{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LOIVUB34M42WJOS5N34UHQSX4E","short_pith_number":"pith:LOIVUB34","schema_version":"1.0","canonical_sha256":"5b915a077c673564ba5d6ef943c257e112c859a14cd43fc59b3fd4a54112d9d6","source":{"kind":"arxiv","id":"2410.12788","version":3},"attestation_state":"computed","paper":{"title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Feiyu Xiong, Jihao Zhao, Pengnian Qi, Simin Niu, Yuchen Feng, Zhiyuan Ji, Zhiyu Li","submitted_at":"2024-10-16T17:59:32Z","abstract_excerpt":"While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucial aspect of text chunking within its workflow. This paper proposes the Meta-Chunking framework, which specifically enhances chunking quality through a dual strategy that identifies optimal segmentation points and preserves global information. Initially, breaking limitations of similarity-based chunking, we design two adaptive chunking techniques based on uncertainty, namely Perplexity Chunking and Margin Sampling Chu"},"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":"2410.12788","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-16T17:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"1708318e7fb04398e262f17c1af7cd8f3514913af5c0d1d0fee647cec7ee72a7","abstract_canon_sha256":"c444e3680e5c386b9d56333543bf1336793be6deb7d9072f27c6879001b1e63e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:06:24.235324Z","signature_b64":"z7xsAF/alQmeLr6a4e73eihjxNYN/eUWTHKC+0cH2sAnC7+QnXwr44dgZhLP4GHXjIUgITzmQ7Cw/YGAV148AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b915a077c673564ba5d6ef943c257e112c859a14cd43fc59b3fd4a54112d9d6","last_reissued_at":"2026-07-05T11:06:24.234799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:06:24.234799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Chunking: Learning Text Segmentation and Semantic Completion via Logical Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Tang, Feiyu Xiong, Jihao Zhao, Pengnian Qi, Simin Niu, Yuchen Feng, Zhiyuan Ji, Zhiyu Li","submitted_at":"2024-10-16T17:59:32Z","abstract_excerpt":"While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucial aspect of text chunking within its workflow. This paper proposes the Meta-Chunking framework, which specifically enhances chunking quality through a dual strategy that identifies optimal segmentation points and preserves global information. Initially, breaking limitations of similarity-based chunking, we design two adaptive chunking techniques based on uncertainty, namely Perplexity Chunking and Margin Sampling Chu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12788","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/2410.12788/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":"2410.12788","created_at":"2026-07-05T11:06:24.234864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.12788v3","created_at":"2026-07-05T11:06:24.234864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12788","created_at":"2026-07-05T11:06:24.234864+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOIVUB34M42W","created_at":"2026-07-05T11:06:24.234864+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOIVUB34M42WJOS5","created_at":"2026-07-05T11:06:24.234864+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOIVUB34","created_at":"2026-07-05T11:06:24.234864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00881","citing_title":"Chunking Methods on Retrieval-Augmented Generation - Effectiveness Evaluation Against Computational Cost and Limitations","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E","json":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E.json","graph_json":"https://pith.science/api/pith-number/LOIVUB34M42WJOS5N34UHQSX4E/graph.json","events_json":"https://pith.science/api/pith-number/LOIVUB34M42WJOS5N34UHQSX4E/events.json","paper":"https://pith.science/paper/LOIVUB34"},"agent_actions":{"view_html":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E","download_json":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E.json","view_paper":"https://pith.science/paper/LOIVUB34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.12788&json=true","fetch_graph":"https://pith.science/api/pith-number/LOIVUB34M42WJOS5N34UHQSX4E/graph.json","fetch_events":"https://pith.science/api/pith-number/LOIVUB34M42WJOS5N34UHQSX4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E/action/storage_attestation","attest_author":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E/action/author_attestation","sign_citation":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E/action/citation_signature","submit_replication":"https://pith.science/pith/LOIVUB34M42WJOS5N34UHQSX4E/action/replication_record"}},"created_at":"2026-07-05T11:06:24.234864+00:00","updated_at":"2026-07-05T11:06:24.234864+00:00"}