{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LHQB57ZJUL4PIF65G5ZLALAIRW","short_pith_number":"pith:LHQB57ZJ","schema_version":"1.0","canonical_sha256":"59e01eff29a2f8f417dd3772b02c088db8b95781848a771431dc32a5038697ab","source":{"kind":"arxiv","id":"2407.00379","version":2},"attestation_state":"computed","paper":{"title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jia Li, Jianheng Tang, Nuo Chen, Qifan Zhang, Yuhan Li","submitted_at":"2024-06-29T09:19:23Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.00379","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-29T09:19:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b2706d7a38fde4a09dfd0d4e090b30e47e5fdc231c7be5c36cdedbd21ce90e7f","abstract_canon_sha256":"46f6194d0a63f3e2220c5604717ebc38696f5d17004e38dc2cae673d293ddb71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:42.697917Z","signature_b64":"kDZoyPwctkEeE76f8rAxcOMkMhziYdInYjpd7qre6+OcBUbYgIRdvYhctSWmNk+Foo1QQ2J1JP6HdK6/WU8cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59e01eff29a2f8f417dd3772b02c088db8b95781848a771431dc32a5038697ab","last_reissued_at":"2026-07-05T10:14:42.697435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:42.697435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraphArena: Evaluating and Exploring Large Language Models on Graph Computation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jia Li, Jianheng Tang, Nuo Chen, Qifan Zhang, Yuhan Li","submitted_at":"2024-06-29T09:19:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00379","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.00379/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.00379","created_at":"2026-07-05T10:14:42.697491+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00379v2","created_at":"2026-07-05T10:14:42.697491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00379","created_at":"2026-07-05T10:14:42.697491+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHQB57ZJUL4P","created_at":"2026-07-05T10:14:42.697491+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHQB57ZJUL4PIF65","created_at":"2026-07-05T10:14:42.697491+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHQB57ZJ","created_at":"2026-07-05T10:14:42.697491+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11562","citing_title":"GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25246","citing_title":"FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2601.19924","citing_title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12197","citing_title":"A Unified Graph Language Model for Multi-Domain Multi-Task Graph Alignment Instruction Tuning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10366","citing_title":"EGL-SCA: Structural Credit Assignment for Co-Evolving Instructions and Tools in Graph Reasoning Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08498","citing_title":"MathConstraint: Automated Generation of Verified Combinatorial Reasoning Instances for LLMs","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW","json":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW.json","graph_json":"https://pith.science/api/pith-number/LHQB57ZJUL4PIF65G5ZLALAIRW/graph.json","events_json":"https://pith.science/api/pith-number/LHQB57ZJUL4PIF65G5ZLALAIRW/events.json","paper":"https://pith.science/paper/LHQB57ZJ"},"agent_actions":{"view_html":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW","download_json":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW.json","view_paper":"https://pith.science/paper/LHQB57ZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00379&json=true","fetch_graph":"https://pith.science/api/pith-number/LHQB57ZJUL4PIF65G5ZLALAIRW/graph.json","fetch_events":"https://pith.science/api/pith-number/LHQB57ZJUL4PIF65G5ZLALAIRW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW/action/storage_attestation","attest_author":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW/action/author_attestation","sign_citation":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW/action/citation_signature","submit_replication":"https://pith.science/pith/LHQB57ZJUL4PIF65G5ZLALAIRW/action/replication_record"}},"created_at":"2026-07-05T10:14:42.697491+00:00","updated_at":"2026-07-05T10:14:42.697491+00:00"}