{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RTCKXFNQR2W2E7QUT33YJ3JUAV","short_pith_number":"pith:RTCKXFNQ","schema_version":"1.0","canonical_sha256":"8cc4ab95b08eada27e149ef784ed34056b848867a8846107e5ec6549568a6146","source":{"kind":"arxiv","id":"2310.01320","version":3},"attestation_state":"computed","paper":{"title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Andrew Zhao, Chang Liu, Chaofei Wang, Gao Huang, Qisen Yang, Shenzhi Wang, Shiji Song, Shuo Chen, Siyuan Qi, Zilong Zheng","submitted_at":"2023-10-02T16:27:36Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have brought remarkable success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information processed by LLMs is consistently honest, neglecting the pervasive deceptive or misleading information in human society and AI-generated content. This oversight makes LLMs susceptible to malicious manipulations, potentially resulting in detrimental outcomes. This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments. Avalon, full of misinformation and requiring sophist"},"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":"2310.01320","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-10-02T16:27:36Z","cross_cats_sorted":["cs.CL","cs.CY","cs.LG","cs.MA"],"title_canon_sha256":"d33f7a582ee8fceaa7f99368833d8c8975f06da919c183d7489daffb2b29bd01","abstract_canon_sha256":"374001d8bd7bec622255aa21209a9b8b2ba306761d77e860a39351d1190158d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:20.957523Z","signature_b64":"fge6sj4N8rP+3VUkHK/SNa+13YJdbj+KrTEjzWFBCwR8Z4inFOXRd/Rhb2amT3a2zwr4fK2ZNGBsMwmRpdf9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cc4ab95b08eada27e149ef784ed34056b848867a8846107e5ec6549568a6146","last_reissued_at":"2026-07-05T07:04:20.957046Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:20.957046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CY","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Andrew Zhao, Chang Liu, Chaofei Wang, Gao Huang, Qisen Yang, Shenzhi Wang, Shiji Song, Shuo Chen, Siyuan Qi, Zilong Zheng","submitted_at":"2023-10-02T16:27:36Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) have brought remarkable success in the field of LLM-as-Agent. Nevertheless, a prevalent assumption is that the information processed by LLMs is consistently honest, neglecting the pervasive deceptive or misleading information in human society and AI-generated content. This oversight makes LLMs susceptible to malicious manipulations, potentially resulting in detrimental outcomes. This study utilizes the intricate Avalon game as a testbed to explore LLMs' potential in deceptive environments. Avalon, full of misinformation and requiring sophist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.01320","kind":"arxiv","version":3},"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/2310.01320/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":"2310.01320","created_at":"2026-07-05T07:04:20.957100+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.01320v3","created_at":"2026-07-05T07:04:20.957100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.01320","created_at":"2026-07-05T07:04:20.957100+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTCKXFNQR2W2","created_at":"2026-07-05T07:04:20.957100+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTCKXFNQR2W2E7QU","created_at":"2026-07-05T07:04:20.957100+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTCKXFNQ","created_at":"2026-07-05T07:04:20.957100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28456","citing_title":"Is Lying an Emergent Behaviour in LLMs? Evidence from Gaslighting AI agents in a Sustainability Game","ref_index":35,"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":86,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17788","citing_title":"Bayesian Social Deduction with Graph-Informed Language Models","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2402.01680","citing_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06452","citing_title":"Learning to Interrupt in Language-based Multi-agent Communication","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19278","citing_title":"Explicit Trait Inference for Multi-Agent Coordination","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV","json":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV.json","graph_json":"https://pith.science/api/pith-number/RTCKXFNQR2W2E7QUT33YJ3JUAV/graph.json","events_json":"https://pith.science/api/pith-number/RTCKXFNQR2W2E7QUT33YJ3JUAV/events.json","paper":"https://pith.science/paper/RTCKXFNQ"},"agent_actions":{"view_html":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV","download_json":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV.json","view_paper":"https://pith.science/paper/RTCKXFNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.01320&json=true","fetch_graph":"https://pith.science/api/pith-number/RTCKXFNQR2W2E7QUT33YJ3JUAV/graph.json","fetch_events":"https://pith.science/api/pith-number/RTCKXFNQR2W2E7QUT33YJ3JUAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV/action/storage_attestation","attest_author":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV/action/author_attestation","sign_citation":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV/action/citation_signature","submit_replication":"https://pith.science/pith/RTCKXFNQR2W2E7QUT33YJ3JUAV/action/replication_record"}},"created_at":"2026-07-05T07:04:20.957100+00:00","updated_at":"2026-07-05T07:04:20.957100+00:00"}