{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2XBEGEMLVWOZZEU67Q75DY2P2D","short_pith_number":"pith:2XBEGEML","schema_version":"1.0","canonical_sha256":"d5c243118bad9d9c929efc3fd1e34fd0ef4fc218355b6bff97c1f3815f8bb60b","source":{"kind":"arxiv","id":"2410.02825","version":2},"attestation_state":"computed","paper":{"title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Alex Goncalves, Arya Pudota, Chenhao Fang, Derek Larson, Gabriel Forgues, Herv\\'e Robert, Rajeev Rao, Shitong Zhu, Sophie Zeng, Wendy Summer, Yanqing Peng, Yuriy Hulovatyy","submitted_at":"2024-09-30T20:32:29Z","abstract_excerpt":"This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model with a privacy-specific knowledge base and then augment it with a semantic RAG layer. Our evaluations demonstrate that this approach enhances the model performance (as much as doubled metrics compared to out-of-box LLM) in handling privacy-related queries, by grounding responses with factual information which reduces inaccuracies."},"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":"2410.02825","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T20:32:29Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"c1135278c32caf57d59f49dbb520ae912dbf248e038b5fdd75ba8e950d149892","abstract_canon_sha256":"340beb23dd45b1e36ec599b47c6be50b5dbb1df67d3d636aeff31c593ea66104"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:32.702947Z","signature_b64":"hQNu5susFnPAMRxfyI6tOTbAv/0Qbc3/f+F11m7VMDbZpMIkyw89YjnOJO5yh2WcbzRpNS5ncS6xWoHbH0ksCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5c243118bad9d9c929efc3fd1e34fd0ef4fc218355b6bff97c1f3815f8bb60b","last_reissued_at":"2026-07-05T09:19:32.702448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:32.702448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ingest-And-Ground: Dispelling Hallucinations from Continually-Pretrained LLMs with RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.CL","authors_text":"Alex Goncalves, Arya Pudota, Chenhao Fang, Derek Larson, Gabriel Forgues, Herv\\'e Robert, Rajeev Rao, Shitong Zhu, Sophie Zeng, Wendy Summer, Yanqing Peng, Yuriy Hulovatyy","submitted_at":"2024-09-30T20:32:29Z","abstract_excerpt":"This paper presents new methods that have the potential to improve privacy process efficiency with LLM and RAG. To reduce hallucination, we continually pre-train the base LLM model with a privacy-specific knowledge base and then augment it with a semantic RAG layer. Our evaluations demonstrate that this approach enhances the model performance (as much as doubled metrics compared to out-of-box LLM) in handling privacy-related queries, by grounding responses with factual information which reduces inaccuracies."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02825","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/2410.02825/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":"2410.02825","created_at":"2026-07-05T09:19:32.702509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02825v2","created_at":"2026-07-05T09:19:32.702509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02825","created_at":"2026-07-05T09:19:32.702509+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XBEGEMLVWOZ","created_at":"2026-07-05T09:19:32.702509+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XBEGEMLVWOZZEU6","created_at":"2026-07-05T09:19:32.702509+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XBEGEML","created_at":"2026-07-05T09:19:32.702509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11141","citing_title":"Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D","json":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D.json","graph_json":"https://pith.science/api/pith-number/2XBEGEMLVWOZZEU67Q75DY2P2D/graph.json","events_json":"https://pith.science/api/pith-number/2XBEGEMLVWOZZEU67Q75DY2P2D/events.json","paper":"https://pith.science/paper/2XBEGEML"},"agent_actions":{"view_html":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D","download_json":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D.json","view_paper":"https://pith.science/paper/2XBEGEML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02825&json=true","fetch_graph":"https://pith.science/api/pith-number/2XBEGEMLVWOZZEU67Q75DY2P2D/graph.json","fetch_events":"https://pith.science/api/pith-number/2XBEGEMLVWOZZEU67Q75DY2P2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D/action/storage_attestation","attest_author":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D/action/author_attestation","sign_citation":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D/action/citation_signature","submit_replication":"https://pith.science/pith/2XBEGEMLVWOZZEU67Q75DY2P2D/action/replication_record"}},"created_at":"2026-07-05T09:19:32.702509+00:00","updated_at":"2026-07-05T09:19:32.702509+00:00"}