{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UNSFLXEGZPUVHACJKNT2XFIC7J","short_pith_number":"pith:UNSFLXEG","schema_version":"1.0","canonical_sha256":"a36455dc86cbe95380495367ab9502fa775652bf3c7e1c33523c8c64a84f10c1","source":{"kind":"arxiv","id":"2510.25110","version":6},"attestation_state":"computed","paper":{"title":"DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binwei Yao, Chengtao Dai, Dhavan Shah, Junjie Hu, Michael Henry Tessler, Robert Hawkins, Ruixuan Tu, Sijia Yang, Smit Vasani, Timothy T. Rogers, You Li, Yun-Shiuan Chuang","submitted_at":"2025-10-29T02:21:10Z","abstract_excerpt":"Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a large-scale benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.25110","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-29T02:21:10Z","cross_cats_sorted":[],"title_canon_sha256":"2639323b53767b9888aa3f599a93329862d08c7cac8c82a68d39cd3ab2813953","abstract_canon_sha256":"c1de3f351e9e0e3ba5ccafccafda2eb3e51c4ed6221db7fcebf92dca45c3dc7e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:24.750829Z","signature_b64":"PMLvhVmR3psxKPE5GXKqhz67EpQMlZNI8oO8L6OXXwVLzEPtHEI5LWPaPWxkVo7iu1qcs/5MMqcu3PuhBknyDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a36455dc86cbe95380495367ab9502fa775652bf3c7e1c33523c8c64a84f10c1","last_reissued_at":"2026-06-01T01:02:24.750050Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:24.750050Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DEBATE: A Large-Scale Benchmark for Evaluating Opinion Dynamics in Role-Playing LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binwei Yao, Chengtao Dai, Dhavan Shah, Junjie Hu, Michael Henry Tessler, Robert Hawkins, Ruixuan Tu, Sijia Yang, Smit Vasani, Timothy T. Rogers, You Li, Yun-Shiuan Chuang","submitted_at":"2025-10-29T02:21:10Z","abstract_excerpt":"Accurately modeling opinion change through social interactions is crucial for understanding and mitigating polarization, misinformation, and societal conflict. Recent work simulates opinion dynamics with role-playing LLM agents (RPLAs), but multi-agent simulations often display unnatural group behavior, such as premature convergence, and lack empirical benchmarks for assessing alignment with real human group interactions. We introduce DEBATE, a large-scale benchmark for evaluating the authenticity of opinion dynamics in multi-agent RPLA simulations. DEBATE contains multi-round public messages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.25110","kind":"arxiv","version":6},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.25110/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.25110","created_at":"2026-06-01T01:02:24.750157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.25110v6","created_at":"2026-06-01T01:02:24.750157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.25110","created_at":"2026-06-01T01:02:24.750157+00:00"},{"alias_kind":"pith_short_12","alias_value":"UNSFLXEGZPUV","created_at":"2026-06-01T01:02:24.750157+00:00"},{"alias_kind":"pith_short_16","alias_value":"UNSFLXEGZPUVHACJ","created_at":"2026-06-01T01:02:24.750157+00:00"},{"alias_kind":"pith_short_8","alias_value":"UNSFLXEG","created_at":"2026-06-01T01:02:24.750157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.17079","citing_title":"Can LLMs Think Like Consumers? Benchmarking Crowd-Level Reaction Reconstruction with ConsumerSimBench","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19141","citing_title":"GRASP: Deterministic argument ranking in interaction graphs","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15343","citing_title":"Belief Engine: Configurable and Inspectable Stance Dynamics in Multi-Agent LLM Deliberation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12718","citing_title":"CHAL: Council of Hierarchical Agentic Language","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J","json":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J.json","graph_json":"https://pith.science/api/pith-number/UNSFLXEGZPUVHACJKNT2XFIC7J/graph.json","events_json":"https://pith.science/api/pith-number/UNSFLXEGZPUVHACJKNT2XFIC7J/events.json","paper":"https://pith.science/paper/UNSFLXEG"},"agent_actions":{"view_html":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J","download_json":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J.json","view_paper":"https://pith.science/paper/UNSFLXEG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.25110&json=true","fetch_graph":"https://pith.science/api/pith-number/UNSFLXEGZPUVHACJKNT2XFIC7J/graph.json","fetch_events":"https://pith.science/api/pith-number/UNSFLXEGZPUVHACJKNT2XFIC7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J/action/storage_attestation","attest_author":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J/action/author_attestation","sign_citation":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J/action/citation_signature","submit_replication":"https://pith.science/pith/UNSFLXEGZPUVHACJKNT2XFIC7J/action/replication_record"}},"created_at":"2026-06-01T01:02:24.750157+00:00","updated_at":"2026-06-01T01:02:24.750157+00:00"}