{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q36PWC7UPIJS7X2S46IP222XIB","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":"14060a8af09edd087968e0dedd154fdc810182d3271c10c69a1bddc139eeb517","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T03:43:21Z","title_canon_sha256":"c57e5ad76ce9d8ee54660ce1516ff67260ac0308bb40ba9489b352a638c72e75"},"schema_version":"1.0","source":{"id":"2503.04065","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.04065","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"arxiv_version","alias_value":"2503.04065v3","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04065","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_12","alias_value":"Q36PWC7UPIJS","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_16","alias_value":"Q36PWC7UPIJS7X2S","created_at":"2026-07-05T11:27:24Z"},{"alias_kind":"pith_short_8","alias_value":"Q36PWC7U","created_at":"2026-07-05T11:27:24Z"}],"graph_snapshots":[{"event_id":"sha256:8f14ca124a5ba8bbe6057f6644e201b1393320c73daf2f29af22389f6db316c4","target":"graph","created_at":"2026-07-05T11:27:24Z","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/2503.04065/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancement of digitalization, various document images are being applied more extensively in production and daily life, and there is an increasingly urgent need for fast and accurate parsing of the content in document images. Therefore, this report presents PP-DocBee, a novel multimodal large language model designed for end-to-end document image understanding. First, we develop a data synthesis strategy tailored to document scenarios in which we build a diverse dataset to improve the model generalization. Then, we apply a few training techniques, including dynamic proportional s","authors_text":"Feng Ni, Guanzhong Wang, Kui Huang, Wenyu Lv, Yao Lu, Yi Liu, Zeyu Chen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T03:43:21Z","title":"PP-DocBee: Improving Multimodal Document Understanding Through a Bag of Tricks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04065","kind":"arxiv","version":3},"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":"sha256:99fb2c79d2f0cf55ffc11bb9872cbcb2dec5afd83640cd805d75c33a9b9eb630","target":"record","created_at":"2026-07-05T11:27:24Z","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":"14060a8af09edd087968e0dedd154fdc810182d3271c10c69a1bddc139eeb517","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-06T03:43:21Z","title_canon_sha256":"c57e5ad76ce9d8ee54660ce1516ff67260ac0308bb40ba9489b352a638c72e75"},"schema_version":"1.0","source":{"id":"2503.04065","kind":"arxiv","version":3}},"canonical_sha256":"86fcfb0bf47a132fdf52e790fd6b574067816c41620f49ce7891aae59e9eab7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86fcfb0bf47a132fdf52e790fd6b574067816c41620f49ce7891aae59e9eab7a","first_computed_at":"2026-07-05T11:27:24.832206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:24.832206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V+l2KHG0KDWleYBIAKdBxdUOxTKRSaodTRPAv9WzLXUD1iruphnoVDh8FYIq/1RnrEcB/cRTxSOuSlDDh03NCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:24.832814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.04065","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99fb2c79d2f0cf55ffc11bb9872cbcb2dec5afd83640cd805d75c33a9b9eb630","sha256:8f14ca124a5ba8bbe6057f6644e201b1393320c73daf2f29af22389f6db316c4"],"state_sha256":"04bb5e8dc0b9147a9189487af175c267986d2b71bd642f272b3916b8b4102400"}