{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6MSFQPEMYVS56RL7IZRXMDZRTN","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":"31163ced39864e66d7d8782afb3587bce807ff1ebfaaa60ae709d66ec3dd49a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T12:32:55Z","title_canon_sha256":"e53f5d8493f6b022203d875d50ed2d18df0248ca7ce148fa531757ec15d85c2d"},"schema_version":"1.0","source":{"id":"2508.18984","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.18984","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"arxiv_version","alias_value":"2508.18984v2","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18984","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_12","alias_value":"6MSFQPEMYVS5","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_16","alias_value":"6MSFQPEMYVS56RL7","created_at":"2026-07-05T12:00:52Z"},{"alias_kind":"pith_short_8","alias_value":"6MSFQPEM","created_at":"2026-07-05T12:00:52Z"}],"graph_snapshots":[{"event_id":"sha256:9c30a845603f5386b61a2acbe8ef3b5c3af47b4901be21eb31c66ea0c996d0e7","target":"graph","created_at":"2026-07-05T12:00:52Z","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/2508.18984/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Visual Question Answering (Document VQA) must cope with documents that span dozens of pages, yet leading systems still concatenate every page or rely on very large vision-language models, both of which are memory-hungry. Retrieval-Augmented Generation (RAG) offers an attractive alternative, first retrieving a concise set of relevant segments before generating answers from this selected evidence. In this paper, we systematically evaluate the impact of incorporating RAG into Document VQA through different retrieval variants - text-based retrieval using OCR tokens and purely visual retri","authors_text":"Artemis LLabr\\'es, Eric L\\'opez, Ernest Valveny","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T12:32:55Z","title":"Enhancing Document VQA Models via Retrieval-Augmented Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18984","kind":"arxiv","version":2},"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":"sha256:257c57e7fb80e8a6b1f3278e5f8bc03ee887e8205b626e1875f7a069002cfcb5","target":"record","created_at":"2026-07-05T12:00:52Z","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":"31163ced39864e66d7d8782afb3587bce807ff1ebfaaa60ae709d66ec3dd49a3","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-26T12:32:55Z","title_canon_sha256":"e53f5d8493f6b022203d875d50ed2d18df0248ca7ce148fa531757ec15d85c2d"},"schema_version":"1.0","source":{"id":"2508.18984","kind":"arxiv","version":2}},"canonical_sha256":"f324583c8cc565df457f4663760f319b609b1710c34167b0884ed42b91a91527","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f324583c8cc565df457f4663760f319b609b1710c34167b0884ed42b91a91527","first_computed_at":"2026-07-05T12:00:52.170855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:52.170855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M2DRZU6KGFNSkZsrFWBRyCZltjpf9JqkYjDnDOXL9uk60TkbZjP3s4YpyLE9b2kENXhejRsr700ntZdv5ATLBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:52.171420Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.18984","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:257c57e7fb80e8a6b1f3278e5f8bc03ee887e8205b626e1875f7a069002cfcb5","sha256:9c30a845603f5386b61a2acbe8ef3b5c3af47b4901be21eb31c66ea0c996d0e7"],"state_sha256":"ac9e6352bdb143d495d471908822e32a9e47e5df24f91b448a7521eb72df635d"}