{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ASSK32XBYLYGULJZISSN5FHMH7","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":"44726843abd9cc84baebad2604febd6b741cf3243ee1389c895e3ef1b2131606","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:29:21Z","title_canon_sha256":"a0d21352f75211616087bc864369d913c42d9d7363dbe1118785a3fd09793803"},"schema_version":"1.0","source":{"id":"2410.08085","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08085","created_at":"2026-07-05T11:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08085v4","created_at":"2026-07-05T11:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08085","created_at":"2026-07-05T11:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"ASSK32XBYLYG","created_at":"2026-07-05T11:07:05Z"},{"alias_kind":"pith_short_16","alias_value":"ASSK32XBYLYGULJZ","created_at":"2026-07-05T11:07:05Z"},{"alias_kind":"pith_short_8","alias_value":"ASSK32XB","created_at":"2026-07-05T11:07:05Z"}],"graph_snapshots":[{"event_id":"sha256:4e4e421a30ed004cbffb07fcafdc986b9530b9ab59343a659c79fe9906028dd8","target":"graph","created_at":"2026-07-05T11:07:05Z","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/2410.08085/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent works integrating Knowledge Graphs (KGs) have shown promising improvements in enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing benchmarks primarily focus on closed-ended tasks, leaving a gap in evaluating performance on more complex, real-world scenarios. This limitation also hinders a thorough assessment of KGs' potential to reduce hallucinations in LLMs. To address this, we introduce OKGQA, a new benchmark specifically designed to evaluate LLMs augmented with KGs in open-ended, real-world question answering settings. OKGQA reflects practical comp","authors_text":"Bryan Hooi, Yuan Sui, Yufei He, Zifeng Ding","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:29:21Z","title":"Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08085","kind":"arxiv","version":4},"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":"sha256:463ebdc4054159e6ff610b1ed23e1824d9dfa6dd50ab75ddeedbd51d323d5493","target":"record","created_at":"2026-07-05T11:07:05Z","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":"44726843abd9cc84baebad2604febd6b741cf3243ee1389c895e3ef1b2131606","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T16:29:21Z","title_canon_sha256":"a0d21352f75211616087bc864369d913c42d9d7363dbe1118785a3fd09793803"},"schema_version":"1.0","source":{"id":"2410.08085","kind":"arxiv","version":4}},"canonical_sha256":"04a4adeae1c2f06a2d3944a4de94ec3fc537f448ac03ce5b5290a0c9547a1df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04a4adeae1c2f06a2d3944a4de94ec3fc537f448ac03ce5b5290a0c9547a1df4","first_computed_at":"2026-07-05T11:07:05.206824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:05.206824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xy1Xb1lzpEm81Q0cmB8C93O2IIEmvjiyv5kYI4Ys6xbBDveyMg1Sq0bmgEqMcQrrRhY5WJ86d9eZ5F18/RXgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:05.207175Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08085","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:463ebdc4054159e6ff610b1ed23e1824d9dfa6dd50ab75ddeedbd51d323d5493","sha256:4e4e421a30ed004cbffb07fcafdc986b9530b9ab59343a659c79fe9906028dd8"],"state_sha256":"059e2eba4ede8598e1c86bdaa7359d186fdc198fc1e178f3f7ce0d9716845273"}