{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:35ARXFJHVI33DTB5NZKK2OSJ4B","short_pith_number":"pith:35ARXFJH","schema_version":"1.0","canonical_sha256":"df411b9527aa37b1cc3d6e54ad3a49e04af2b00401bbbbc7113867539d5d2f70","source":{"kind":"arxiv","id":"2407.03627","version":5},"attestation_state":"computed","paper":{"title":"DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jong C. Park, SeungYoon Han, Soyeong Jeong, Sukmin Cho, Taeho Hwang","submitted_at":"2024-07-04T04:30:04Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still struggle with generating non-factual responses due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) systems address this issue by incorporating external knowledge with a retrieval module. Despite their successes, however, current RAG systems face challenges with retrieval failures and the limited ability of LLMs to filter out irrelevant information. Therefore, in this work, we propose DSLR (D"},"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":"2407.03627","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-04T04:30:04Z","cross_cats_sorted":[],"title_canon_sha256":"bdf4e49d637ba4a48104fcec7f640be35d3778e966928cba907867b51d3f2a61","abstract_canon_sha256":"c25aa79520e605a1575d0a258deec222304e1b59f87464a6b08459c56e61b35c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:04:37.470515Z","signature_b64":"nfiP55hfP1FD3jCU6m0ABtBlf2/PYcOUNjL8Dz+JVVa+9XQRcqKNDs+EY0FcU/oAFsehUyKpmi9toOyPg+jECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df411b9527aa37b1cc3d6e54ad3a49e04af2b00401bbbbc7113867539d5d2f70","last_reissued_at":"2026-07-05T09:04:37.470109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:04:37.470109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DSLR: Document Refinement with Sentence-Level Re-ranking and Reconstruction to Enhance Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jong C. Park, SeungYoon Han, Soyeong Jeong, Sukmin Cho, Taeho Hwang","submitted_at":"2024-07-04T04:30:04Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have significantly improved their performance across various Natural Language Processing (NLP) tasks. However, LLMs still struggle with generating non-factual responses due to limitations in their parametric memory. Retrieval-Augmented Generation (RAG) systems address this issue by incorporating external knowledge with a retrieval module. Despite their successes, however, current RAG systems face challenges with retrieval failures and the limited ability of LLMs to filter out irrelevant information. Therefore, in this work, we propose DSLR (D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03627","kind":"arxiv","version":5},"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/2407.03627/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":"2407.03627","created_at":"2026-07-05T09:04:37.470166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.03627v5","created_at":"2026-07-05T09:04:37.470166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03627","created_at":"2026-07-05T09:04:37.470166+00:00"},{"alias_kind":"pith_short_12","alias_value":"35ARXFJHVI33","created_at":"2026-07-05T09:04:37.470166+00:00"},{"alias_kind":"pith_short_16","alias_value":"35ARXFJHVI33DTB5","created_at":"2026-07-05T09:04:37.470166+00:00"},{"alias_kind":"pith_short_8","alias_value":"35ARXFJH","created_at":"2026-07-05T09:04:37.470166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01079","citing_title":"MobileRAG: A Fast, Memory-Efficient, and Energy-Efficient Method for On-Device RAG","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B","json":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B.json","graph_json":"https://pith.science/api/pith-number/35ARXFJHVI33DTB5NZKK2OSJ4B/graph.json","events_json":"https://pith.science/api/pith-number/35ARXFJHVI33DTB5NZKK2OSJ4B/events.json","paper":"https://pith.science/paper/35ARXFJH"},"agent_actions":{"view_html":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B","download_json":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B.json","view_paper":"https://pith.science/paper/35ARXFJH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.03627&json=true","fetch_graph":"https://pith.science/api/pith-number/35ARXFJHVI33DTB5NZKK2OSJ4B/graph.json","fetch_events":"https://pith.science/api/pith-number/35ARXFJHVI33DTB5NZKK2OSJ4B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B/action/storage_attestation","attest_author":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B/action/author_attestation","sign_citation":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B/action/citation_signature","submit_replication":"https://pith.science/pith/35ARXFJHVI33DTB5NZKK2OSJ4B/action/replication_record"}},"created_at":"2026-07-05T09:04:37.470166+00:00","updated_at":"2026-07-05T09:04:37.470166+00:00"}