{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G2TLGX7A6I5DA55YXGWD4AK4SJ","short_pith_number":"pith:G2TLGX7A","schema_version":"1.0","canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","source":{"kind":"arxiv","id":"2506.13607","version":1},"attestation_state":"computed","paper":{"title":"Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chia-Heng Yu, Yen-lung Tsai","submitted_at":"2025-06-16T15:34:29Z","abstract_excerpt":"Traditional Retrieval-Augmented Generation (RAG) systems employ brute-force inner product search to retrieve the top-k most similar documents, then combined with the user query and passed to a language model. This allows the model to access external knowledge and reduce hallucinations. However, selecting an appropriate k value remains a significant challenge in practical applications: a small k may fail to retrieve sufficient information, while a large k can introduce excessive and irrelevant content. To address this, we propose a hierarchical clustering-based retrieval method that eliminates "},"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":"2506.13607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-16T15:34:29Z","cross_cats_sorted":[],"title_canon_sha256":"8c7e630cde2c8de941e31ae83a16e57efd5abf3946cbb6546ce496421d577cb1","abstract_canon_sha256":"6a71d7d1517764f73856b726c10e8ea769fa4fc03d21440f5e1a2786eb32b8b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:23.322008Z","signature_b64":"B1JgnhZAUw6ePDqDHKmxjgVI6CEJcvTRksG83c/ocwtget8TqkQprDR9TfCyOXjX8aTSbcSLV9zFh8XmiP72Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","last_reissued_at":"2026-07-05T11:22:23.321494Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:23.321494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chia-Heng Yu, Yen-lung Tsai","submitted_at":"2025-06-16T15:34:29Z","abstract_excerpt":"Traditional Retrieval-Augmented Generation (RAG) systems employ brute-force inner product search to retrieve the top-k most similar documents, then combined with the user query and passed to a language model. This allows the model to access external knowledge and reduce hallucinations. However, selecting an appropriate k value remains a significant challenge in practical applications: a small k may fail to retrieve sufficient information, while a large k can introduce excessive and irrelevant content. To address this, we propose a hierarchical clustering-based retrieval method that eliminates "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13607","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/2506.13607/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":"2506.13607","created_at":"2026-07-05T11:22:23.321556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.13607v1","created_at":"2026-07-05T11:22:23.321556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13607","created_at":"2026-07-05T11:22:23.321556+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2TLGX7A6I5D","created_at":"2026-07-05T11:22:23.321556+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2TLGX7A6I5DA55Y","created_at":"2026-07-05T11:22:23.321556+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2TLGX7A","created_at":"2026-07-05T11:22:23.321556+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/G2TLGX7A6I5DA55YXGWD4AK4SJ","json":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ.json","graph_json":"https://pith.science/api/pith-number/G2TLGX7A6I5DA55YXGWD4AK4SJ/graph.json","events_json":"https://pith.science/api/pith-number/G2TLGX7A6I5DA55YXGWD4AK4SJ/events.json","paper":"https://pith.science/paper/G2TLGX7A"},"agent_actions":{"view_html":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ","download_json":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ.json","view_paper":"https://pith.science/paper/G2TLGX7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.13607&json=true","fetch_graph":"https://pith.science/api/pith-number/G2TLGX7A6I5DA55YXGWD4AK4SJ/graph.json","fetch_events":"https://pith.science/api/pith-number/G2TLGX7A6I5DA55YXGWD4AK4SJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/action/storage_attestation","attest_author":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/action/author_attestation","sign_citation":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/action/citation_signature","submit_replication":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/action/replication_record"}},"created_at":"2026-07-05T11:22:23.321556+00:00","updated_at":"2026-07-05T11:22:23.321556+00:00"}