{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2XAMK6IRE5NDL2GHB2OS5RPXEA","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":"eadaff09361df2302fd67597ce06f61214a6aac08478726fc88a6825f6fea7d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T11:28:07Z","title_canon_sha256":"660be02768fcddfbd845514082783f256ec6745c224cdd42fbb6627eec5ffb06"},"schema_version":"1.0","source":{"id":"2307.02499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.02499","created_at":"2026-07-05T06:28:20Z"},{"alias_kind":"arxiv_version","alias_value":"2307.02499v1","created_at":"2026-07-05T06:28:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02499","created_at":"2026-07-05T06:28:20Z"},{"alias_kind":"pith_short_12","alias_value":"2XAMK6IRE5ND","created_at":"2026-07-05T06:28:20Z"},{"alias_kind":"pith_short_16","alias_value":"2XAMK6IRE5NDL2GH","created_at":"2026-07-05T06:28:20Z"},{"alias_kind":"pith_short_8","alias_value":"2XAMK6IR","created_at":"2026-07-05T06:28:20Z"}],"graph_snapshots":[{"event_id":"sha256:4ea6fd4c8d530898e44f5f07c57c6f580ca5f19aac381c0a0e3ae8c320453c0e","target":"graph","created_at":"2026-07-05T06:28:20Z","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/2307.02499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Document understanding refers to automatically extract, analyze and comprehend information from various types of digital documents, such as a web page. Existing Multi-model Large Language Models (MLLMs), including mPLUG-Owl, have demonstrated promising zero-shot capabilities in shallow OCR-free text recognition, indicating their potential for OCR-free document understanding. Nevertheless, without in-domain training, these models tend to ignore fine-grained OCR features, such as sophisticated tables or large blocks of text, which are essential for OCR-free document understanding. In this paper,","authors_text":"Anwen Hu, Chenliang Li, Chenlin Zhao, Fei Huang, Guohai Xu, Haiyang Xu, Jiabo Ye, Ji Zhang, Junfeng Tian, Ming Yan, Qian Qi, Qinghao Ye, Yuhao Dan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T11:28:07Z","title":"mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02499","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":"sha256:40d7e97c9ba5d0305ac44ad80a36aa54f5d6562ade9baa55a9565d2cc9cee5bb","target":"record","created_at":"2026-07-05T06:28:20Z","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":"eadaff09361df2302fd67597ce06f61214a6aac08478726fc88a6825f6fea7d0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-07-04T11:28:07Z","title_canon_sha256":"660be02768fcddfbd845514082783f256ec6745c224cdd42fbb6627eec5ffb06"},"schema_version":"1.0","source":{"id":"2307.02499","kind":"arxiv","version":1}},"canonical_sha256":"d5c0c57911275a35e8c70e9d2ec5f72035a8bc58c3aa53a7a8b0b8e15eaf5364","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5c0c57911275a35e8c70e9d2ec5f72035a8bc58c3aa53a7a8b0b8e15eaf5364","first_computed_at":"2026-07-05T06:28:20.807595Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:20.807595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P8QQnbCQIhMnDDfz4Z2TVdDw0rvDGkg/FMFdMgfqMAX3qzzoJ3CLME7ncoXGvXK0ixUZkEnJbKRMU+9b0LYmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:20.808137Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.02499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40d7e97c9ba5d0305ac44ad80a36aa54f5d6562ade9baa55a9565d2cc9cee5bb","sha256:4ea6fd4c8d530898e44f5f07c57c6f580ca5f19aac381c0a0e3ae8c320453c0e"],"state_sha256":"49e963b5bc586d9f7ab7d5b794ec79d1657e3d1625d9277725d8f3d3f68964c3"}