{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O66NRQHXYYS7MCITWNQHDFXK3I","short_pith_number":"pith:O66NRQHX","schema_version":"1.0","canonical_sha256":"77bcd8c0f7c625f60913b3607196eada3f968dfdd8f818ad5b9e91643845f666","source":{"kind":"arxiv","id":"2407.02936","version":2},"attestation_state":"computed","paper":{"title":"GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Qin, Hui Wang, Ming Liu, Zike Yuan","submitted_at":"2024-07-03T09:12:38Z","abstract_excerpt":"Evaluating the graph comprehension and reasoning abilities of Large Language Models (LLMs) is challenging and often incomplete. Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions. This paper presents GraCoRe, a benchmark for systematically assessing LLMs' graph comprehension and reasoning. GraCoRe uses a three-tier hierarchical taxonomy to categorize and test models on pure graph and heterogeneous graphs, subdividing capabilities into 10 distinct areas tested through 19 tasks. Our benchm"},"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":"2407.02936","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-03T09:12:38Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"48995bc52bf895eb45e6277984035bb06df4cbdd60a2d8016eeae1cbc61f9d0d","abstract_canon_sha256":"cc596d9213f006d19cf2f40e65457bd0dd277a21cb9789dbaca46a163d8c7be9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:20:13.445510Z","signature_b64":"YPX8VyiP30JShTcEoibGY+I27JRqaCKI8mtT/tIY9rl1TFbekYStNI3wIxFDbaEH5btAotzVaX5vmeLCGU0cAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77bcd8c0f7c625f60913b3607196eada3f968dfdd8f818ad5b9e91643845f666","last_reissued_at":"2026-07-05T10:20:13.444910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:20:13.444910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Bing Qin, Hui Wang, Ming Liu, Zike Yuan","submitted_at":"2024-07-03T09:12:38Z","abstract_excerpt":"Evaluating the graph comprehension and reasoning abilities of Large Language Models (LLMs) is challenging and often incomplete. Existing benchmarks focus primarily on pure graph understanding, lacking a comprehensive evaluation across all graph types and detailed capability definitions. This paper presents GraCoRe, a benchmark for systematically assessing LLMs' graph comprehension and reasoning. GraCoRe uses a three-tier hierarchical taxonomy to categorize and test models on pure graph and heterogeneous graphs, subdividing capabilities into 10 distinct areas tested through 19 tasks. Our benchm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02936","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/2407.02936/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":"2407.02936","created_at":"2026-07-05T10:20:13.444990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02936v2","created_at":"2026-07-05T10:20:13.444990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02936","created_at":"2026-07-05T10:20:13.444990+00:00"},{"alias_kind":"pith_short_12","alias_value":"O66NRQHXYYS7","created_at":"2026-07-05T10:20:13.444990+00:00"},{"alias_kind":"pith_short_16","alias_value":"O66NRQHXYYS7MCIT","created_at":"2026-07-05T10:20:13.444990+00:00"},{"alias_kind":"pith_short_8","alias_value":"O66NRQHX","created_at":"2026-07-05T10:20:13.444990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01684","citing_title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","ref_index":57,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I","json":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I.json","graph_json":"https://pith.science/api/pith-number/O66NRQHXYYS7MCITWNQHDFXK3I/graph.json","events_json":"https://pith.science/api/pith-number/O66NRQHXYYS7MCITWNQHDFXK3I/events.json","paper":"https://pith.science/paper/O66NRQHX"},"agent_actions":{"view_html":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I","download_json":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I.json","view_paper":"https://pith.science/paper/O66NRQHX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02936&json=true","fetch_graph":"https://pith.science/api/pith-number/O66NRQHXYYS7MCITWNQHDFXK3I/graph.json","fetch_events":"https://pith.science/api/pith-number/O66NRQHXYYS7MCITWNQHDFXK3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I/action/storage_attestation","attest_author":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I/action/author_attestation","sign_citation":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I/action/citation_signature","submit_replication":"https://pith.science/pith/O66NRQHXYYS7MCITWNQHDFXK3I/action/replication_record"}},"created_at":"2026-07-05T10:20:13.444990+00:00","updated_at":"2026-07-05T10:20:13.444990+00:00"}