{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LV5DOP25BWLD6RM2VVBCX33RHB","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":"e8d48b2dcd6c126950c33fca50177c320ebbdd1ea1b06e04324a714352eed5e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T03:27:50Z","title_canon_sha256":"93760249e9c531206b664d86b263bb80522d55d48af4316dd52f3d252081673b"},"schema_version":"1.0","source":{"id":"2607.22723","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22723","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22723v1","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22723","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_12","alias_value":"LV5DOP25BWLD","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_16","alias_value":"LV5DOP25BWLD6RM2","created_at":"2026-07-28T00:21:51Z"},{"alias_kind":"pith_short_8","alias_value":"LV5DOP25","created_at":"2026-07-28T00:21:51Z"}],"graph_snapshots":[{"event_id":"sha256:fd8496a284bcb58c38c99eda7ca4177ecc04286b82637425d101f7030d35e428","target":"graph","created_at":"2026-07-28T00:21:51Z","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/2607.22723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual information extraction (VIE) from visually rich documents remains challenging due to high layout variability and real-world impairments. Existing methods typically rely on sequential OCR pipelines or end-to-end models requiring extensive labeled data and layout-specific training, limiting their scalability.We propose a classification-guided large vision-language model (LVLM) framework for multi-type VIE that achieves high accuracy with minimal supervision. The approach decouples document-type classification from content extraction and employs in-context learning (ICL)-based dynamic prom","authors_text":"Guo Chen, Huafu Li, Jia Xia, Lei Wang, Liming Li, Wei Du, Weijun Peng, Yun Yao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T03:27:50Z","title":"Visual Information Extraction from Documents via Classification-Guided Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22723","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":"sha256:57d3950782b9458ba4b19a95d30c8e7b7d1551142f65ffad10e3f62920581105","target":"record","created_at":"2026-07-28T00:21:51Z","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":"e8d48b2dcd6c126950c33fca50177c320ebbdd1ea1b06e04324a714352eed5e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T03:27:50Z","title_canon_sha256":"93760249e9c531206b664d86b263bb80522d55d48af4316dd52f3d252081673b"},"schema_version":"1.0","source":{"id":"2607.22723","kind":"arxiv","version":1}},"canonical_sha256":"5d7a373f5d0d963f459aad422bef713864f3a6c2956ac4e82077b1c7eb7f4c25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d7a373f5d0d963f459aad422bef713864f3a6c2956ac4e82077b1c7eb7f4c25","first_computed_at":"2026-07-28T00:21:51.107917Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:21:51.107917Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gBlmu0+tV7+u2SCop4AMCTGBNcmvFg8Cd10jRmiumN5ZpoFkRSnHVXSGrxq2WUqaWCUVGXX9p1yVuX19GFisBg==","signature_status":"signed_v1","signed_at":"2026-07-28T00:21:51.108791Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22723","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57d3950782b9458ba4b19a95d30c8e7b7d1551142f65ffad10e3f62920581105","sha256:fd8496a284bcb58c38c99eda7ca4177ecc04286b82637425d101f7030d35e428"],"state_sha256":"bc19ef30ff4f5456f6f38fed4d200ac2d95c9ca2ec6028d187348de47fb5e2d5"}