{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AFXWN6VWI2RWLLJR2IQI3VY2RJ","short_pith_number":"pith:AFXWN6VW","schema_version":"1.0","canonical_sha256":"016f66fab646a365ad31d2208dd71a8a4c1d5c8318b8b80b7a28c27bc6560f80","source":{"kind":"arxiv","id":"2407.13943","version":1},"attestation_state":"computed","paper":{"title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feiyang Chen, Jane Friedhoff, Suma Bailis","submitted_at":"2024-07-18T23:41:05Z","abstract_excerpt":"This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's complex dynamics of deception, deduction, and persuasion. The framework introduces a dynamic turn-taking system based on bidding, mirroring real-world discussions where individuals strategically choose when to speak. We demonstrate the framework's utility through an arena-style tournament featuring Gemini and GPT models. Our results reveal distinct strengths "},"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":"2407.13943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-18T23:41:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"741c17bba9fd09235a558e89e0c7b20565dab764d422a7860f897bad07a1a318","abstract_canon_sha256":"b6a93bf8ec7f0038803d1656a0df955705c573079237303f3aa575138b39f710"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:56.011309Z","signature_b64":"Nwg5zVn1+5Aemsh74eTRufZ/oxyYPSd3OAi8Hi4EYekZZLMFTl3lkTB/IAzcMKQ5QobYKEwjOvXCYkIrMHAnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"016f66fab646a365ad31d2208dd71a8a4c1d5c8318b8b80b7a28c27bc6560f80","last_reissued_at":"2026-07-05T08:45:56.010770Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:56.010770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Werewolf Arena: A Case Study in LLM Evaluation via Social Deduction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Feiyang Chen, Jane Friedhoff, Suma Bailis","submitted_at":"2024-07-18T23:41:05Z","abstract_excerpt":"This paper introduces Werewolf Arena, a novel framework for evaluating large language models (LLMs) through the lens of the classic social deduction game, Werewolf. In Werewolf Arena, LLMs compete against each other, navigating the game's complex dynamics of deception, deduction, and persuasion. The framework introduces a dynamic turn-taking system based on bidding, mirroring real-world discussions where individuals strategically choose when to speak. We demonstrate the framework's utility through an arena-style tournament featuring Gemini and GPT models. Our results reveal distinct strengths "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13943","kind":"arxiv","version":1},"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/2407.13943/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":"2407.13943","created_at":"2026-07-05T08:45:56.010832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.13943v1","created_at":"2026-07-05T08:45:56.010832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13943","created_at":"2026-07-05T08:45:56.010832+00:00"},{"alias_kind":"pith_short_12","alias_value":"AFXWN6VWI2RW","created_at":"2026-07-05T08:45:56.010832+00:00"},{"alias_kind":"pith_short_16","alias_value":"AFXWN6VWI2RWLLJR","created_at":"2026-07-05T08:45:56.010832+00:00"},{"alias_kind":"pith_short_8","alias_value":"AFXWN6VW","created_at":"2026-07-05T08:45:56.010832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19308","citing_title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13310","citing_title":"RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31916","citing_title":"Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30649","citing_title":"Thinking Out Loud: Real-Time Deception Monitoring in Asymmetric LLM Negotiations","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29512","citing_title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23023","citing_title":"Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17989","citing_title":"AIT Academy: Cultivating the Complete Agent with a Confucian Three-Domain Curriculum","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ","json":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ.json","graph_json":"https://pith.science/api/pith-number/AFXWN6VWI2RWLLJR2IQI3VY2RJ/graph.json","events_json":"https://pith.science/api/pith-number/AFXWN6VWI2RWLLJR2IQI3VY2RJ/events.json","paper":"https://pith.science/paper/AFXWN6VW"},"agent_actions":{"view_html":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ","download_json":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ.json","view_paper":"https://pith.science/paper/AFXWN6VW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.13943&json=true","fetch_graph":"https://pith.science/api/pith-number/AFXWN6VWI2RWLLJR2IQI3VY2RJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AFXWN6VWI2RWLLJR2IQI3VY2RJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ/action/storage_attestation","attest_author":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ/action/author_attestation","sign_citation":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ/action/citation_signature","submit_replication":"https://pith.science/pith/AFXWN6VWI2RWLLJR2IQI3VY2RJ/action/replication_record"}},"created_at":"2026-07-05T08:45:56.010832+00:00","updated_at":"2026-07-05T08:45:56.010832+00:00"}