{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KYZB4JPMIRUT4576YXBZKGD5H","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":"1869facb6d41b427d17527fd2d3c921c55039eb5b0865158cf96fe4078aab16c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T16:55:04Z","title_canon_sha256":"dee7e6265614e71526aa10e2b7a9f7c2b69723c8c8fe38c04ce9fd8657d7a890"},"schema_version":"1.0","source":{"id":"2405.21013","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.21013","created_at":"2026-07-05T08:27:09Z"},{"alias_kind":"arxiv_version","alias_value":"2405.21013v3","created_at":"2026-07-05T08:27:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21013","created_at":"2026-07-05T08:27:09Z"},{"alias_kind":"pith_short_12","alias_value":"2KYZB4JPMIRU","created_at":"2026-07-05T08:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"2KYZB4JPMIRUT457","created_at":"2026-07-05T08:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"2KYZB4JP","created_at":"2026-07-05T08:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:5239768ddb204b022b1fe06242900b697b75d021aa7fc4d64b0d8586a2f0be4f","target":"graph","created_at":"2026-07-05T08:27:09Z","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/2405.21013/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images play crucial roles in information transmission but are accompanied by diverse challenges. Therefore, the efficient and effective understanding of text-rich images is a crucial litmus test for the capability of Vision-Language Models. We have crafted an efficient vision-language model, StrucTexTv3, tailored to tackle various intelligent tasks for text-rich images. The significant design of StrucTexTv3 is presented in th","authors_text":"Chengquan Zhang, Errui Ding, Hao Zhou, Jingdong Wang, Kun Yao, Liang Wu, Pengyuan Lyu, Qunyi Xie, Weihong Ma, Xingyu Wan, Yulin Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T16:55:04Z","title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21013","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:e9cad49bba424aa9bd20b7f2fd6dcd2e81764eb5321b1d55e81796cc838630c9","target":"record","created_at":"2026-07-05T08:27:09Z","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":"1869facb6d41b427d17527fd2d3c921c55039eb5b0865158cf96fe4078aab16c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T16:55:04Z","title_canon_sha256":"dee7e6265614e71526aa10e2b7a9f7c2b69723c8c8fe38c04ce9fd8657d7a890"},"schema_version":"1.0","source":{"id":"2405.21013","kind":"arxiv","version":3}},"canonical_sha256":"d2b190f12f622349f3bff62e1ca8c3e9d65e5bfd2814eee311c20a8f6db9f328","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2b190f12f622349f3bff62e1ca8c3e9d65e5bfd2814eee311c20a8f6db9f328","first_computed_at":"2026-07-05T08:27:09.460546Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:09.460546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1T5muSJDgR1WORKJNmy8VFwgt/VYbTIf/dFSxqPSxmX/JBcvdUgjJScwtK8Ea7d9Auw+tk8rIB0xulTOVbY1Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:09.460993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.21013","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9cad49bba424aa9bd20b7f2fd6dcd2e81764eb5321b1d55e81796cc838630c9","sha256:5239768ddb204b022b1fe06242900b697b75d021aa7fc4d64b0d8586a2f0be4f"],"state_sha256":"53a76044e76424814ac228227643d5c8c33b01b9d5aaf6f79efc656d78bb183a"}