{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V47ROJF7ZZE2SKRW7DLDPQSQBI","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":"69b84116481db88ae1e1bde621373cb412d3365e8b1e6c145cb9b3d8cab80b2f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T01:51:00Z","title_canon_sha256":"6334d597b955ac933c0b34035fd2242d9aaff7e96508756ab202466bf4713b7a"},"schema_version":"1.0","source":{"id":"2401.13178","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13178","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13178v2","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13178","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"V47ROJF7ZZE2","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"V47ROJF7ZZE2SKRW","created_at":"2026-07-05T09:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"V47ROJF7","created_at":"2026-07-05T09:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:9955ea94736ffc126c5a94d2e077d663d8814621abc66d8187660628f8fd8afb","target":"graph","created_at":"2026-07-05T09:53:28Z","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/2401.13178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating Large Language Models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A primary obstacle is the benchmarking of agent performance across diverse scenarios within a unified framework, especially in maintaining partially-observable environments and ensuring multi-round interactions. Moreover, current evaluation frameworks mostly focus on the final success rate, revealing few insights during the process and failing to provid","authors_text":"Chang Ma, Cheng Yang, Junlei Zhang, Junxian He, Lingpeng Kong, Yaohui Jin, Yujiu Yang, Zhenzhong Lan, Zhihao Zhu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T01:51:00Z","title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13178","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":"sha256:92b35ed7b9894b0e8b2a668b466e0bcaddecf259e04e96e090674d1b0689843d","target":"record","created_at":"2026-07-05T09:53:28Z","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":"69b84116481db88ae1e1bde621373cb412d3365e8b1e6c145cb9b3d8cab80b2f","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T01:51:00Z","title_canon_sha256":"6334d597b955ac933c0b34035fd2242d9aaff7e96508756ab202466bf4713b7a"},"schema_version":"1.0","source":{"id":"2401.13178","kind":"arxiv","version":2}},"canonical_sha256":"af3f1724bfce49a92a36f8d637c2500a059d2b29b7ee2b1971748104e8982f4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af3f1724bfce49a92a36f8d637c2500a059d2b29b7ee2b1971748104e8982f4f","first_computed_at":"2026-07-05T09:53:28.191874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:28.191874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yiqkVzIBG9H17EBzg0qoDnQLRMdDYUHNK1feeNVzKDtaknM9dkrAwTeK+LucQuzPneor6mzd2eq6nTR8MxtIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:28.192407Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13178","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92b35ed7b9894b0e8b2a668b466e0bcaddecf259e04e96e090674d1b0689843d","sha256:9955ea94736ffc126c5a94d2e077d663d8814621abc66d8187660628f8fd8afb"],"state_sha256":"ce24df3f75936e5f782b925336bb37323e61b6a9fc07ca940868c476cd6986da"}