{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WH5A5AIZS4TBIJW4JI2HLS2I4D","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":"d26d0abac586edafd041eb10668a422efeb9f7d60b6c2150d6262079766335cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T06:57:21Z","title_canon_sha256":"8fe8a47991f4e26798f5eb6b904580669fb57ae35de2a116f470838b154926a7"},"schema_version":"1.0","source":{"id":"2503.13964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13964","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13964v1","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13964","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_12","alias_value":"WH5A5AIZS4TB","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_16","alias_value":"WH5A5AIZS4TBIJW4","created_at":"2026-07-05T10:33:51Z"},{"alias_kind":"pith_short_8","alias_value":"WH5A5AIZ","created_at":"2026-07-05T10:33:51Z"}],"graph_snapshots":[{"event_id":"sha256:859a530c87fbe100a0d9f9c6105db5c536c932f2aa06b924b04f3dc8b7e42300","target":"graph","created_at":"2026-07-05T10:33:51Z","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/2503.13964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single modal, failing to effectively integrate textual and visual cues. These approaches struggle with complex multi-modal reasoning, limiting their performance on real-world documents. We present MDocAgent (A Multi-Modal Multi-Agent Framework for Document Understanding), a novel RAG and multi-agent framework that leverages both text and image. Our system employs five s","authors_text":"Hongtu Zhu, Huaxiu Yao, Peng Xia, Ruiyi Zhang, Siwei Han, Tong Sun, Yun Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T06:57:21Z","title":"MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13964","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":"sha256:1ce4baaec7967e5205ff23773c92baee1d4800fca2fa411cde0360b5c10d20fc","target":"record","created_at":"2026-07-05T10:33:51Z","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":"d26d0abac586edafd041eb10668a422efeb9f7d60b6c2150d6262079766335cc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-18T06:57:21Z","title_canon_sha256":"8fe8a47991f4e26798f5eb6b904580669fb57ae35de2a116f470838b154926a7"},"schema_version":"1.0","source":{"id":"2503.13964","kind":"arxiv","version":1}},"canonical_sha256":"b1fa0e811997261426dc4a3475cb48e0c6deb94d76109c63935a1c785c05d9a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1fa0e811997261426dc4a3475cb48e0c6deb94d76109c63935a1c785c05d9a0","first_computed_at":"2026-07-05T10:33:51.647907Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:51.647907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJIpBzEP6HBBeP3pm9A+NyphKIZYZK/EyL3N/X+fdkOq/mJKzFmiFRlJC/ZaUAHZzZi1vgegN4UNBPQeHlSrDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:51.648534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ce4baaec7967e5205ff23773c92baee1d4800fca2fa411cde0360b5c10d20fc","sha256:859a530c87fbe100a0d9f9c6105db5c536c932f2aa06b924b04f3dc8b7e42300"],"state_sha256":"0a972adf8852315a85de9674a9c8434befca9de177b8c657519bacff53b904e9"}