110355,0.0001811076,0.005348037],"genre_scores_gemma":[0.58305,0.00003459028,0.4090045,0.003102372,0.0007599121,0.00003238614,0.000006020622,0.0000515948,0.003958588],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8751276,"threshold_uncertainty_score":0.9998388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03232246663242414,"score_gpt":0.2480692774491834,"score_spread":0.2157468108167592,"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."}}