{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BECWW2Q3C6GLLBTJMDDIRH34O4","short_pith_number":"pith:BECWW2Q3","schema_version":"1.0","canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","source":{"kind":"arxiv","id":"2607.24748","version":1},"attestation_state":"computed","paper":{"title":"VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Seonok Kim","submitted_at":"2026-05-21T13:33:38Z","abstract_excerpt":"Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures. This work studies multimodal retrieval-augmented generation for question answering over such visually-rich long documents, where retrieval must select evidence pages that include both textual and visual signals. We present VLD-RAG, an agentic multimodal RAG framework for multi-page evidence retrieval and cross-page reasoning over long documents. VLD-RAG builds a page-preserving multimodal index t"},"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":"2607.24748","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-21T13:33:38Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"dad29c4936f3314c7b2d37655d9bcf488143b5a716f2eb1f7e73526f6649c97d","abstract_canon_sha256":"7f7c083b2c56347b0c8a6a1ff608af1740870f4fcdd6eeeceafcf9aec0f04eb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:41.907722Z","signature_b64":"iQJS0XPQBMRvW+6s2SRCzw2XI8cdyzNC8yvyRN1Y+oOlndRtmxvCGIjyJA6SC6kaaJjgn1FYF8LjogD/YHh+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","last_reissued_at":"2026-07-29T00:24:41.906820Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:41.906820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Seonok Kim","submitted_at":"2026-05-21T13:33:38Z","abstract_excerpt":"Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures. This work studies multimodal retrieval-augmented generation for question answering over such visually-rich long documents, where retrieval must select evidence pages that include both textual and visual signals. We present VLD-RAG, an agentic multimodal RAG framework for multi-page evidence retrieval and cross-page reasoning over long documents. VLD-RAG builds a page-preserving multimodal index t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24748","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/2607.24748/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":"2607.24748","created_at":"2026-07-29T00:24:41.907242+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24748v1","created_at":"2026-07-29T00:24:41.907242+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24748","created_at":"2026-07-29T00:24:41.907242+00:00"},{"alias_kind":"pith_short_12","alias_value":"BECWW2Q3C6GL","created_at":"2026-07-29T00:24:41.907242+00:00"},{"alias_kind":"pith_short_16","alias_value":"BECWW2Q3C6GLLBTJ","created_at":"2026-07-29T00:24:41.907242+00:00"},{"alias_kind":"pith_short_8","alias_value":"BECWW2Q3","created_at":"2026-07-29T00:24:41.907242+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/BECWW2Q3C6GLLBTJMDDIRH34O4","json":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4.json","graph_json":"https://pith.science/api/pith-number/BECWW2Q3C6GLLBTJMDDIRH34O4/graph.json","events_json":"https://pith.science/api/pith-number/BECWW2Q3C6GLLBTJMDDIRH34O4/events.json","paper":"https://pith.science/paper/BECWW2Q3"},"agent_actions":{"view_html":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4","download_json":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4.json","view_paper":"https://pith.science/paper/BECWW2Q3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24748&json=true","fetch_graph":"https://pith.science/api/pith-number/BECWW2Q3C6GLLBTJMDDIRH34O4/graph.json","fetch_events":"https://pith.science/api/pith-number/BECWW2Q3C6GLLBTJMDDIRH34O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/action/storage_attestation","attest_author":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/action/author_attestation","sign_citation":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/action/citation_signature","submit_replication":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/action/replication_record"}},"created_at":"2026-07-29T00:24:41.907242+00:00","updated_at":"2026-07-29T00:24:41.907242+00:00"}