{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5K32PKUKKICIYUDJK6T5CXB2GC","short_pith_number":"pith:5K32PKUK","schema_version":"1.0","canonical_sha256":"eab7a7aa8a52048c506957a7d15c3a30a1b0d2650d31520f4b9b3be0718df392","source":{"kind":"arxiv","id":"2501.15915","version":1},"attestation_state":"computed","paper":{"title":"Parametric Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Changyue Wang, Hongning Wang, Junxi Yan, Qingyao Ai, Weihang Su, Yichen Tang, Yiqun Liu, Yujia Zhou, Ziyi Ye","submitted_at":"2025-01-27T10:04:49Z","abstract_excerpt":"Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of LLMs to guide their generation process, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant doc"},"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":"2501.15915","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T10:04:49Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"1327a845c3b7c1ffbb743476d39fddf99f25cae702e73767ef5939e5109cee01","abstract_canon_sha256":"1ee6196e4d87682ce1ca32cf9fa20e0fe2c17f6cbe7f4e18b41d329b3f67a6fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:52.001452Z","signature_b64":"T9+leWFDahBqYdEOGe20vixqDQsPrYEbvhfpImFA7J5u+vRkjGqHtMVbVhl/Oz6bdi06eUpalYxMpdse3BU+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eab7a7aa8a52048c506957a7d15c3a30a1b0d2650d31520f4b9b3be0718df392","last_reissued_at":"2026-07-05T10:05:52.000985Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:52.000985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parametric Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Changyue Wang, Hongning Wang, Junxi Yan, Qingyao Ai, Weihang Su, Yichen Tang, Yiqun Liu, Yujia Zhou, Ziyi Ye","submitted_at":"2025-01-27T10:04:49Z","abstract_excerpt":"Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of LLMs to guide their generation process, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant doc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15915","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/2501.15915/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":"2501.15915","created_at":"2026-07-05T10:05:52.001044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15915v1","created_at":"2026-07-05T10:05:52.001044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15915","created_at":"2026-07-05T10:05:52.001044+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K32PKUKKICI","created_at":"2026-07-05T10:05:52.001044+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K32PKUKKICIYUDJ","created_at":"2026-07-05T10:05:52.001044+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K32PKUK","created_at":"2026-07-05T10:05:52.001044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19172","citing_title":"User as Engram: Internalizing Per-User Memory as Local Parametric Edits","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03979","citing_title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","ref_index":122,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32002","citing_title":"Self-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QA","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2507.03724","citing_title":"MemOS: A Memory OS for AI System","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02011","citing_title":"Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC","json":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC.json","graph_json":"https://pith.science/api/pith-number/5K32PKUKKICIYUDJK6T5CXB2GC/graph.json","events_json":"https://pith.science/api/pith-number/5K32PKUKKICIYUDJK6T5CXB2GC/events.json","paper":"https://pith.science/paper/5K32PKUK"},"agent_actions":{"view_html":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC","download_json":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC.json","view_paper":"https://pith.science/paper/5K32PKUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15915&json=true","fetch_graph":"https://pith.science/api/pith-number/5K32PKUKKICIYUDJK6T5CXB2GC/graph.json","fetch_events":"https://pith.science/api/pith-number/5K32PKUKKICIYUDJK6T5CXB2GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC/action/storage_attestation","attest_author":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC/action/author_attestation","sign_citation":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC/action/citation_signature","submit_replication":"https://pith.science/pith/5K32PKUKKICIYUDJK6T5CXB2GC/action/replication_record"}},"created_at":"2026-07-05T10:05:52.001044+00:00","updated_at":"2026-07-05T10:05:52.001044+00:00"}