{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNWQGOIPDC7RA5DZ64ZFAFJKK4","short_pith_number":"pith:HNWQGOIP","schema_version":"1.0","canonical_sha256":"3b6d03390f18bf107479f73250152a572f32d364cd4e30dea259c3b9aa5029bf","source":{"kind":"arxiv","id":"2406.16367","version":1},"attestation_state":"computed","paper":{"title":"On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chengyu Wang, Dongyang Li, Hui Xue, Junbing Yan, Jun Huang, Longtao Huang, Taolin Zhang, Xiaofeng He","submitted_at":"2024-06-24T07:17:59Z","abstract_excerpt":"Retrieval augmented generation (RAG) exhibits outstanding performance in promoting the knowledge capabilities of large language models (LLMs) with retrieved documents related to user queries. However, RAG only focuses on improving the response quality of LLMs via enhancing queries indiscriminately with retrieved information, paying little attention to what type of knowledge LLMs really need to answer original queries more accurately. In this paper, we suggest that long-tail knowledge is crucial for RAG as LLMs have already remembered common world knowledge during large-scale pre-training. Base"},"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":"2406.16367","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2024-06-24T07:17:59Z","cross_cats_sorted":[],"title_canon_sha256":"86ba384a73077ae9a6df113863526deabaf6c3476de3943f0f9074bf2c0691d9","abstract_canon_sha256":"4e532ac2fc1c11f41909de8b7619eaaeae523e20b9e721f204435ddd088da24c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:57.475865Z","signature_b64":"8yV/et62dVpkp0xWt0zKykJOnwrM9JjIfb658bTTnNoWygqoW7xoxkLz3bZYKFfs5RMV+KXQ97gBj9CRc98hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b6d03390f18bf107479f73250152a572f32d364cd4e30dea259c3b9aa5029bf","last_reissued_at":"2026-07-05T08:35:57.475399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:57.475399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Role of Long-tail Knowledge in Retrieval Augmented Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chengyu Wang, Dongyang Li, Hui Xue, Junbing Yan, Jun Huang, Longtao Huang, Taolin Zhang, Xiaofeng He","submitted_at":"2024-06-24T07:17:59Z","abstract_excerpt":"Retrieval augmented generation (RAG) exhibits outstanding performance in promoting the knowledge capabilities of large language models (LLMs) with retrieved documents related to user queries. However, RAG only focuses on improving the response quality of LLMs via enhancing queries indiscriminately with retrieved information, paying little attention to what type of knowledge LLMs really need to answer original queries more accurately. In this paper, we suggest that long-tail knowledge is crucial for RAG as LLMs have already remembered common world knowledge during large-scale pre-training. Base"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16367","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/2406.16367/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":"2406.16367","created_at":"2026-07-05T08:35:57.475458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.16367v1","created_at":"2026-07-05T08:35:57.475458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16367","created_at":"2026-07-05T08:35:57.475458+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNWQGOIPDC7R","created_at":"2026-07-05T08:35:57.475458+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNWQGOIPDC7RA5DZ","created_at":"2026-07-05T08:35:57.475458+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNWQGOIP","created_at":"2026-07-05T08:35:57.475458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02870","citing_title":"Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models","ref_index":177,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4","json":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4.json","graph_json":"https://pith.science/api/pith-number/HNWQGOIPDC7RA5DZ64ZFAFJKK4/graph.json","events_json":"https://pith.science/api/pith-number/HNWQGOIPDC7RA5DZ64ZFAFJKK4/events.json","paper":"https://pith.science/paper/HNWQGOIP"},"agent_actions":{"view_html":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4","download_json":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4.json","view_paper":"https://pith.science/paper/HNWQGOIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.16367&json=true","fetch_graph":"https://pith.science/api/pith-number/HNWQGOIPDC7RA5DZ64ZFAFJKK4/graph.json","fetch_events":"https://pith.science/api/pith-number/HNWQGOIPDC7RA5DZ64ZFAFJKK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4/action/storage_attestation","attest_author":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4/action/author_attestation","sign_citation":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4/action/citation_signature","submit_replication":"https://pith.science/pith/HNWQGOIPDC7RA5DZ64ZFAFJKK4/action/replication_record"}},"created_at":"2026-07-05T08:35:57.475458+00:00","updated_at":"2026-07-05T08:35:57.475458+00:00"}