{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MG54F3ZQSYHY437LSVHERQEF5J","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":"9313da74f8c97a8c05d3bcbc90eb851bfd55f185e84cb3e933be46d511cc6a45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-02T02:09:01Z","title_canon_sha256":"b55e664516d6ce8a886b7946f8313e525d24465763e92fb4a57b814c0ca87595"},"schema_version":"1.0","source":{"id":"2411.01106","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.01106","created_at":"2026-07-05T10:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2411.01106v2","created_at":"2026-07-05T10:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01106","created_at":"2026-07-05T10:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"MG54F3ZQSYHY","created_at":"2026-07-05T10:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"MG54F3ZQSYHY437L","created_at":"2026-07-05T10:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"MG54F3ZQ","created_at":"2026-07-05T10:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:1043cebd52ae7a624470cc474a80bf46e607cac78d5ccd527cf09ad614baa6a2","target":"graph","created_at":"2026-07-05T10:22:09Z","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/2411.01106/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have recently shown great progress in text-rich image understanding, yet they still struggle with complex, multi-page visually-rich documents. Traditional methods using document parsers for retrieval-augmented generation suffer from performance and efficiency limitations, while directly presenting all pages to MLLMs leads to inefficiencies, especially with lengthy ones. In this work, we present a novel framework named **S**elf-**V**isual **R**etrieval-**A**ugmented **G**eneration (SV-RAG), which can broaden horizons of any MLLM to support long-document ","authors_text":"Changyou Chen, Franck Dernoncourt, Jian Chen, Jiuxiang Gu, Ruiyi Zhang, Ryan A. Rossi, Tong Sun, Tong Yu, Yufan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-02T02:09:01Z","title":"SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01106","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":"sha256:7a8fa6f2c53a03380ad57a5ad045cc0434d2640eefe085dfd97ac0c621946ada","target":"record","created_at":"2026-07-05T10:22:09Z","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":"9313da74f8c97a8c05d3bcbc90eb851bfd55f185e84cb3e933be46d511cc6a45","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-02T02:09:01Z","title_canon_sha256":"b55e664516d6ce8a886b7946f8313e525d24465763e92fb4a57b814c0ca87595"},"schema_version":"1.0","source":{"id":"2411.01106","kind":"arxiv","version":2}},"canonical_sha256":"61bbc2ef30960f8e6feb954e48c085ea63f37ec0a6cb449b2015c4fa26627f1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61bbc2ef30960f8e6feb954e48c085ea63f37ec0a6cb449b2015c4fa26627f1b","first_computed_at":"2026-07-05T10:22:09.029994Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:09.029994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HFA03T12Z8EVkcEOTYDA1u5qXHKLp6O7TU5sdT8Dr/rrzKnfI1xEUPy5RA5dOFhfepcozv0wYEYgCRD5iRn2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:09.030502Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.01106","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a8fa6f2c53a03380ad57a5ad045cc0434d2640eefe085dfd97ac0c621946ada","sha256:1043cebd52ae7a624470cc474a80bf46e607cac78d5ccd527cf09ad614baa6a2"],"state_sha256":"28d3b13d62cad8a89156220350446f809a7e5f82f47cb08dc0455015a8f6b3e9"}