{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AYCRFXG3GKVA33T6KYXHWTEGFL","short_pith_number":"pith:AYCRFXG3","schema_version":"1.0","canonical_sha256":"060512dcdb32aa0dee7e562e7b4c862af59f8bd9f3b68b6160d30597fd56b29a","source":{"kind":"arxiv","id":"2506.06704","version":1},"attestation_state":"computed","paper":{"title":"Dynamic and Parametric Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jingtao Zhan, Qian Dong, Qingyao Ai, Weihang Su, Yiqun Liu","submitted_at":"2025-06-07T07:59:33Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a foundational paradigm for equipping large language models (LLMs) with external knowledge, playing a critical role in information retrieval and knowledge-intensive applications. However, conventional RAG systems typically adopt a static retrieve-then-generate pipeline and rely on in-context knowledge injection, which can be suboptimal for complex tasks that require multihop reasoning, adaptive information access, and deeper integration of external knowledge. Motivated by these limitations, the research community has moved beyond static retrieval"},"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":"2506.06704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-07T07:59:33Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"ed2a5aa01b81cd8683c5a655107857fa52c25348438098873d8850b1670c9720","abstract_canon_sha256":"edd93cb8f1b0d059195b5c320ee8656d784190e03feb43d801843db7fcb6dabc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:54.325366Z","signature_b64":"xTL/ZeiXbfCzUtUm5KmyVk5h90Wc54gJ9aHffBasYIa6l7UINDDwtTA0gFGg8Mlz+BOpoXQR0nynLphjCqdqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"060512dcdb32aa0dee7e562e7b4c862af59f8bd9f3b68b6160d30597fd56b29a","last_reissued_at":"2026-07-05T11:17:54.324835Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:54.324835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic and Parametric Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Jingtao Zhan, Qian Dong, Qingyao Ai, Weihang Su, Yiqun Liu","submitted_at":"2025-06-07T07:59:33Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has become a foundational paradigm for equipping large language models (LLMs) with external knowledge, playing a critical role in information retrieval and knowledge-intensive applications. However, conventional RAG systems typically adopt a static retrieve-then-generate pipeline and rely on in-context knowledge injection, which can be suboptimal for complex tasks that require multihop reasoning, adaptive information access, and deeper integration of external knowledge. Motivated by these limitations, the research community has moved beyond static retrieval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06704","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/2506.06704/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":"2506.06704","created_at":"2026-07-05T11:17:54.324901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06704v1","created_at":"2026-07-05T11:17:54.324901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06704","created_at":"2026-07-05T11:17:54.324901+00:00"},{"alias_kind":"pith_short_12","alias_value":"AYCRFXG3GKVA","created_at":"2026-07-05T11:17:54.324901+00:00"},{"alias_kind":"pith_short_16","alias_value":"AYCRFXG3GKVA33T6","created_at":"2026-07-05T11:17:54.324901+00:00"},{"alias_kind":"pith_short_8","alias_value":"AYCRFXG3","created_at":"2026-07-05T11:17:54.324901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17041","citing_title":"MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24894","citing_title":"RWGBench: Evaluating Scholarly Positioning in Related Work Generation","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL","json":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL.json","graph_json":"https://pith.science/api/pith-number/AYCRFXG3GKVA33T6KYXHWTEGFL/graph.json","events_json":"https://pith.science/api/pith-number/AYCRFXG3GKVA33T6KYXHWTEGFL/events.json","paper":"https://pith.science/paper/AYCRFXG3"},"agent_actions":{"view_html":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL","download_json":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL.json","view_paper":"https://pith.science/paper/AYCRFXG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06704&json=true","fetch_graph":"https://pith.science/api/pith-number/AYCRFXG3GKVA33T6KYXHWTEGFL/graph.json","fetch_events":"https://pith.science/api/pith-number/AYCRFXG3GKVA33T6KYXHWTEGFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL/action/storage_attestation","attest_author":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL/action/author_attestation","sign_citation":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL/action/citation_signature","submit_replication":"https://pith.science/pith/AYCRFXG3GKVA33T6KYXHWTEGFL/action/replication_record"}},"created_at":"2026-07-05T11:17:54.324901+00:00","updated_at":"2026-07-05T11:17:54.324901+00:00"}