{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LHQB57ZJUL4PIF65G5ZLALAIRW","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":"46f6194d0a63f3e2220c5604717ebc38696f5d17004e38dc2cae673d293ddb71","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-29T09:19:23Z","title_canon_sha256":"b2706d7a38fde4a09dfd0d4e090b30e47e5fdc231c7be5c36cdedbd21ce90e7f"},"schema_version":"1.0","source":{"id":"2407.00379","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00379","created_at":"2026-07-05T10:14:42Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00379v2","created_at":"2026-07-05T10:14:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00379","created_at":"2026-07-05T10:14:42Z"},{"alias_kind":"pith_short_12","alias_value":"LHQB57ZJUL4P","created_at":"2026-07-05T10:14:42Z"},{"alias_kind":"pith_short_16","alias_value":"LHQB57ZJUL4PIF65","created_at":"2026-07-05T10:14:42Z"},{"alias_kind":"pith_short_8","alias_value":"LHQB57ZJ","created_at":"2026-07-05T10:14:42Z"}],"graph_snapshots":[{"event_id":"sha256:88f456a7343a317039c4c87c9fc74706256c168c445e69f672b24ad9e3cf7d50","target":"graph","created_at":"2026-07-05T10:14:42Z","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/2407.00379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The ``arms race'' of Large Language Models (LLMs) demands new benchmarks to examine their progresses. In this paper, we introduce GraphArena, a benchmarking tool designed to evaluate LLMs on real-world graph computational problems. It offers a suite of four polynomial-time tasks (e.g., Shortest Distance) and six NP-complete challenges (e.g., Traveling Salesman Problem). GraphArena features a rigorous evaluation framework that classifies LLM outputs as correct, suboptimal (feasible but not optimal), hallucinatory (properly formatted but infeasible), or missing. Evaluation of over 10 LLMs reveal","authors_text":"Jia Li, Jianheng Tang, Nuo Chen, Qifan Zhang, Yuhan Li","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-29T09:19:23Z","title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00379","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:bfa10ca5d2954a67e4f19d7182f2ff13a4a41401d1377eae402a1cc48d3e7bac","target":"record","created_at":"2026-07-05T10:14:42Z","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":"46f6194d0a63f3e2220c5604717ebc38696f5d17004e38dc2cae673d293ddb71","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-29T09:19:23Z","title_canon_sha256":"b2706d7a38fde4a09dfd0d4e090b30e47e5fdc231c7be5c36cdedbd21ce90e7f"},"schema_version":"1.0","source":{"id":"2407.00379","kind":"arxiv","version":2}},"canonical_sha256":"59e01eff29a2f8f417dd3772b02c088db8b95781848a771431dc32a5038697ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59e01eff29a2f8f417dd3772b02c088db8b95781848a771431dc32a5038697ab","first_computed_at":"2026-07-05T10:14:42.697435Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:14:42.697435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kDZoyPwctkEeE76f8rAxcOMkMhziYdInYjpd7qre6+OcBUbYgIRdvYhctSWmNk+Foo1QQ2J1JP6HdK6/WU8cAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:14:42.697917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00379","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bfa10ca5d2954a67e4f19d7182f2ff13a4a41401d1377eae402a1cc48d3e7bac","sha256:88f456a7343a317039c4c87c9fc74706256c168c445e69f672b24ad9e3cf7d50"],"state_sha256":"46a15cf7467e6162f7e6249f3f6abf365cc67ca7c3db2a97a9654bf35c9f78c9"}