{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O66FUVDMNAIKPBFQU5LDUC46Z4","short_pith_number":"pith:O66FUVDM","schema_version":"1.0","canonical_sha256":"77bc5a546c6810a784b0a7563a0b9ecf0f63ab2b9c1de8725687143d2b457ca5","source":{"kind":"arxiv","id":"2504.03165","version":3},"attestation_state":"computed","paper":{"title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaiming Liu, Weitao Li, Weizhi Ma, Xiangyu Zhang, Xuanyu Lei, Yang Liu","submitted_at":"2025-04-04T04:43:13Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for knowledge injection during large language model (LLM) inference in recent years. However, due to their limited ability to exploit fine-grained inter-document relationships, current RAG implementations face challenges in effectively addressing the retrieved noise and redundancy content, which may cause error in the generation results. To address these limitations, we propose an Efficient Dynamic Clustering-based document Compression framework (EDC2-RAG) that utilizes latent inter-document relationships while simul"},"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":"2504.03165","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T04:43:13Z","cross_cats_sorted":[],"title_canon_sha256":"6b8306bbe9eaf9d760374c0626e40bbbb7735a18bfa0e2f9d350fbe14d4e2f86","abstract_canon_sha256":"b2511abae17f57a202eccc36579652ef4d766913124313333da084717c35d8dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:47.551238Z","signature_b64":"esi7LPKcd+TOqLAw/ZGaAshlPzhpSPi16ctXKtTBEIWvXsZfW8oYDrFp4O1X1stn8nPv8nnBwUrwdSDWM+u7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77bc5a546c6810a784b0a7563a0b9ecf0f63ab2b9c1de8725687143d2b457ca5","last_reissued_at":"2026-07-05T12:06:47.550744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:47.550744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Dynamic Clustering-Based Document Compression for Retrieval-Augmented-Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kaiming Liu, Weitao Li, Weizhi Ma, Xiangyu Zhang, Xuanyu Lei, Yang Liu","submitted_at":"2025-04-04T04:43:13Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for knowledge injection during large language model (LLM) inference in recent years. However, due to their limited ability to exploit fine-grained inter-document relationships, current RAG implementations face challenges in effectively addressing the retrieved noise and redundancy content, which may cause error in the generation results. To address these limitations, we propose an Efficient Dynamic Clustering-based document Compression framework (EDC2-RAG) that utilizes latent inter-document relationships while simul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03165","kind":"arxiv","version":3},"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/2504.03165/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":"2504.03165","created_at":"2026-07-05T12:06:47.550809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03165v3","created_at":"2026-07-05T12:06:47.550809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03165","created_at":"2026-07-05T12:06:47.550809+00:00"},{"alias_kind":"pith_short_12","alias_value":"O66FUVDMNAIK","created_at":"2026-07-05T12:06:47.550809+00:00"},{"alias_kind":"pith_short_16","alias_value":"O66FUVDMNAIKPBFQ","created_at":"2026-07-05T12:06:47.550809+00:00"},{"alias_kind":"pith_short_8","alias_value":"O66FUVDM","created_at":"2026-07-05T12:06:47.550809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11907","citing_title":"Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4","json":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4.json","graph_json":"https://pith.science/api/pith-number/O66FUVDMNAIKPBFQU5LDUC46Z4/graph.json","events_json":"https://pith.science/api/pith-number/O66FUVDMNAIKPBFQU5LDUC46Z4/events.json","paper":"https://pith.science/paper/O66FUVDM"},"agent_actions":{"view_html":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4","download_json":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4.json","view_paper":"https://pith.science/paper/O66FUVDM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03165&json=true","fetch_graph":"https://pith.science/api/pith-number/O66FUVDMNAIKPBFQU5LDUC46Z4/graph.json","fetch_events":"https://pith.science/api/pith-number/O66FUVDMNAIKPBFQU5LDUC46Z4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4/action/storage_attestation","attest_author":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4/action/author_attestation","sign_citation":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4/action/citation_signature","submit_replication":"https://pith.science/pith/O66FUVDMNAIKPBFQU5LDUC46Z4/action/replication_record"}},"created_at":"2026-07-05T12:06:47.550809+00:00","updated_at":"2026-07-05T12:06:47.550809+00:00"}