{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIFZOF72OG7QIVSK5RGZLG5HXG","short_pith_number":"pith:JIFZOF72","schema_version":"1.0","canonical_sha256":"4a0b9717fa71bf04564aec4d959ba7b99d59f4f93e3818a72df098e1509e4186","source":{"kind":"arxiv","id":"2505.12731","version":2},"attestation_state":"computed","paper":{"title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Ou, Jinyu Guo, Libo Qin, Shuaihong Jiang, Shunyu Yao, Wenhong Tian, Zhaokun Wang","submitted_at":"2025-05-19T05:39:38Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated quality through multiple interactions with external knowledge bases. Despite its effectiveness, A-RAG exacerbates the pre-existing efficiency challenges inherent in RAG, which are attributable to its reliance on multiple iterations of generation. Existing A-RAG approaches process all retrieved contents from scratch. However, they ignore the situation where there "},"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":"2505.12731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T05:39:38Z","cross_cats_sorted":[],"title_canon_sha256":"967b14744c4902bd696753f7bcefdb4bd517ebbaa8d925c01249fd9178d03466","abstract_canon_sha256":"dd54f65c492ee79b276646d36b3df79e61f4aaa7d9201eb0b68d5cb72e144d2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:13.901370Z","signature_b64":"/9m/hxDIQdEF6a7fm+OAE747PhQ1yODL8+a9nRbgQwO166zajGIzSA/HP+bICbbHN/4RdfQIGmvfawys1Q8HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0b9717fa71bf04564aec4d959ba7b99d59f4f93e3818a72df098e1509e4186","last_reissued_at":"2026-07-05T11:09:13.900860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:13.900860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Jie Ou, Jinyu Guo, Libo Qin, Shuaihong Jiang, Shunyu Yao, Wenhong Tian, Zhaokun Wang","submitted_at":"2025-05-19T05:39:38Z","abstract_excerpt":"Retrieval-augmented generation (RAG) has emerged as a pivotal method for expanding the knowledge of large language models. To handle complex queries more effectively, researchers developed Adaptive-RAG (A-RAG) to enhance the generated quality through multiple interactions with external knowledge bases. Despite its effectiveness, A-RAG exacerbates the pre-existing efficiency challenges inherent in RAG, which are attributable to its reliance on multiple iterations of generation. Existing A-RAG approaches process all retrieved contents from scratch. However, they ignore the situation where there "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12731","kind":"arxiv","version":2},"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/2505.12731/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":"2505.12731","created_at":"2026-07-05T11:09:13.900918+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12731v2","created_at":"2026-07-05T11:09:13.900918+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12731","created_at":"2026-07-05T11:09:13.900918+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIFZOF72OG7Q","created_at":"2026-07-05T11:09:13.900918+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIFZOF72OG7QIVSK","created_at":"2026-07-05T11:09:13.900918+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIFZOF72","created_at":"2026-07-05T11:09:13.900918+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/JIFZOF72OG7QIVSK5RGZLG5HXG","json":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG.json","graph_json":"https://pith.science/api/pith-number/JIFZOF72OG7QIVSK5RGZLG5HXG/graph.json","events_json":"https://pith.science/api/pith-number/JIFZOF72OG7QIVSK5RGZLG5HXG/events.json","paper":"https://pith.science/paper/JIFZOF72"},"agent_actions":{"view_html":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG","download_json":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG.json","view_paper":"https://pith.science/paper/JIFZOF72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12731&json=true","fetch_graph":"https://pith.science/api/pith-number/JIFZOF72OG7QIVSK5RGZLG5HXG/graph.json","fetch_events":"https://pith.science/api/pith-number/JIFZOF72OG7QIVSK5RGZLG5HXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG/action/storage_attestation","attest_author":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG/action/author_attestation","sign_citation":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG/action/citation_signature","submit_replication":"https://pith.science/pith/JIFZOF72OG7QIVSK5RGZLG5HXG/action/replication_record"}},"created_at":"2026-07-05T11:09:13.900918+00:00","updated_at":"2026-07-05T11:09:13.900918+00:00"}