{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DGPBQVK3L4T56MGDODCRANDTKD","short_pith_number":"pith:DGPBQVK3","schema_version":"1.0","canonical_sha256":"199e18555b5f27df30c370c510347350edba5355e9400e38fbd3e76197ab764c","source":{"kind":"arxiv","id":"2402.12348","version":2},"attestation_state":"computed","paper":{"title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhavya Kailkhura, Elias Stengel-Eskin, James Diffenderfer, Jinhao Duan, Kaidi Xu, Lichao Sun, Mohit Bansal, Renming Zhang, Tianlong Chen","submitted_at":"2024-02-19T18:23:36Z","abstract_excerpt":"As Large Language Models (LLMs) are integrated into critical real-world applications, their strategic and logical reasoning abilities are increasingly crucial. This paper evaluates LLMs' reasoning abilities in competitive environments through game-theoretic tasks, e.g., board and card games that require pure logic and strategic reasoning to compete with opponents. We first propose GTBench, a language-driven environment composing 10 widely recognized tasks, across a comprehensive game taxonomy: complete versus incomplete information, dynamic versus static, and probabilistic versus deterministic"},"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":"2402.12348","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T18:23:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d52fdb5ad4c5b550b2f9d78996c8eed78f31909d1c180cbe5ea54aaf4639a7c5","abstract_canon_sha256":"8033d701b784453ae6cb54a30c19446604b1981f192239d5ae69e8cbd7ec175d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.538382Z","signature_b64":"ispahf5nUKdAH6ngBPKm/kmqppouz2fJJLgrP2KKBeu0aQ5ymrM7re1//k405+Zoru6MOb4vQzHRHp7LqztEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"199e18555b5f27df30c370c510347350edba5355e9400e38fbd3e76197ab764c","last_reissued_at":"2026-07-05T08:29:22.537912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.537912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bhavya Kailkhura, Elias Stengel-Eskin, James Diffenderfer, Jinhao Duan, Kaidi Xu, Lichao Sun, Mohit Bansal, Renming Zhang, Tianlong Chen","submitted_at":"2024-02-19T18:23:36Z","abstract_excerpt":"As Large Language Models (LLMs) are integrated into critical real-world applications, their strategic and logical reasoning abilities are increasingly crucial. This paper evaluates LLMs' reasoning abilities in competitive environments through game-theoretic tasks, e.g., board and card games that require pure logic and strategic reasoning to compete with opponents. We first propose GTBench, a language-driven environment composing 10 widely recognized tasks, across a comprehensive game taxonomy: complete versus incomplete information, dynamic versus static, and probabilistic versus deterministic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12348","kind":"arxiv","version":2},"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/2402.12348/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":"2402.12348","created_at":"2026-07-05T08:29:22.537971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12348v2","created_at":"2026-07-05T08:29:22.537971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12348","created_at":"2026-07-05T08:29:22.537971+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGPBQVK3L4T5","created_at":"2026-07-05T08:29:22.537971+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGPBQVK3L4T56MGD","created_at":"2026-07-05T08:29:22.537971+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGPBQVK3","created_at":"2026-07-05T08:29:22.537971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24391","citing_title":"Age of LLM: A Strategic 1v1 Benchmark for Reasoning, Diplomacy and Reliability of Large Language Models under Fog of War","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19338","citing_title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","ref_index":20,"is_internal_anchor":false},{"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":120,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24539","citing_title":"DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27757","citing_title":"Towards Reliable and Robust LLM Planning: Symbolic Feedback-Driven Iterative Self-Refinement Framework","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24162","citing_title":"BehaviorBench: Benchmarking Foundation Models for Behavioral Science Tasks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02387","citing_title":"VS-Bench: Evaluating VLMs for Strategic Abilities in Multi-Agent Environments","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13875","citing_title":"Common-agency Games for Multi-Objective Test-Time Alignment","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21282","citing_title":"Strategic Heterogeneous Multi-Agent Architecture for Cost-Effective Code Vulnerability Detection","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD","json":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD.json","graph_json":"https://pith.science/api/pith-number/DGPBQVK3L4T56MGDODCRANDTKD/graph.json","events_json":"https://pith.science/api/pith-number/DGPBQVK3L4T56MGDODCRANDTKD/events.json","paper":"https://pith.science/paper/DGPBQVK3"},"agent_actions":{"view_html":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD","download_json":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD.json","view_paper":"https://pith.science/paper/DGPBQVK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12348&json=true","fetch_graph":"https://pith.science/api/pith-number/DGPBQVK3L4T56MGDODCRANDTKD/graph.json","fetch_events":"https://pith.science/api/pith-number/DGPBQVK3L4T56MGDODCRANDTKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD/action/storage_attestation","attest_author":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD/action/author_attestation","sign_citation":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD/action/citation_signature","submit_replication":"https://pith.science/pith/DGPBQVK3L4T56MGDODCRANDTKD/action/replication_record"}},"created_at":"2026-07-05T08:29:22.537971+00:00","updated_at":"2026-07-05T08:29:22.537971+00:00"}