{"id":"W7077918497","doi":"10.48448/1h16-v556","title":"Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation","year":2025,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Geochemistry and Geologic Mapping","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Ambiguity; Fluency; Dimension (graph theory); Diversity (politics); Taxonomy (biology)","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":[0.009368308,0.001482159,0.001042796,0.002228555,0.001169524,0.003953114,0.001389641,0.002261735,0.003175124],"category_scores_gemma":[0.05025566,0.0003066378,0.0006050568,0.001013414,0.0009046906,0.005264157,0.002617924,0.002166474,0.001185175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001506895,"about_ca_system_score_gemma":0.00134601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001697827,"about_ca_topic_score_gemma":0.002991303,"domain_scores_codex":[0.9910263,0.005612584,0.0006777519,0.001202474,0.001228525,0.0002522332],"domain_scores_gemma":[0.9729812,0.0187252,0.002541254,0.002168496,0.002804228,0.0007795671],"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":[0.004208888,0.0008946215,0.02170889,0.002481676,0.0004613055,0.0007207762,0.006123096,0.04510251,0.0305357,0.0309223,0.02888171,0.8279586],"study_design_scores_gemma":[0.0004869766,0.0008668326,0.006789356,0.0004564285,0.0003716638,0.0003681706,0.002937737,0.8574723,0.03065218,0.06874889,0.0306859,0.0001635693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2638678,0.006434277,0.6893706,0.005508733,0.0006442891,0.001307738,0.002503541,0.0140243,0.01633865],"genre_scores_gemma":[0.7509415,0.0003123946,0.2419867,0.0005764337,0.0001852457,0.0003537493,0.002122345,0.0003004272,0.003221216],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009368308,"threshold_uncertainty_score":0.04954499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05066007469008505,"score_gpt":0.3303294747411062,"score_spread":0.2796694000510211,"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."}}