{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2KYZB4JPMIRUT4576YXBZKGD5H","short_pith_number":"pith:2KYZB4JP","schema_version":"1.0","canonical_sha256":"d2b190f12f622349f3bff62e1ca8c3e9d65e5bfd2814eee311c20a8f6db9f328","source":{"kind":"arxiv","id":"2405.21013","version":3},"attestation_state":"computed","paper":{"title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Hao Zhou, Jingdong Wang, Kun Yao, Liang Wu, Pengyuan Lyu, Qunyi Xie, Weihong Ma, Xingyu Wan, Yulin Li","submitted_at":"2024-05-31T16:55:04Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.21013","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-31T16:55:04Z","cross_cats_sorted":[],"title_canon_sha256":"dee7e6265614e71526aa10e2b7a9f7c2b69723c8c8fe38c04ce9fd8657d7a890","abstract_canon_sha256":"1869facb6d41b427d17527fd2d3c921c55039eb5b0865158cf96fe4078aab16c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:27:09.460993Z","signature_b64":"1T5muSJDgR1WORKJNmy8VFwgt/VYbTIf/dFSxqPSxmX/JBcvdUgjJScwtK8Ea7d9Auw+tk8rIB0xulTOVbY1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2b190f12f622349f3bff62e1ca8c3e9d65e5bfd2814eee311c20a8f6db9f328","last_reissued_at":"2026-07-05T08:27:09.460546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:27:09.460546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengquan Zhang, Errui Ding, Hao Zhou, Jingdong Wang, Kun Yao, Liang Wu, Pengyuan Lyu, Qunyi Xie, Weihong Ma, Xingyu Wan, Yulin Li","submitted_at":"2024-05-31T16:55:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.21013","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2405.21013/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.21013","created_at":"2026-07-05T08:27:09.460600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.21013v3","created_at":"2026-07-05T08:27:09.460600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.21013","created_at":"2026-07-05T08:27:09.460600+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KYZB4JPMIRU","created_at":"2026-07-05T08:27:09.460600+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KYZB4JPMIRUT457","created_at":"2026-07-05T08:27:09.460600+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KYZB4JP","created_at":"2026-07-05T08:27:09.460600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.09861","citing_title":"A Survey on MLLM-based Visually Rich Document Understanding: Methods, Challenges, and Emerging Trends","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H","json":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H.json","graph_json":"https://pith.science/api/pith-number/2KYZB4JPMIRUT4576YXBZKGD5H/graph.json","events_json":"https://pith.science/api/pith-number/2KYZB4JPMIRUT4576YXBZKGD5H/events.json","paper":"https://pith.science/paper/2KYZB4JP"},"agent_actions":{"view_html":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H","download_json":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H.json","view_paper":"https://pith.science/paper/2KYZB4JP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.21013&json=true","fetch_graph":"https://pith.science/api/pith-number/2KYZB4JPMIRUT4576YXBZKGD5H/graph.json","fetch_events":"https://pith.science/api/pith-number/2KYZB4JPMIRUT4576YXBZKGD5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H/action/storage_attestation","attest_author":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H/action/author_attestation","sign_citation":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H/action/citation_signature","submit_replication":"https://pith.science/pith/2KYZB4JPMIRUT4576YXBZKGD5H/action/replication_record"}},"created_at":"2026-07-05T08:27:09.460600+00:00","updated_at":"2026-07-05T08:27:09.460600+00:00"}