{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:G2TLGX7A6I5DA55YXGWD4AK4SJ","short_pith_number":"pith:G2TLGX7A","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"},"canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","source":{"kind":"arxiv","id":"2506.13607","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13607","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13607v1","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13607","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"G2TLGX7A6I5D","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"G2TLGX7A6I5DA55Y","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"G2TLGX7A","created_at":"2026-07-05T11:22:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:G2TLGX7A6I5DA55YXGWD4AK4SJ","target":"record","payload":{"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"},"canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","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"},"source_kind":"arxiv","source_id":"2506.13607","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9dfhQJ3cJuS7txHBLevoNfDGBiJXzM7X03BRCGbJVlxwmuGG/AnWyq1TG4SIhAEIQxu3jqRAu9NzZsfvoCeTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:16:43.645322Z"},"content_sha256":"8341cddc1d1014c81ea357c67b179cf3803679f7b18744a72a26870bd033d3de","schema_version":"1.0","event_id":"sha256:8341cddc1d1014c81ea357c67b179cf3803679f7b18744a72a26870bd033d3de"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:G2TLGX7A6I5DA55YXGWD4AK4SJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnCtsSpUSIFSiR0dnrYBbKXJioXYg/Fc+LrtkDisU2lz+/8B2NuaJ7TIqWhCl5SkUSqpDW0l92WoH6OiyzpLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T14:16:43.645827Z"},"content_sha256":"81eecf60e11b8698712bdbb1749ee668eeafed1094673d2c198ef7cc12d7de3b","schema_version":"1.0","event_id":"sha256:81eecf60e11b8698712bdbb1749ee668eeafed1094673d2c198ef7cc12d7de3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/bundle.json","state_url":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-21T14:16:43Z","links":{"resolver":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ","bundle":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/bundle.json","state":"https://pith.science/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G2TLGX7A6I5DA55YXGWD4AK4SJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:G2TLGX7A6I5DA55YXGWD4AK4SJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6a71d7d1517764f73856b726c10e8ea769fa4fc03d21440f5e1a2786eb32b8b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-16T15:34:29Z","title_canon_sha256":"8c7e630cde2c8de941e31ae83a16e57efd5abf3946cbb6546ce496421d577cb1"},"schema_version":"1.0","source":{"id":"2506.13607","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.13607","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2506.13607v1","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.13607","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"G2TLGX7A6I5D","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"G2TLGX7A6I5DA55Y","created_at":"2026-07-05T11:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"G2TLGX7A","created_at":"2026-07-05T11:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:81eecf60e11b8698712bdbb1749ee668eeafed1094673d2c198ef7cc12d7de3b","target":"graph","created_at":"2026-07-05T11:22:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.13607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chia-Heng Yu, Yen-lung Tsai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-16T15:34:29Z","title":"Tree-Based Text Retrieval via Hierarchical Clustering in RAGFrameworks: Application on Taiwanese Regulations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.13607","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8341cddc1d1014c81ea357c67b179cf3803679f7b18744a72a26870bd033d3de","target":"record","created_at":"2026-07-05T11:22:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6a71d7d1517764f73856b726c10e8ea769fa4fc03d21440f5e1a2786eb32b8b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-06-16T15:34:29Z","title_canon_sha256":"8c7e630cde2c8de941e31ae83a16e57efd5abf3946cbb6546ce496421d577cb1"},"schema_version":"1.0","source":{"id":"2506.13607","kind":"arxiv","version":1}},"canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36a6b35fe0f23a3077b8b9ac3e015c924cc5d66fb2d00191a9a74316fe6b77f3","first_computed_at":"2026-07-05T11:22:23.321494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:23.321494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B1JgnhZAUw6ePDqDHKmxjgVI6CEJcvTRksG83c/ocwtget8TqkQprDR9TfCyOXjX8aTSbcSLV9zFh8XmiP72Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:23.322008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.13607","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8341cddc1d1014c81ea357c67b179cf3803679f7b18744a72a26870bd033d3de","sha256:81eecf60e11b8698712bdbb1749ee668eeafed1094673d2c198ef7cc12d7de3b"],"state_sha256":"59efc86dcbb13a49584b46ca2b673088c718419b7fce6f32a7109bde06978b71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiii5NUrtcOMDDeBVZSEayQ+SysOz0BS0y/3nS68VSjCf78aVnuhC7zwKE2bUJj9GFC9TrZRCGxu+lI8hiwVDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T14:16:43.651368Z","bundle_sha256":"732802bf3236a5b82575acf60405efa1ec9d5593d9ed6e58444ae49ff842ddda"}}