{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MSSAA4RUBSHGVTDCXQQEIRICYD","short_pith_number":"pith:MSSAA4RU","schema_version":"1.0","canonical_sha256":"64a40072340c8e6acc62bc20444502c0c8e8f7bbf7f761489bc47afb8795e74f","source":{"kind":"arxiv","id":"2412.15235","version":1},"attestation_state":"computed","paper":{"title":"OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kartik Sharma, Peeyush Kumar, Yunqing Li","submitted_at":"2024-12-12T01:21:03Z","abstract_excerpt":"This paper presents OG-RAG, an Ontology-Grounded Retrieval Augmented Generation method designed to enhance LLM-generated responses by anchoring retrieval processes in domain-specific ontologies. While LLMs are widely used for tasks like question answering and search, they struggle to adapt to specialized knowledge, such as industrial workflows or knowledge work, without expensive fine-tuning or sub-optimal retrieval methods. Existing retrieval-augmented models, such as RAG, offer improvements but fail to account for structured domain knowledge, leading to suboptimal context generation. Ontolog"},"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":"2412.15235","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T01:21:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8ec3cf56468771a0a2a152977356f654cf4ff4b51cbe1b1bbbc7d00a4a9b20d0","abstract_canon_sha256":"1cb45ab2015f3f7fd15c5021d2921f7a7a33a67b6fde62dec69b339e1ca46c22"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:52:00.156004Z","signature_b64":"nqAdrSiIDPf5YMU+64m6JhRXsc4GRqWpO1UrPFrRmJl8m7SfFsMvrqJiRcvoaL70t6R/IPmfEp7LXX5FgwUgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64a40072340c8e6acc62bc20444502c0c8e8f7bbf7f761489bc47afb8795e74f","last_reissued_at":"2026-07-05T09:52:00.155588Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:52:00.155588Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Kartik Sharma, Peeyush Kumar, Yunqing Li","submitted_at":"2024-12-12T01:21:03Z","abstract_excerpt":"This paper presents OG-RAG, an Ontology-Grounded Retrieval Augmented Generation method designed to enhance LLM-generated responses by anchoring retrieval processes in domain-specific ontologies. While LLMs are widely used for tasks like question answering and search, they struggle to adapt to specialized knowledge, such as industrial workflows or knowledge work, without expensive fine-tuning or sub-optimal retrieval methods. Existing retrieval-augmented models, such as RAG, offer improvements but fail to account for structured domain knowledge, leading to suboptimal context generation. Ontolog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15235","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/2412.15235/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":"2412.15235","created_at":"2026-07-05T09:52:00.155643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15235v1","created_at":"2026-07-05T09:52:00.155643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15235","created_at":"2026-07-05T09:52:00.155643+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSSAA4RUBSHG","created_at":"2026-07-05T09:52:00.155643+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSSAA4RUBSHGVTDC","created_at":"2026-07-05T09:52:00.155643+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSSAA4RU","created_at":"2026-07-05T09:52:00.155643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13669","citing_title":"Agents-K1: Towards Agent-native Knowledge Orchestration","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00610","citing_title":"MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22911","citing_title":"ThermoLLM: Thermodynamics-Aware HVAC Control with Spatial-Semantic Knowledge Graph","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18913","citing_title":"LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08256","citing_title":"HyperMem: Hypergraph Memory for Long-Term Conversations","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD","json":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD.json","graph_json":"https://pith.science/api/pith-number/MSSAA4RUBSHGVTDCXQQEIRICYD/graph.json","events_json":"https://pith.science/api/pith-number/MSSAA4RUBSHGVTDCXQQEIRICYD/events.json","paper":"https://pith.science/paper/MSSAA4RU"},"agent_actions":{"view_html":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD","download_json":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD.json","view_paper":"https://pith.science/paper/MSSAA4RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15235&json=true","fetch_graph":"https://pith.science/api/pith-number/MSSAA4RUBSHGVTDCXQQEIRICYD/graph.json","fetch_events":"https://pith.science/api/pith-number/MSSAA4RUBSHGVTDCXQQEIRICYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD/action/storage_attestation","attest_author":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD/action/author_attestation","sign_citation":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD/action/citation_signature","submit_replication":"https://pith.science/pith/MSSAA4RUBSHGVTDCXQQEIRICYD/action/replication_record"}},"created_at":"2026-07-05T09:52:00.155643+00:00","updated_at":"2026-07-05T09:52:00.155643+00:00"}