{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DGPBQVK3L4T56MGDODCRANDTKD","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8033d701b784453ae6cb54a30c19446604b1981f192239d5ae69e8cbd7ec175d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T18:23:36Z","title_canon_sha256":"d52fdb5ad4c5b550b2f9d78996c8eed78f31909d1c180cbe5ea54aaf4639a7c5"},"schema_version":"1.0","source":{"id":"2402.12348","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12348","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12348v2","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12348","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"DGPBQVK3L4T5","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"DGPBQVK3L4T56MGD","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"DGPBQVK3","created_at":"2026-07-05T08:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:d9593876e3714d70d03e05d6682dc663db838d7f8f6e42b82a8f7b7362fec797","target":"graph","created_at":"2026-07-05T08:29:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.12348/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bhavya Kailkhura, Elias Stengel-Eskin, James Diffenderfer, Jinhao Duan, Kaidi Xu, Lichao Sun, Mohit Bansal, Renming Zhang, Tianlong Chen","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T18:23:36Z","title":"GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12348","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1891bd0499d1e70934512f6fcdd98835c3ffaa21caccf860c6b3dfb7660465ce","target":"record","created_at":"2026-07-05T08:29:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8033d701b784453ae6cb54a30c19446604b1981f192239d5ae69e8cbd7ec175d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T18:23:36Z","title_canon_sha256":"d52fdb5ad4c5b550b2f9d78996c8eed78f31909d1c180cbe5ea54aaf4639a7c5"},"schema_version":"1.0","source":{"id":"2402.12348","kind":"arxiv","version":2}},"canonical_sha256":"199e18555b5f27df30c370c510347350edba5355e9400e38fbd3e76197ab764c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"199e18555b5f27df30c370c510347350edba5355e9400e38fbd3e76197ab764c","first_computed_at":"2026-07-05T08:29:22.537912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:22.537912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ispahf5nUKdAH6ngBPKm/kmqppouz2fJJLgrP2KKBeu0aQ5ymrM7re1//k405+Zoru6MOb4vQzHRHp7LqztEDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:22.538382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12348","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1891bd0499d1e70934512f6fcdd98835c3ffaa21caccf860c6b3dfb7660465ce","sha256:d9593876e3714d70d03e05d6682dc663db838d7f8f6e42b82a8f7b7362fec797"],"state_sha256":"75e7f04b6466968dfcf43e59061851442fbe738a96e79c19d286a23d0367480d"}