{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:EAIMZ3YM2TTWAYKU4XEW2Y557A","short_pith_number":"pith:EAIMZ3YM","schema_version":"1.0","canonical_sha256":"2010ccef0cd4e7606154e5c96d63bdf807f9553b79e790269a9adbb8bfb7df35","source":{"kind":"arxiv","id":"2406.12534","version":4},"attestation_state":"computed","paper":{"title":"Unified Active Retrieval for Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Yan, Linyang Li, Qinyuan Cheng, Qin Zhu, Shimin Li, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Yunfan Shao, Zhangyue Yin","submitted_at":"2024-06-18T12:09:02Z","abstract_excerpt":"In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challen"},"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":"2406.12534","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T12:09:02Z","cross_cats_sorted":[],"title_canon_sha256":"66572d7ffb54484e56a27a35c3510e944923fe724a64e5fef611b24639e58c90","abstract_canon_sha256":"cddb36e1676a9e9762c82019c14af1005cf82199baaa7a05ac049d4c6b963e6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:11.840996Z","signature_b64":"M2xpx2ZLnO52TA6g2SgxwK0/kjbT3nHCBrxrttBm+0cioQ9JjN40GDz08aJ/5auxsC0zOiYy+0bV1JWQrvRjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2010ccef0cd4e7606154e5c96d63bdf807f9553b79e790269a9adbb8bfb7df35","last_reissued_at":"2026-07-05T09:15:11.840577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:11.840577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Active Retrieval for Retrieval Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Yan, Linyang Li, Qinyuan Cheng, Qin Zhu, Shimin Li, Tianxiang Sun, Xiaonan Li, Xipeng Qiu, Yunfan Shao, Zhangyue Yin","submitted_at":"2024-06-18T12:09:02Z","abstract_excerpt":"In Retrieval-Augmented Generation (RAG), retrieval is not always helpful and applying it to every instruction is sub-optimal. Therefore, determining whether to retrieve is crucial for RAG, which is usually referred to as Active Retrieval. However, existing active retrieval methods face two challenges: 1. They usually rely on a single criterion, which struggles with handling various types of instructions. 2. They depend on specialized and highly differentiated procedures, and thus combining them makes the RAG system more complicated and leads to higher response latency. To address these challen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12534","kind":"arxiv","version":4},"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/2406.12534/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":"2406.12534","created_at":"2026-07-05T09:15:11.840630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12534v4","created_at":"2026-07-05T09:15:11.840630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12534","created_at":"2026-07-05T09:15:11.840630+00:00"},{"alias_kind":"pith_short_12","alias_value":"EAIMZ3YM2TTW","created_at":"2026-07-05T09:15:11.840630+00:00"},{"alias_kind":"pith_short_16","alias_value":"EAIMZ3YM2TTWAYKU","created_at":"2026-07-05T09:15:11.840630+00:00"},{"alias_kind":"pith_short_8","alias_value":"EAIMZ3YM","created_at":"2026-07-05T09:15:11.840630+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.19827","citing_title":"When Iterative RAG Beats Ideal Evidence: A Diagnostic Study in Scientific Multi-hop Question Answering","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A","json":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A.json","graph_json":"https://pith.science/api/pith-number/EAIMZ3YM2TTWAYKU4XEW2Y557A/graph.json","events_json":"https://pith.science/api/pith-number/EAIMZ3YM2TTWAYKU4XEW2Y557A/events.json","paper":"https://pith.science/paper/EAIMZ3YM"},"agent_actions":{"view_html":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A","download_json":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A.json","view_paper":"https://pith.science/paper/EAIMZ3YM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12534&json=true","fetch_graph":"https://pith.science/api/pith-number/EAIMZ3YM2TTWAYKU4XEW2Y557A/graph.json","fetch_events":"https://pith.science/api/pith-number/EAIMZ3YM2TTWAYKU4XEW2Y557A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A/action/storage_attestation","attest_author":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A/action/author_attestation","sign_citation":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A/action/citation_signature","submit_replication":"https://pith.science/pith/EAIMZ3YM2TTWAYKU4XEW2Y557A/action/replication_record"}},"created_at":"2026-07-05T09:15:11.840630+00:00","updated_at":"2026-07-05T09:15:11.840630+00:00"}