{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KSGSMS6AOPCRGUMIEO55CQEIMY","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":"6c9a7826018a8eceddd14e9efbce3717a814f342c75e202a634c1ae5e0562881","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T05:21:58Z","title_canon_sha256":"0df20bbcb911ec2f330a0bcbfc1cf4cffbd5928a6ba68cfe70dbef5641a5e0d7"},"schema_version":"1.0","source":{"id":"2507.09935","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.09935","created_at":"2026-07-05T11:36:42Z"},{"alias_kind":"arxiv_version","alias_value":"2507.09935v1","created_at":"2026-07-05T11:36:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.09935","created_at":"2026-07-05T11:36:42Z"},{"alias_kind":"pith_short_12","alias_value":"KSGSMS6AOPCR","created_at":"2026-07-05T11:36:42Z"},{"alias_kind":"pith_short_16","alias_value":"KSGSMS6AOPCRGUMI","created_at":"2026-07-05T11:36:42Z"},{"alias_kind":"pith_short_8","alias_value":"KSGSMS6A","created_at":"2026-07-05T11:36:42Z"}],"graph_snapshots":[{"event_id":"sha256:a35e300057526ba470a8eec20bde9818bcd7a3718c5f5907b314173c42e0ad3b","target":"graph","created_at":"2026-07-05T11:36:42Z","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/2507.09935/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-Augmented Generation (RAG) systems commonly use chunking strategies for retrieval, which enhance large language models (LLMs) by enabling them to access external knowledge, ensuring that the retrieved information is up-to-date and domain-specific. However, traditional methods often fail to create chunks that capture sufficient semantic meaning, as they do not account for the underlying textual structure. This paper proposes a novel framework that enhances RAG by integrating hierarchical text segmentation and clustering to generate more meaningful and semantically coherent chunks. Dur","authors_text":"Hai Toan Nguyen, Tien Dat Nguyen, Viet Ha Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T05:21:58Z","title":"Enhancing Retrieval Augmented Generation with Hierarchical Text Segmentation Chunking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.09935","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":"sha256:3fa513faf1bc6d73bba29471b433d17c537a07956afc93eb0199e215a19694ba","target":"record","created_at":"2026-07-05T11:36:42Z","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":"6c9a7826018a8eceddd14e9efbce3717a814f342c75e202a634c1ae5e0562881","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T05:21:58Z","title_canon_sha256":"0df20bbcb911ec2f330a0bcbfc1cf4cffbd5928a6ba68cfe70dbef5641a5e0d7"},"schema_version":"1.0","source":{"id":"2507.09935","kind":"arxiv","version":1}},"canonical_sha256":"548d264bc073c513518823bbd140886604f9a1b2611d1c35908537d0c0a67d65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"548d264bc073c513518823bbd140886604f9a1b2611d1c35908537d0c0a67d65","first_computed_at":"2026-07-05T11:36:42.465917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:42.465917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rtizHVeUtgwMGu4B7emPxApBA6TGBIGXO9zCrmZY6FKTFBAD5a+/XsTpA6+egS3w5q6fdS6YhdJln6ZT89j5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:42.466440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.09935","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fa513faf1bc6d73bba29471b433d17c537a07956afc93eb0199e215a19694ba","sha256:a35e300057526ba470a8eec20bde9818bcd7a3718c5f5907b314173c42e0ad3b"],"state_sha256":"69f10c658eb4dc1a350976059f9881f49c023054f014ae051c9f80a9fbe48226"}