{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ANJLWVU3ITETA4TQ4N7WZKEOVE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"58df7925302f82a5ab50302d214440720abe36769116bac629bedc4345b1b4e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T05:54:41Z","title_canon_sha256":"9187be730c7194e7873f35430a2b7f3d0141912e7c64defe9e25fd0def5560d4"},"schema_version":"1.0","source":{"id":"2311.17371","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17371","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17371v3","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17371","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_12","alias_value":"ANJLWVU3ITET","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_16","alias_value":"ANJLWVU3ITETA4TQ","created_at":"2026-07-05T08:45:23Z"},{"alias_kind":"pith_short_8","alias_value":"ANJLWVU3","created_at":"2026-07-05T08:45:23Z"}],"graph_snapshots":[{"event_id":"sha256:21f0793a2d440fa64f0aa1777a1311ef73649082e97746bc7c6918917e54c3d0","target":"graph","created_at":"2026-07-05T08:45:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2311.17371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) underscore their potential for responding to inquiries in various domains. However, ensuring that generative agents provide accurate and reliable answers remains an ongoing challenge. In this context, multi-agent debate (MAD) has emerged as a promising strategy for enhancing the truthfulness of LLMs. We benchmark a range of debating and prompting strategies to explore the trade-offs between cost, time, and accuracy. Importantly, we find that multi-agent debating systems, in their current form, do not reliably outperform other proposed prompti","authors_text":"Andries Smit, Arnu Pretorius, Nathan Grinsztajn, Paul Duckworth, Thomas D. Barrett","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T05:54:41Z","title":"Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17371","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd355081016db90442fa5d0615e6efd95fb7d9db6c9aaf5449a8ea779f2cd65b","target":"record","created_at":"2026-07-05T08:45:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"58df7925302f82a5ab50302d214440720abe36769116bac629bedc4345b1b4e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-29T05:54:41Z","title_canon_sha256":"9187be730c7194e7873f35430a2b7f3d0141912e7c64defe9e25fd0def5560d4"},"schema_version":"1.0","source":{"id":"2311.17371","kind":"arxiv","version":3}},"canonical_sha256":"0352bb569b44c9307270e37f6ca88ea929f0a623110384bcafc035bec5fc815f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0352bb569b44c9307270e37f6ca88ea929f0a623110384bcafc035bec5fc815f","first_computed_at":"2026-07-05T08:45:23.611046Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:45:23.611046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5l4g5b3tNCfFfa9wvv0X2pwBIQ1xsn9D5Nnz/8kN0J9lA4eZBKzc1FDnETIv0qHhHHh9QLO0X8Fn1+vWl1/TDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:45:23.611547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17371","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd355081016db90442fa5d0615e6efd95fb7d9db6c9aaf5449a8ea779f2cd65b","sha256:21f0793a2d440fa64f0aa1777a1311ef73649082e97746bc7c6918917e54c3d0"],"state_sha256":"b5717ff1ecdbe8922e523e0573f860f91ee0531e31772f71cee0e5a9334125ba"}