{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XIEDBL23FR6ZFZZTSZAXGRIS7M","short_pith_number":"pith:XIEDBL23","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"},"canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","source":{"kind":"arxiv","id":"2501.09940","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09940","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09940v1","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09940","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"XIEDBL23FR6Z","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_16","alias_value":"XIEDBL23FR6ZFZZT","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_8","alias_value":"XIEDBL23","created_at":"2026-07-05T10:02:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XIEDBL23FR6ZFZZTSZAXGRIS7M","target":"record","payload":{"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"},"canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","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"},"source_kind":"arxiv","source_id":"2501.09940","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":"2026-07-05T10:02:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+KCzamP4GlmApLOmHT7NjzCMLk2tjt90CiQCCtI+w/sJPynTi9jIxlfCUhZ93fhgRpZuWyUEV9rmfUKjM1qqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:23:26.302865Z"},"content_sha256":"08c0e8daf965983717f7a1899ecf80d317545c290791b8ebf10d3660bfccef52","schema_version":"1.0","event_id":"sha256:08c0e8daf965983717f7a1899ecf80d317545c290791b8ebf10d3660bfccef52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XIEDBL23FR6ZFZZTSZAXGRIS7M","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:02:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t8EbIdKOec6/R+tMGnNZZuZq5OgA78hoBBM0XvgIK59tReWY8Ffm/4q2Gx9hKsLv0ShhUbq7rgWBBhahHM/2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T15:23:26.303364Z"},"content_sha256":"720b847a6d7628afaca51da80d2ddcae910a5c039cf2827f485420dede8f9cc9","schema_version":"1.0","event_id":"sha256:720b847a6d7628afaca51da80d2ddcae910a5c039cf2827f485420dede8f9cc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/bundle.json","state_url":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/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":"2026-08-11T15:23:26Z","links":{"resolver":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M","bundle":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/bundle.json","state":"https://pith.science/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XIEDBL23FR6ZFZZTSZAXGRIS7M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XIEDBL23FR6ZFZZTSZAXGRIS7M","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":"cd61fcc41c5d9753d8cddb1715e33df26718e98b6b4aefefce4a8852f37245b5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T03:42:18Z","title_canon_sha256":"4a5c2fe134d6f404dc0522da8874a48ba45f5b199af11176c459cbfd37269c37"},"schema_version":"1.0","source":{"id":"2501.09940","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.09940","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"arxiv_version","alias_value":"2501.09940v1","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09940","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_12","alias_value":"XIEDBL23FR6Z","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_16","alias_value":"XIEDBL23FR6ZFZZT","created_at":"2026-07-05T10:02:13Z"},{"alias_kind":"pith_short_8","alias_value":"XIEDBL23","created_at":"2026-07-05T10:02:13Z"}],"graph_snapshots":[{"event_id":"sha256:720b847a6d7628afaca51da80d2ddcae910a5c039cf2827f485420dede8f9cc9","target":"graph","created_at":"2026-07-05T10:02:13Z","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/2501.09940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Charles-Elie Simon, Fabien Caspani, Zuhong Liu","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T03:42:18Z","title":"Passage Segmentation of Documents for Extractive Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09940","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":"sha256:08c0e8daf965983717f7a1899ecf80d317545c290791b8ebf10d3660bfccef52","target":"record","created_at":"2026-07-05T10:02:13Z","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":"cd61fcc41c5d9753d8cddb1715e33df26718e98b6b4aefefce4a8852f37245b5","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T03:42:18Z","title_canon_sha256":"4a5c2fe134d6f404dc0522da8874a48ba45f5b199af11176c459cbfd37269c37"},"schema_version":"1.0","source":{"id":"2501.09940","kind":"arxiv","version":1}},"canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba0830af5b2c7d92e7339641734512fb2f4f9aeb3eee0564bd4f34919863a714","first_computed_at":"2026-07-05T10:02:13.549604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:02:13.549604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OtaBuem4BvkT4AxMiKYVxlS1P2Lz4AfPD5QXbhpNVLtnjZ8SvHsXTkAKWlFrp2IEmf/5iGn40TzkfTWplj4ZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:02:13.549991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.09940","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08c0e8daf965983717f7a1899ecf80d317545c290791b8ebf10d3660bfccef52","sha256:720b847a6d7628afaca51da80d2ddcae910a5c039cf2827f485420dede8f9cc9"],"state_sha256":"f12d9892fd455751a906342b1bfd6d4931d1eca8163156fbecdf730ddef3af11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AhIXLGMhU7X3mzXTaOvrGeR+QYsIUh/UUnPtLdV68SY2OvU2gSw7W6rj37vvno5I054l63wCC3M4ib06pxg2Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T15:23:26.308400Z","bundle_sha256":"28a3f9f487289aac86cf1fdc8362462084be73bace7474222400a294ca66a17a"}}