{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B3UTIKUOOQY5RM23RGB4Z3JYYU","short_pith_number":"pith:B3UTIKUO","schema_version":"1.0","canonical_sha256":"0ee9342a8e7431d8b35b8983cced38c50d3e2c6b680a4b3bc23c857b5a0ccd38","source":{"kind":"arxiv","id":"2406.17526","version":1},"attestation_state":"computed","paper":{"title":"LumberChunker: Long-Form Narrative Document Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Andr\\'e V. Duarte, Arlindo L. Oliveira, Jo\\~ao Marques, Lei Li, Miguel Freire, Miguel Gra\\c{c}a","submitted_at":"2024-06-25T13:08:35Z","abstract_excerpt":"Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from segments that can vary in size such that a content's semantic independence is better captured. We propose LumberChunker, a method leveraging an LLM to dynamically segment documents, which iteratively prompts the LLM to identify the point within a group of sequential passages where the content begins to shift. To evaluate our method, we introduce GutenQA, a benchmark with 3000 \"needle in a haystack\" type of question-"},"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":"2406.17526","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-25T13:08:35Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"545367c7c59a00dc9f75f144838cd1d03464285d9441ce01c7012f0d020b2a95","abstract_canon_sha256":"7de397a058c3cff65795d719fdd83f25d24d99e94a6beed3bf23f894c58b5e3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:36.396188Z","signature_b64":"1yBd2fPDO3nZXqReJeOXurrQY/lLEos4mYGxNssFlP3D7J/Z7CuPv30GNJppX2U5LH/YiuoDY0omSEAQt7RMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ee9342a8e7431d8b35b8983cced38c50d3e2c6b680a4b3bc23c857b5a0ccd38","last_reissued_at":"2026-07-05T08:36:36.395692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:36.395692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LumberChunker: Long-Form Narrative Document Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Andr\\'e V. Duarte, Arlindo L. Oliveira, Jo\\~ao Marques, Lei Li, Miguel Freire, Miguel Gra\\c{c}a","submitted_at":"2024-06-25T13:08:35Z","abstract_excerpt":"Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from segments that can vary in size such that a content's semantic independence is better captured. We propose LumberChunker, a method leveraging an LLM to dynamically segment documents, which iteratively prompts the LLM to identify the point within a group of sequential passages where the content begins to shift. To evaluate our method, we introduce GutenQA, a benchmark with 3000 \"needle in a haystack\" type of question-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17526","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/2406.17526/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":"2406.17526","created_at":"2026-07-05T08:36:36.395749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.17526v1","created_at":"2026-07-05T08:36:36.395749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17526","created_at":"2026-07-05T08:36:36.395749+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3UTIKUOOQY5","created_at":"2026-07-05T08:36:36.395749+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3UTIKUOOQY5RM23","created_at":"2026-07-05T08:36:36.395749+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3UTIKUO","created_at":"2026-07-05T08:36:36.395749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19806","citing_title":"Chunking German Legal Code","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18774","citing_title":"M3DocDep: Multi-modal, Multi-page, Multi-document Dependency Chunking with Large Vision-Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19806","citing_title":"Chunking German Legal Code","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12352","citing_title":"MultiDocFusion: Hierarchical and Multimodal Chunking Pipeline for Enhanced RAG on Long Industrial Documents","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU","json":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU.json","graph_json":"https://pith.science/api/pith-number/B3UTIKUOOQY5RM23RGB4Z3JYYU/graph.json","events_json":"https://pith.science/api/pith-number/B3UTIKUOOQY5RM23RGB4Z3JYYU/events.json","paper":"https://pith.science/paper/B3UTIKUO"},"agent_actions":{"view_html":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU","download_json":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU.json","view_paper":"https://pith.science/paper/B3UTIKUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.17526&json=true","fetch_graph":"https://pith.science/api/pith-number/B3UTIKUOOQY5RM23RGB4Z3JYYU/graph.json","fetch_events":"https://pith.science/api/pith-number/B3UTIKUOOQY5RM23RGB4Z3JYYU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU/action/storage_attestation","attest_author":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU/action/author_attestation","sign_citation":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU/action/citation_signature","submit_replication":"https://pith.science/pith/B3UTIKUOOQY5RM23RGB4Z3JYYU/action/replication_record"}},"created_at":"2026-07-05T08:36:36.395749+00:00","updated_at":"2026-07-05T08:36:36.395749+00:00"}