{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XIEDBL23FR6ZFZZTSZAXGRIS7M","short_pith_number":"pith:XIEDBL23","schema_version":"1.0","canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","source":{"kind":"arxiv","id":"2501.09940","version":1},"attestation_state":"computed","paper":{"title":"Passage Segmentation of Documents for Extractive Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Charles-Elie Simon, Fabien Caspani, Zuhong Liu","submitted_at":"2025-01-17T03:42:18Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has proven effective in open-domain question answering. However, the chunking process, which is essential to this pipeline, often receives insufficient attention relative to retrieval and synthesis components. This study emphasizes the critical role of chunking in improving the performance of both dense passage retrieval and the end-to-end RAG pipeline. We then introduce the Logits-Guided Multi-Granular Chunker (LGMGC), a novel framework that splits long documents into contextualized, self-contained chunks of varied granularity. Our experimental results, ev"},"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":"2501.09940","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T03:42:18Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"4a5c2fe134d6f404dc0522da8874a48ba45f5b199af11176c459cbfd37269c37","abstract_canon_sha256":"cd61fcc41c5d9753d8cddb1715e33df26718e98b6b4aefefce4a8852f37245b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:13.549991Z","signature_b64":"OtaBuem4BvkT4AxMiKYVxlS1P2Lz4AfPD5QXbhpNVLtnjZ8SvHsXTkAKWlFrp2IEmf/5iGn40TzkfTWplj4ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","last_reissued_at":"2026-07-05T10:02:13.549604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:13.549604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Passage Segmentation of Documents for Extractive Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Charles-Elie Simon, Fabien Caspani, Zuhong Liu","submitted_at":"2025-01-17T03:42:18Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) has proven effective in open-domain question answering. However, the chunking process, which is essential to this pipeline, often receives insufficient attention relative to retrieval and synthesis components. This study emphasizes the critical role of chunking in improving the performance of both dense passage retrieval and the end-to-end RAG pipeline. We then introduce the Logits-Guided Multi-Granular Chunker (LGMGC), a novel framework that splits long documents into contextualized, self-contained chunks of varied granularity. Our experimental results, ev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09940","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/2501.09940/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":"2501.09940","created_at":"2026-07-05T10:02:13.549661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09940v1","created_at":"2026-07-05T10:02:13.549661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09940","created_at":"2026-07-05T10:02:13.549661+00:00"},{"alias_kind":"pith_short_12","alias_value":"XIEDBL23FR6Z","created_at":"2026-07-05T10:02:13.549661+00:00"},{"alias_kind":"pith_short_16","alias_value":"XIEDBL23FR6ZFZZT","created_at":"2026-07-05T10:02:13.549661+00:00"},{"alias_kind":"pith_short_8","alias_value":"XIEDBL23","created_at":"2026-07-05T10:02:13.549661+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/XIEDBL23FR6ZFZZTSZAXGRIS7M","json":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M.json","graph_json":"https://pith.science/api/pith-number/XIEDBL23FR6ZFZZTSZAXGRIS7M/graph.json","events_json":"https://pith.science/api/pith-number/XIEDBL23FR6ZFZZTSZAXGRIS7M/events.json","paper":"https://pith.science/paper/XIEDBL23"},"agent_actions":{"view_html":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M","download_json":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M.json","view_paper":"https://pith.science/paper/XIEDBL23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09940&json=true","fetch_graph":"https://pith.science/api/pith-number/XIEDBL23FR6ZFZZTSZAXGRIS7M/graph.json","fetch_events":"https://pith.science/api/pith-number/XIEDBL23FR6ZFZZTSZAXGRIS7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/action/storage_attestation","attest_author":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/action/author_attestation","sign_citation":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/action/citation_signature","submit_replication":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/action/replication_record"}},"created_at":"2026-07-05T10:02:13.549661+00:00","updated_at":"2026-07-05T10:02:13.549661+00:00"}