{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X3Q35LJ2N6B2UFFGIEGQFELEGF","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":"110eb644e5770fe5f3297a79ce24536d4baf5e95767c4568152475fac7e24367","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T11:31:48Z","title_canon_sha256":"2e846d588e74a0b9826d36b0fc71bf22ba12f50bff80fe0fbbba760f969bbc36"},"schema_version":"1.0","source":{"id":"2402.16499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16499","created_at":"2026-07-05T07:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16499v1","created_at":"2026-07-05T07:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16499","created_at":"2026-07-05T07:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"X3Q35LJ2N6B2","created_at":"2026-07-05T07:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"X3Q35LJ2N6B2UFFG","created_at":"2026-07-05T07:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"X3Q35LJ2","created_at":"2026-07-05T07:49:22Z"}],"graph_snapshots":[{"event_id":"sha256:4802658dc74c64e90600778bbc8b3dd4ac865083a4e34d3fa765bdb753af7d8d","target":"graph","created_at":"2026-07-05T07:49:22Z","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/2402.16499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence. However, existing benchmarks for evaluating LLM Agents either use static datasets, potentially leading to data leakage or focus only on single-agent scenarios, overlooking the complexities of multi-agent interactions. There is a lack of a benchmark that evaluates the diverse capabilities of LLM agents in multi-agent, dynamic environments. To this end, we introduce LLMArena, a novel and easily extensible framework for evaluating the diverse capab","authors_text":"Junzhe Chen, Lijie Wen, Shiyu Huang, Shuodi Liu, Wei-Wei Tu, Xuming Hu, Zhaofeng He","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T11:31:48Z","title":"LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16499","kind":"arxiv","version":1},"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":"sha256:3891d4a4de50cf30c04307a6a86083132b651722ab3bc356a66e1585e0a0c954","target":"record","created_at":"2026-07-05T07:49:22Z","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":"110eb644e5770fe5f3297a79ce24536d4baf5e95767c4568152475fac7e24367","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T11:31:48Z","title_canon_sha256":"2e846d588e74a0b9826d36b0fc71bf22ba12f50bff80fe0fbbba760f969bbc36"},"schema_version":"1.0","source":{"id":"2402.16499","kind":"arxiv","version":1}},"canonical_sha256":"bee1bead3a6f83aa14a6410d029164314b36773004329f9abebd1c630d1596ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bee1bead3a6f83aa14a6410d029164314b36773004329f9abebd1c630d1596ba","first_computed_at":"2026-07-05T07:49:22.959759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:49:22.959759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1oucKp0nyNHcxMYHGvl20tXUI3YhoOhl1sYlbA3NYyR9T9X5DKKf5kb9ihYdUK+mPcuTIaEv/2b1QD285Ef+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:49:22.960183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3891d4a4de50cf30c04307a6a86083132b651722ab3bc356a66e1585e0a0c954","sha256:4802658dc74c64e90600778bbc8b3dd4ac865083a4e34d3fa765bdb753af7d8d"],"state_sha256":"552da4780db6801fac492950f98bfdf855e39303cd43132e9986626898f0879e"}