{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TFI4BKQLYNTZZDYMQ73MSYFASF","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":"1aeaa0cb6707f5fd4d17b1f5b8dc2f8a4b9a2beba0878454239c4dd3ec30dbeb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T00:28:43Z","title_canon_sha256":"1f9eca2e477ebd2c137704f8a6499246dbb3f3a976b1934735725ba75b4d2010"},"schema_version":"1.0","source":{"id":"2406.06613","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06613","created_at":"2026-07-05T08:46:55Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06613v2","created_at":"2026-07-05T08:46:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06613","created_at":"2026-07-05T08:46:55Z"},{"alias_kind":"pith_short_12","alias_value":"TFI4BKQLYNTZ","created_at":"2026-07-05T08:46:55Z"},{"alias_kind":"pith_short_16","alias_value":"TFI4BKQLYNTZZDYM","created_at":"2026-07-05T08:46:55Z"},{"alias_kind":"pith_short_8","alias_value":"TFI4BKQL","created_at":"2026-07-05T08:46:55Z"}],"graph_snapshots":[{"event_id":"sha256:e0ed370e12c88735a017f7cc85206f11fafe35c38c20e13adcb3b34a89518e4c","target":"graph","created_at":"2026-07-05T08:46:55Z","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/2406.06613/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models have demonstrated remarkable few-shot performance on many natural language understanding tasks. Despite several demonstrations of using large language models in complex, strategic scenarios, there lacks a comprehensive framework for evaluating agents' performance across various types of reasoning found in games. To address this gap, we introduce GameBench, a cross-domain benchmark for evaluating strategic reasoning abilities of LLM agents. We focus on 9 different game environments, where each covers at least one axis of key reasoning skill identified in strategy games, an","authors_text":"Anthony Costarelli, Arjun Yadav, Carlson Cheng, Grace Sodunke, Joshua Clymer, Mat Allen, Roman Hauksson, Suhas Hariharan, Wenjie Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T00:28:43Z","title":"GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06613","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:cc2ae999a41dc6f45b6b2878e5ea5871a3529a983c615952a6f4a48c18f92959","target":"record","created_at":"2026-07-05T08:46:55Z","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":"1aeaa0cb6707f5fd4d17b1f5b8dc2f8a4b9a2beba0878454239c4dd3ec30dbeb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-07T00:28:43Z","title_canon_sha256":"1f9eca2e477ebd2c137704f8a6499246dbb3f3a976b1934735725ba75b4d2010"},"schema_version":"1.0","source":{"id":"2406.06613","kind":"arxiv","version":2}},"canonical_sha256":"9951c0aa0bc3679c8f0c87f6c960a0915a1ca5033dfd60a77ba7c9252c0bfbf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9951c0aa0bc3679c8f0c87f6c960a0915a1ca5033dfd60a77ba7c9252c0bfbf2","first_computed_at":"2026-07-05T08:46:55.396538Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:46:55.396538Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mCRVJ21NkJXMUMpfFgC+6bDyhAvEQIdIZBj0eJagBVYx5R5qG4VUR9bhHX8xsIECqvw/KH0L6ej7N6fleBYGCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:46:55.397045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06613","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc2ae999a41dc6f45b6b2878e5ea5871a3529a983c615952a6f4a48c18f92959","sha256:e0ed370e12c88735a017f7cc85206f11fafe35c38c20e13adcb3b34a89518e4c"],"state_sha256":"8aa43f0699ac585c23222e8660554bd869429eea9a3b9b73cc7acb371dede897"}