{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RG6JXY3LVBNFQW25HGILJ76ENU","short_pith_number":"pith:RG6JXY3L","schema_version":"1.0","canonical_sha256":"89bc9be36ba85a585b5d3990b4ffc46d26833fc40286b8f207609dfe092482c0","source":{"kind":"arxiv","id":"2505.02171","version":1},"attestation_state":"computed","paper":{"title":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Alexander S. Nossum, Henrik Br{\\aa}dland, Morten Goodwin, Per-Arne Andersen","submitted_at":"2025-05-04T16:22:27Z","abstract_excerpt":"Document chunking fundamentally impacts Retrieval-Augmented Generation (RAG) by determining how source materials are segmented before indexing. Despite evidence that Large Language Models (LLMs) are sensitive to the layout and structure of retrieved data, there is currently no framework to analyze the impact of different chunking methods. In this paper, we introduce a novel methodology that defines essential characteristics of the chunking process at three levels: intrinsic passage properties, extrinsic passage properties, and passages-document coherence. We propose HOPE (Holistic Passage Eval"},"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":"2505.02171","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-04T16:22:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"415cf5aaa181c8d95fce9ac0a5607388850b60f8cc4e0cf70f4a5f080fa5e418","abstract_canon_sha256":"12e1cf2149f82af5e2167520c37f7059a79610fec6d557d720f7c25cd9e06d65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:33.223993Z","signature_b64":"grY0HuSe1HwpFA1KKjoB/kocOVwJYVT1hYYVqQSbTOFhTWNH2UaFsu8QtK5F8SkLn9lb1QLJymrZh6Q86KrqBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89bc9be36ba85a585b5d3990b4ffc46d26833fc40286b8f207609dfe092482c0","last_reissued_at":"2026-07-05T10:58:33.223492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:33.223492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A New HOPE: Domain-agnostic Automatic Evaluation of Text Chunking","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Gupta, Alexander S. Nossum, Henrik Br{\\aa}dland, Morten Goodwin, Per-Arne Andersen","submitted_at":"2025-05-04T16:22:27Z","abstract_excerpt":"Document chunking fundamentally impacts Retrieval-Augmented Generation (RAG) by determining how source materials are segmented before indexing. Despite evidence that Large Language Models (LLMs) are sensitive to the layout and structure of retrieved data, there is currently no framework to analyze the impact of different chunking methods. In this paper, we introduce a novel methodology that defines essential characteristics of the chunking process at three levels: intrinsic passage properties, extrinsic passage properties, and passages-document coherence. We propose HOPE (Holistic Passage Eval"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02171","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/2505.02171/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":"2505.02171","created_at":"2026-07-05T10:58:33.223552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02171v1","created_at":"2026-07-05T10:58:33.223552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02171","created_at":"2026-07-05T10:58:33.223552+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG6JXY3LVBNF","created_at":"2026-07-05T10:58:33.223552+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG6JXY3LVBNFQW25","created_at":"2026-07-05T10:58:33.223552+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG6JXY3L","created_at":"2026-07-05T10:58:33.223552+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/RG6JXY3LVBNFQW25HGILJ76ENU","json":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU.json","graph_json":"https://pith.science/api/pith-number/RG6JXY3LVBNFQW25HGILJ76ENU/graph.json","events_json":"https://pith.science/api/pith-number/RG6JXY3LVBNFQW25HGILJ76ENU/events.json","paper":"https://pith.science/paper/RG6JXY3L"},"agent_actions":{"view_html":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU","download_json":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU.json","view_paper":"https://pith.science/paper/RG6JXY3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02171&json=true","fetch_graph":"https://pith.science/api/pith-number/RG6JXY3LVBNFQW25HGILJ76ENU/graph.json","fetch_events":"https://pith.science/api/pith-number/RG6JXY3LVBNFQW25HGILJ76ENU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU/action/storage_attestation","attest_author":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU/action/author_attestation","sign_citation":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU/action/citation_signature","submit_replication":"https://pith.science/pith/RG6JXY3LVBNFQW25HGILJ76ENU/action/replication_record"}},"created_at":"2026-07-05T10:58:33.223552+00:00","updated_at":"2026-07-05T10:58:33.223552+00:00"}