{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XPQSI4DLYDCJYVLCJOO5RTHG5F","short_pith_number":"pith:XPQSI4DL","schema_version":"1.0","canonical_sha256":"bbe124706bc0c49c55624b9dd8cce6e957c9f8aa6643f4c6295ac2f51c2b13eb","source":{"kind":"arxiv","id":"2309.17277","version":3},"attestation_state":"computed","paper":{"title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bill Yuchen Lin, Bo Yang, Jiaxian Guo, Paul Yoo, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2023-09-29T14:30:03Z","abstract_excerpt":"Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information. GPT-4, the recent breakthrough in large language models (LLMs) trained on massive passive data, is notable for its knowledge retrieval and reasoning abilities. This paper delves into the applicability of GPT-4's learned knowledge for imperfect information games. To achieve this, we introduce \\textbf{Suspicion-Agent}, an innovative agent that leverages GPT-4's capabilities for performing in i"},"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":"2309.17277","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-09-29T14:30:03Z","cross_cats_sorted":[],"title_canon_sha256":"db99f8276a4631df7c61fd49c3bdede0d6ce2cc98e28ef0fee4a845a2ad6c62e","abstract_canon_sha256":"5ff3c732c2dee74b17209224efabce3cda5de54e0f7d89db958482d00f199147"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:25.968852Z","signature_b64":"WUqKcJwRfKZbSk+GRkGYMvfpfno8RsgoXuqrT7v3LgeSuYUOK4ciB/9e0ZDFU09w5fYFRZBoYm8/l6RagOvMBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbe124706bc0c49c55624b9dd8cce6e957c9f8aa6643f4c6295ac2f51c2b13eb","last_reissued_at":"2026-07-05T09:01:25.968380Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:25.968380Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bill Yuchen Lin, Bo Yang, Jiaxian Guo, Paul Yoo, Yusuke Iwasawa, Yutaka Matsuo","submitted_at":"2023-09-29T14:30:03Z","abstract_excerpt":"Unlike perfect information games, where all elements are known to every player, imperfect information games emulate the real-world complexities of decision-making under uncertain or incomplete information. GPT-4, the recent breakthrough in large language models (LLMs) trained on massive passive data, is notable for its knowledge retrieval and reasoning abilities. This paper delves into the applicability of GPT-4's learned knowledge for imperfect information games. To achieve this, we introduce \\textbf{Suspicion-Agent}, an innovative agent that leverages GPT-4's capabilities for performing in i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17277","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/2309.17277/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":"2309.17277","created_at":"2026-07-05T09:01:25.968439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.17277v3","created_at":"2026-07-05T09:01:25.968439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17277","created_at":"2026-07-05T09:01:25.968439+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPQSI4DLYDCJ","created_at":"2026-07-05T09:01:25.968439+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPQSI4DLYDCJYVLC","created_at":"2026-07-05T09:01:25.968439+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPQSI4DL","created_at":"2026-07-05T09:01:25.968439+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"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":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22826","citing_title":"Evaluating Large Language Models in a Complex Hidden Role Game","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17510","citing_title":"Scale-Dependent Collective Adaptation in Self-Amending LLM Societies: A Cross-Family Study of Emergent Governance","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17788","citing_title":"Bayesian Social Deduction with Graph-Informed Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07301","citing_title":"SOM: Structured Opponent Modeling for LLM-based Agents via Structural Causal Model","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F","json":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F.json","graph_json":"https://pith.science/api/pith-number/XPQSI4DLYDCJYVLCJOO5RTHG5F/graph.json","events_json":"https://pith.science/api/pith-number/XPQSI4DLYDCJYVLCJOO5RTHG5F/events.json","paper":"https://pith.science/paper/XPQSI4DL"},"agent_actions":{"view_html":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F","download_json":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F.json","view_paper":"https://pith.science/paper/XPQSI4DL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.17277&json=true","fetch_graph":"https://pith.science/api/pith-number/XPQSI4DLYDCJYVLCJOO5RTHG5F/graph.json","fetch_events":"https://pith.science/api/pith-number/XPQSI4DLYDCJYVLCJOO5RTHG5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F/action/storage_attestation","attest_author":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F/action/author_attestation","sign_citation":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F/action/citation_signature","submit_replication":"https://pith.science/pith/XPQSI4DLYDCJYVLCJOO5RTHG5F/action/replication_record"}},"created_at":"2026-07-05T09:01:25.968439+00:00","updated_at":"2026-07-05T09:01:25.968439+00:00"}