{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4VWDYPCPTOCPJDN7BDPL6MMRJO","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":"70abbeded872f4c50a4f0773935942fe635b90a92093e542387586d004277198","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-18T14:04:47Z","title_canon_sha256":"1859a9394e223fd572cc8c3e05e80ddef2e449f8272bf8b9c5c7fdb52d3707b4"},"schema_version":"1.0","source":{"id":"2403.11807","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11807","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11807v7","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11807","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_12","alias_value":"4VWDYPCPTOCP","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_16","alias_value":"4VWDYPCPTOCPJDN7","created_at":"2026-07-05T10:25:05Z"},{"alias_kind":"pith_short_8","alias_value":"4VWDYPCP","created_at":"2026-07-05T10:25:05Z"}],"graph_snapshots":[{"event_id":"sha256:af45de001f11ff7b514be81a7e2613949ad864796796b8e53164f850ac2d6eba","target":"graph","created_at":"2026-07-05T10:25:05Z","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/2403.11807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Decision-making is a complex process requiring diverse abilities, making it an excellent framework for evaluating Large Language Models (LLMs). Researchers have examined LLMs' decision-making through the lens of Game Theory. However, existing evaluation mainly focus on two-player scenarios where an LLM competes against another. Additionally, previous benchmarks suffer from test set leakage due to their static design. We introduce GAMA($\\gamma$)-Bench, a new framework for evaluating LLMs' Gaming Ability in Multi-Agent environments. It includes eight classical game theory scenarios and a dynamic","authors_text":"Eric John Li, Jen-tse Huang, Man Ho Lam, Michael R. Lyu, Tian Liang, Wenxiang Jiao, Wenxuan Wang, Xing Wang, Youliang Yuan, Zhaopeng Tu","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-18T14:04:47Z","title":"How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11807","kind":"arxiv","version":7},"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":"sha256:3552a448444d09ae21750b7d2e5cdb5b090bca30196c848225f3b7d535ce7525","target":"record","created_at":"2026-07-05T10:25:05Z","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":"70abbeded872f4c50a4f0773935942fe635b90a92093e542387586d004277198","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-03-18T14:04:47Z","title_canon_sha256":"1859a9394e223fd572cc8c3e05e80ddef2e449f8272bf8b9c5c7fdb52d3707b4"},"schema_version":"1.0","source":{"id":"2403.11807","kind":"arxiv","version":7}},"canonical_sha256":"e56c3c3c4f9b84f48dbf08debf31914bac18c7e08295e780363ef404ba19dc52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e56c3c3c4f9b84f48dbf08debf31914bac18c7e08295e780363ef404ba19dc52","first_computed_at":"2026-07-05T10:25:05.320815Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:25:05.320815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wf9RlkfuYbthhpbx8HrX096TYNdmrvY0wjNqndAypRWxja5wlqjW0qe7umV9y3wreMAwlNdpzRM65tt7IYtMBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:25:05.321295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11807","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3552a448444d09ae21750b7d2e5cdb5b090bca30196c848225f3b7d535ce7525","sha256:af45de001f11ff7b514be81a7e2613949ad864796796b8e53164f850ac2d6eba"],"state_sha256":"42766c88592699009fdc40fba90671c0f070cd4c1b7786288cc59b6c2afcd714"}