{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NYFTBH626WJAY63H75C5ANZQGP","short_pith_number":"pith:NYFTBH62","schema_version":"1.0","canonical_sha256":"6e0b309fdaf5920c7b67ff45d0373033d697327d320a3d7694a765c9c0b8fe63","source":{"kind":"arxiv","id":"2503.02401","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Re-ranker Retriever (HRR)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ashish Singh, Priti Mohapatra","submitted_at":"2025-03-04T08:43:19Z","abstract_excerpt":"Retrieving the right level of context for a given query is a perennial challenge in information retrieval - too large a chunk dilutes semantic specificity, while chunks that are too small lack broader context. This paper introduces the Hierarchical Re-ranker Retriever (HRR), a framework designed to achieve both fine-grained and high-level context retrieval for large language model (LLM) applications. In HRR, documents are split into sentence-level and intermediate-level (512 tokens) chunks to maximize vector-search quality for both short and broad queries. We then employ a reranker that operat"},"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":"2503.02401","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-04T08:43:19Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"32bf79ab2a7a4136eb70c54923c4b1b6b6d5876a4db97dce65b2167579688684","abstract_canon_sha256":"641a1cd75f4d768e57cd8e315e4a9f82eb3ccac4c31188d4d9509f6fb6e7552b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:43.718416Z","signature_b64":"HNdyHqxJaSnSrE457kOdBTKdBnJId5qEqOhKtm3OT7qEYgpe9CIu/jqVSIf7CtYZdVSp0J0aD/wlGJHddybmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e0b309fdaf5920c7b67ff45d0373033d697327d320a3d7694a765c9c0b8fe63","last_reissued_at":"2026-07-05T10:23:43.717598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:43.717598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Re-ranker Retriever (HRR)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Ashish Singh, Priti Mohapatra","submitted_at":"2025-03-04T08:43:19Z","abstract_excerpt":"Retrieving the right level of context for a given query is a perennial challenge in information retrieval - too large a chunk dilutes semantic specificity, while chunks that are too small lack broader context. This paper introduces the Hierarchical Re-ranker Retriever (HRR), a framework designed to achieve both fine-grained and high-level context retrieval for large language model (LLM) applications. In HRR, documents are split into sentence-level and intermediate-level (512 tokens) chunks to maximize vector-search quality for both short and broad queries. We then employ a reranker that operat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02401","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/2503.02401/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":"2503.02401","created_at":"2026-07-05T10:23:43.717698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02401v1","created_at":"2026-07-05T10:23:43.717698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02401","created_at":"2026-07-05T10:23:43.717698+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYFTBH626WJA","created_at":"2026-07-05T10:23:43.717698+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYFTBH626WJAY63H","created_at":"2026-07-05T10:23:43.717698+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYFTBH62","created_at":"2026-07-05T10:23:43.717698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00631","citing_title":"H-RAG at SemEval-2026 Task 8: Hierarchical Parent-Child Retrieval for Multi-Turn RAG Conversations","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP","json":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP.json","graph_json":"https://pith.science/api/pith-number/NYFTBH626WJAY63H75C5ANZQGP/graph.json","events_json":"https://pith.science/api/pith-number/NYFTBH626WJAY63H75C5ANZQGP/events.json","paper":"https://pith.science/paper/NYFTBH62"},"agent_actions":{"view_html":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP","download_json":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP.json","view_paper":"https://pith.science/paper/NYFTBH62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02401&json=true","fetch_graph":"https://pith.science/api/pith-number/NYFTBH626WJAY63H75C5ANZQGP/graph.json","fetch_events":"https://pith.science/api/pith-number/NYFTBH626WJAY63H75C5ANZQGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP/action/storage_attestation","attest_author":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP/action/author_attestation","sign_citation":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP/action/citation_signature","submit_replication":"https://pith.science/pith/NYFTBH626WJAY63H75C5ANZQGP/action/replication_record"}},"created_at":"2026-07-05T10:23:43.717698+00:00","updated_at":"2026-07-05T10:23:43.717698+00:00"}