{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G7FHE7EOWSV5NA5WKRZZRFVCFV","short_pith_number":"pith:G7FHE7EO","schema_version":"1.0","canonical_sha256":"37ca727c8eb4abd683b654739896a22d6b100546d4a4baa346f9a5e40490ed29","source":{"kind":"arxiv","id":"2505.10413","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanting Dong, Jiajie Jin, Qi Ye, Xiaoxi Li, Yongkang Wu, Yutao Zhu, Yuyao Zhang, Zhicheng Dou, Zhonghua Li","submitted_at":"2025-05-15T15:34:15Z","abstract_excerpt":"Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in vario"},"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":"2505.10413","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-15T15:34:15Z","cross_cats_sorted":[],"title_canon_sha256":"9dcba23593e2fb7d218f4035434d2bb3ff685e59474c3a002e69106be9483063","abstract_canon_sha256":"09a1d6a36060a2b3203f49b526a38156a1b8026cf608d1a3907b2e92d2aa88af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:38.053712Z","signature_b64":"OVGCaJzfoWa9avLqvVKn2qPNfDFjQxe/3kOR1EUQ0b2VOuPQwI7PB8w+sM/ShNexsR+1MmJGW+2XJKGSiottBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"37ca727c8eb4abd683b654739896a22d6b100546d4a4baa346f9a5e40490ed29","last_reissued_at":"2026-07-05T11:03:38.053227Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:38.053227Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Document Refinement for Long-context Retrieval-augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guanting Dong, Jiajie Jin, Qi Ye, Xiaoxi Li, Yongkang Wu, Yutao Zhu, Yuyao Zhang, Zhicheng Dou, Zhonghua Li","submitted_at":"2025-05-15T15:34:15Z","abstract_excerpt":"Real-world RAG applications often encounter long-context input scenarios, where redundant information and noise results in higher inference costs and reduced performance. To address these challenges, we propose LongRefiner, an efficient plug-and-play refiner that leverages the inherent structural characteristics of long documents. LongRefiner employs dual-level query analysis, hierarchical document structuring, and adaptive refinement through multi-task learning on a single foundation model. Experiments on seven QA datasets demonstrate that LongRefiner achieves competitive performance in vario"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10413","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/2505.10413/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":"2505.10413","created_at":"2026-07-05T11:03:38.053284+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.10413v1","created_at":"2026-07-05T11:03:38.053284+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10413","created_at":"2026-07-05T11:03:38.053284+00:00"},{"alias_kind":"pith_short_12","alias_value":"G7FHE7EOWSV5","created_at":"2026-07-05T11:03:38.053284+00:00"},{"alias_kind":"pith_short_16","alias_value":"G7FHE7EOWSV5NA5W","created_at":"2026-07-05T11:03:38.053284+00:00"},{"alias_kind":"pith_short_8","alias_value":"G7FHE7EO","created_at":"2026-07-05T11:03:38.053284+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28349","citing_title":"HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2506.06313","citing_title":"Beyond Chunking: Discourse-Aware Hierarchical Retrieval for Long Document Question Answering","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV","json":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV.json","graph_json":"https://pith.science/api/pith-number/G7FHE7EOWSV5NA5WKRZZRFVCFV/graph.json","events_json":"https://pith.science/api/pith-number/G7FHE7EOWSV5NA5WKRZZRFVCFV/events.json","paper":"https://pith.science/paper/G7FHE7EO"},"agent_actions":{"view_html":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV","download_json":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV.json","view_paper":"https://pith.science/paper/G7FHE7EO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.10413&json=true","fetch_graph":"https://pith.science/api/pith-number/G7FHE7EOWSV5NA5WKRZZRFVCFV/graph.json","fetch_events":"https://pith.science/api/pith-number/G7FHE7EOWSV5NA5WKRZZRFVCFV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV/action/storage_attestation","attest_author":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV/action/author_attestation","sign_citation":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV/action/citation_signature","submit_replication":"https://pith.science/pith/G7FHE7EOWSV5NA5WKRZZRFVCFV/action/replication_record"}},"created_at":"2026-07-05T11:03:38.053284+00:00","updated_at":"2026-07-05T11:03:38.053284+00:00"}