{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2LN7PHKDYKUX65WL4GBVGQ6Z72","short_pith_number":"pith:2LN7PHKD","schema_version":"1.0","canonical_sha256":"d2dbf79d43c2a97f76cbe1835343d9fe9054f3279fc2f5a12259570cf84c7f6d","source":{"kind":"arxiv","id":"2504.07087","version":1},"attestation_state":"computed","paper":{"title":"KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aram Galstyan, Elan Markowitz, Greg Ver Steeg, Krupa Galiya","submitted_at":"2025-04-09T17:58:47Z","abstract_excerpt":"Knowledge graphs have emerged as a popular method for injecting up-to-date, factual knowledge into large language models (LLMs). This is typically achieved by converting the knowledge graph into text that the LLM can process in context. While multiple methods of encoding knowledge graphs have been proposed, the impact of this textualization process on LLM performance remains under-explored. We introduce KG-LLM-Bench, a comprehensive and extensible benchmark spanning five knowledge graph understanding tasks, and evaluate how different encoding strategies affect performance across various base m"},"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":"2504.07087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-09T17:58:47Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"fea13bc4d5757de2ded7ea61f6633e376595c357036140e731c29f2efaab03f1","abstract_canon_sha256":"fd6ab0fb0f0b16aac20c1b062c23409fd24bd2b164e12abc539de09adbb2e18e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:50.983674Z","signature_b64":"UCK/lAvKOEglkYaARkEzlQu9vlW07ML7ezEQGwgZCxb97zfvnN7stx4Ro/9b/8BcovPETWfZt5kSMCfXrdoRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2dbf79d43c2a97f76cbe1835343d9fe9054f3279fc2f5a12259570cf84c7f6d","last_reissued_at":"2026-07-05T10:46:50.983152Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:50.983152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Aram Galstyan, Elan Markowitz, Greg Ver Steeg, Krupa Galiya","submitted_at":"2025-04-09T17:58:47Z","abstract_excerpt":"Knowledge graphs have emerged as a popular method for injecting up-to-date, factual knowledge into large language models (LLMs). This is typically achieved by converting the knowledge graph into text that the LLM can process in context. While multiple methods of encoding knowledge graphs have been proposed, the impact of this textualization process on LLM performance remains under-explored. We introduce KG-LLM-Bench, a comprehensive and extensible benchmark spanning five knowledge graph understanding tasks, and evaluate how different encoding strategies affect performance across various base m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07087","kind":"arxiv","version":1},"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/2504.07087/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":"2504.07087","created_at":"2026-07-05T10:46:50.983216+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07087v1","created_at":"2026-07-05T10:46:50.983216+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07087","created_at":"2026-07-05T10:46:50.983216+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LN7PHKDYKUX","created_at":"2026-07-05T10:46:50.983216+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LN7PHKDYKUX65WL","created_at":"2026-07-05T10:46:50.983216+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LN7PHKD","created_at":"2026-07-05T10:46:50.983216+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22636","citing_title":"A Multi-Source Framework for Relational Validation of Large Language Models Using Expert-Curated Encyclopedic Sources","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72","json":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72.json","graph_json":"https://pith.science/api/pith-number/2LN7PHKDYKUX65WL4GBVGQ6Z72/graph.json","events_json":"https://pith.science/api/pith-number/2LN7PHKDYKUX65WL4GBVGQ6Z72/events.json","paper":"https://pith.science/paper/2LN7PHKD"},"agent_actions":{"view_html":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72","download_json":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72.json","view_paper":"https://pith.science/paper/2LN7PHKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07087&json=true","fetch_graph":"https://pith.science/api/pith-number/2LN7PHKDYKUX65WL4GBVGQ6Z72/graph.json","fetch_events":"https://pith.science/api/pith-number/2LN7PHKDYKUX65WL4GBVGQ6Z72/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72/action/storage_attestation","attest_author":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72/action/author_attestation","sign_citation":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72/action/citation_signature","submit_replication":"https://pith.science/pith/2LN7PHKDYKUX65WL4GBVGQ6Z72/action/replication_record"}},"created_at":"2026-07-05T10:46:50.983216+00:00","updated_at":"2026-07-05T10:46:50.983216+00:00"}