{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PANDPR6WBR4PTDMHNYGRBFK4H6","short_pith_number":"pith:PANDPR6W","schema_version":"1.0","canonical_sha256":"781a37c7d60c78f98d876e0d10955c3fb6528b3f8f93d2469dfe62f4d6d34d8a","source":{"kind":"arxiv","id":"2410.02721","version":1},"attestation_state":"computed","paper":{"title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SE"],"primary_cat":"cs.CL","authors_text":"Boian S. Alexandrov, Charles Nicholas, Cynthia Matuszek, George Tompkins, Kim {\\O}. Rasmussen, Maksim E. Eren, Manish Bhattarai, Nicholas Solovyev, Ryan C. Barron, Selma Wanna, Ves Grantcharov","submitted_at":"2024-10-03T17:40:55Z","abstract_excerpt":"Large Language Models (LLMs) are pre-trained on large-scale corpora and excel in numerous general natural language processing (NLP) tasks, such as question answering (QA). Despite their advanced language capabilities, when it comes to domain-specific and knowledge-intensive tasks, LLMs suffer from hallucinations, knowledge cut-offs, and lack of knowledge attributions. Additionally, fine tuning LLMs' intrinsic knowledge to highly specific domains is an expensive and time consuming process. The retrieval-augmented generation (RAG) process has recently emerged as a method capable of optimization "},"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":"2410.02721","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:40:55Z","cross_cats_sorted":["cs.AI","cs.IR","cs.SE"],"title_canon_sha256":"585d416137220429b9c40181e65e96dc4b30dc9087cba32e753f09d3594d24dc","abstract_canon_sha256":"18dbe4ff8196fb9d4f6849f9a56d012363e76648923ec06e505866481cd7dc49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:24.458694Z","signature_b64":"Oz1NjIN/c+bCRfeFhKsQ2s2s76I85abL6kaMgia5xRZP6EhuuTYgTTWJ1FbAk26yGgT53Ia3og1WszXcf3HZBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"781a37c7d60c78f98d876e0d10955c3fb6528b3f8f93d2469dfe62f4d6d34d8a","last_reissued_at":"2026-07-05T09:15:24.458164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:24.458164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Specific Retrieval-Augmented Generation Using Vector Stores, Knowledge Graphs, and Tensor Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.SE"],"primary_cat":"cs.CL","authors_text":"Boian S. Alexandrov, Charles Nicholas, Cynthia Matuszek, George Tompkins, Kim {\\O}. Rasmussen, Maksim E. Eren, Manish Bhattarai, Nicholas Solovyev, Ryan C. Barron, Selma Wanna, Ves Grantcharov","submitted_at":"2024-10-03T17:40:55Z","abstract_excerpt":"Large Language Models (LLMs) are pre-trained on large-scale corpora and excel in numerous general natural language processing (NLP) tasks, such as question answering (QA). Despite their advanced language capabilities, when it comes to domain-specific and knowledge-intensive tasks, LLMs suffer from hallucinations, knowledge cut-offs, and lack of knowledge attributions. Additionally, fine tuning LLMs' intrinsic knowledge to highly specific domains is an expensive and time consuming process. The retrieval-augmented generation (RAG) process has recently emerged as a method capable of optimization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02721","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/2410.02721/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":"2410.02721","created_at":"2026-07-05T09:15:24.458223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02721v1","created_at":"2026-07-05T09:15:24.458223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02721","created_at":"2026-07-05T09:15:24.458223+00:00"},{"alias_kind":"pith_short_12","alias_value":"PANDPR6WBR4P","created_at":"2026-07-05T09:15:24.458223+00:00"},{"alias_kind":"pith_short_16","alias_value":"PANDPR6WBR4PTDMH","created_at":"2026-07-05T09:15:24.458223+00:00"},{"alias_kind":"pith_short_8","alias_value":"PANDPR6W","created_at":"2026-07-05T09:15:24.458223+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6","json":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6.json","graph_json":"https://pith.science/api/pith-number/PANDPR6WBR4PTDMHNYGRBFK4H6/graph.json","events_json":"https://pith.science/api/pith-number/PANDPR6WBR4PTDMHNYGRBFK4H6/events.json","paper":"https://pith.science/paper/PANDPR6W"},"agent_actions":{"view_html":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6","download_json":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6.json","view_paper":"https://pith.science/paper/PANDPR6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02721&json=true","fetch_graph":"https://pith.science/api/pith-number/PANDPR6WBR4PTDMHNYGRBFK4H6/graph.json","fetch_events":"https://pith.science/api/pith-number/PANDPR6WBR4PTDMHNYGRBFK4H6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6/action/storage_attestation","attest_author":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6/action/author_attestation","sign_citation":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6/action/citation_signature","submit_replication":"https://pith.science/pith/PANDPR6WBR4PTDMHNYGRBFK4H6/action/replication_record"}},"created_at":"2026-07-05T09:15:24.458223+00:00","updated_at":"2026-07-05T09:15:24.458223+00:00"}