{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BECWW2Q3C6GLLBTJMDDIRH34O4","short_pith_number":"pith:BECWW2Q3","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"},"canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","source":{"kind":"arxiv","id":"2607.24748","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24748","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24748v1","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24748","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"BECWW2Q3C6GL","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"BECWW2Q3C6GLLBTJ","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"BECWW2Q3","created_at":"2026-07-29T00:24:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BECWW2Q3C6GLLBTJMDDIRH34O4","target":"record","payload":{"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"},"canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","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"},"source_kind":"arxiv","source_id":"2607.24748","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":"2026-07-29T00:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6V348dro0uXt9nXtQYpAe9QlmwmPsaR6ZJusmJFU5E+UHaW+MFAFVGCRRCaSLWoThV7sUZFu3Yn+NBevYBIyBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:23:59.407111Z"},"content_sha256":"b7dcf087711a315118e46de157f94cd4d4d89eff7537151b488103630e5e3f83","schema_version":"1.0","event_id":"sha256:b7dcf087711a315118e46de157f94cd4d4d89eff7537151b488103630e5e3f83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BECWW2Q3C6GLLBTJMDDIRH34O4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-29T00:24:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pmf+mmbRv5kIvyiS2oCqEceLqsdrhQ9GLP/2GdU+ds8oJUqJaUQSDKrBLfDfCvag6bAPtX2THKlX1GCJhebxAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T06:23:59.407628Z"},"content_sha256":"e38e2ac9df1c38e4f070b28c8d37a4174a22d5b46497f58d831132f01f14f71b","schema_version":"1.0","event_id":"sha256:e38e2ac9df1c38e4f070b28c8d37a4174a22d5b46497f58d831132f01f14f71b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/bundle.json","state_url":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/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":"2026-08-04T06:23:59Z","links":{"resolver":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4","bundle":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/bundle.json","state":"https://pith.science/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BECWW2Q3C6GLLBTJMDDIRH34O4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BECWW2Q3C6GLLBTJMDDIRH34O4","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":"7f7c083b2c56347b0c8a6a1ff608af1740870f4fcdd6eeeceafcf9aec0f04eb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-21T13:33:38Z","title_canon_sha256":"dad29c4936f3314c7b2d37655d9bcf488143b5a716f2eb1f7e73526f6649c97d"},"schema_version":"1.0","source":{"id":"2607.24748","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24748","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24748v1","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24748","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_12","alias_value":"BECWW2Q3C6GL","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_16","alias_value":"BECWW2Q3C6GLLBTJ","created_at":"2026-07-29T00:24:41Z"},{"alias_kind":"pith_short_8","alias_value":"BECWW2Q3","created_at":"2026-07-29T00:24:41Z"}],"graph_snapshots":[{"event_id":"sha256:e38e2ac9df1c38e4f070b28c8d37a4174a22d5b46497f58d831132f01f14f71b","target":"graph","created_at":"2026-07-29T00:24:41Z","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/2607.24748/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Seonok Kim","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-21T13:33:38Z","title":"VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24748","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:b7dcf087711a315118e46de157f94cd4d4d89eff7537151b488103630e5e3f83","target":"record","created_at":"2026-07-29T00:24:41Z","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":"7f7c083b2c56347b0c8a6a1ff608af1740870f4fcdd6eeeceafcf9aec0f04eb7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-05-21T13:33:38Z","title_canon_sha256":"dad29c4936f3314c7b2d37655d9bcf488143b5a716f2eb1f7e73526f6649c97d"},"schema_version":"1.0","source":{"id":"2607.24748","kind":"arxiv","version":1}},"canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"09056b6a1b178cb5866960c6889f7c772713460ba7c44d950053e4a99d92c84c","first_computed_at":"2026-07-29T00:24:41.906820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-29T00:24:41.906820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iQJS0XPQBMRvW+6s2SRCzw2XI8cdyzNC8yvyRN1Y+oOlndRtmxvCGIjyJA6SC6kaaJjgn1FYF8LjogD/YHh+DA==","signature_status":"signed_v1","signed_at":"2026-07-29T00:24:41.907722Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24748","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7dcf087711a315118e46de157f94cd4d4d89eff7537151b488103630e5e3f83","sha256:e38e2ac9df1c38e4f070b28c8d37a4174a22d5b46497f58d831132f01f14f71b"],"state_sha256":"80863048afb8eec187a23ac409bd7b85c217c1f1a75f0638927000c288de42da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b0AKJjHmCqV6rjnMy5/KX5m28LaKrpdgkPXhF/rt4KyaDZPWCCp3xWqWTHH6dhf094ibjINjL5UyfSwAUtttAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T06:23:59.419499Z","bundle_sha256":"4bf3d8c783cd208bfcc37c138f77ba07229b721a1fbab0c743b22b33d239aaa7"}}