{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EOJJGXJ3AHXPF6APJGLPEE67YL","short_pith_number":"pith:EOJJGXJ3","schema_version":"1.0","canonical_sha256":"2392935d3b01eef2f80f4996f213dfc2ef753d2b5e7e7cb6db4b576297d19880","source":{"kind":"arxiv","id":"2407.04467","version":3},"attestation_state":"computed","paper":{"title":"Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT"],"primary_cat":"cs.AI","authors_text":"Fernando Acero, Mar\\'ia P\\'erez-Ortiz, Nathan Herr, Roberta Raileanu, Zhibin Li","submitted_at":"2024-07-05T12:30:02Z","abstract_excerpt":"Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. To fully benefit from the potential of LLMs, it's essential to understand their ability to function in complex social scenarios. Game theory, which is already used to understand real-world interactions, provides a good framework for assessing these abilities. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5,"},"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":"2407.04467","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-05T12:30:02Z","cross_cats_sorted":["cs.CL","cs.GT"],"title_canon_sha256":"914385c7ae8bc3f44dfb56e0ef9ad2f491b8cf1c2c4abdba8ed2dfe8fe58d9bc","abstract_canon_sha256":"ece048c1e912a4de87ce9de329975b4a59d3029bc9ac0b5fd1ec08f8d21f1a38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:45.191993Z","signature_b64":"0Pv0CFJwDguy9Dzh0CImHmvDj00uDRvnddUxM8nMCepgrqn7nLUSJECn0L4mBGdHBtzosQtLDR3P4DedDcB8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2392935d3b01eef2f80f4996f213dfc2ef753d2b5e7e7cb6db4b576297d19880","last_reissued_at":"2026-07-05T09:20:45.191468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:45.191468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.GT"],"primary_cat":"cs.AI","authors_text":"Fernando Acero, Mar\\'ia P\\'erez-Ortiz, Nathan Herr, Roberta Raileanu, Zhibin Li","submitted_at":"2024-07-05T12:30:02Z","abstract_excerpt":"Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. To fully benefit from the potential of LLMs, it's essential to understand their ability to function in complex social scenarios. Game theory, which is already used to understand real-world interactions, provides a good framework for assessing these abilities. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04467","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/2407.04467/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":"2407.04467","created_at":"2026-07-05T09:20:45.191544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04467v3","created_at":"2026-07-05T09:20:45.191544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04467","created_at":"2026-07-05T09:20:45.191544+00:00"},{"alias_kind":"pith_short_12","alias_value":"EOJJGXJ3AHXP","created_at":"2026-07-05T09:20:45.191544+00:00"},{"alias_kind":"pith_short_16","alias_value":"EOJJGXJ3AHXPF6AP","created_at":"2026-07-05T09:20:45.191544+00:00"},{"alias_kind":"pith_short_8","alias_value":"EOJJGXJ3","created_at":"2026-07-05T09:20:45.191544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.10102","citing_title":"When Identity Overrides Incentives: Representational Choices as Governance Decisions in Multi-Agent LLM Systems","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12127","citing_title":"BLAST: Blockchain-based LLM-powered Agentic Spectrum Trading","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12127","citing_title":"BLAST: Blockchain-based LLM-powered Agentic Spectrum Trading","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL","json":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL.json","graph_json":"https://pith.science/api/pith-number/EOJJGXJ3AHXPF6APJGLPEE67YL/graph.json","events_json":"https://pith.science/api/pith-number/EOJJGXJ3AHXPF6APJGLPEE67YL/events.json","paper":"https://pith.science/paper/EOJJGXJ3"},"agent_actions":{"view_html":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL","download_json":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL.json","view_paper":"https://pith.science/paper/EOJJGXJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04467&json=true","fetch_graph":"https://pith.science/api/pith-number/EOJJGXJ3AHXPF6APJGLPEE67YL/graph.json","fetch_events":"https://pith.science/api/pith-number/EOJJGXJ3AHXPF6APJGLPEE67YL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL/action/storage_attestation","attest_author":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL/action/author_attestation","sign_citation":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL/action/citation_signature","submit_replication":"https://pith.science/pith/EOJJGXJ3AHXPF6APJGLPEE67YL/action/replication_record"}},"created_at":"2026-07-05T09:20:45.191544+00:00","updated_at":"2026-07-05T09:20:45.191544+00:00"}