{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KYQTR6AAAAEEFJSNB42VI3UWQV","short_pith_number":"pith:KYQTR6AA","schema_version":"1.0","canonical_sha256":"562138f800000842a64d0f35546e968550ebd9a7535d49856efd4891d25f5990","source":{"kind":"arxiv","id":"2407.14138","version":2},"attestation_state":"computed","paper":{"title":"Visual Text Generation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Yao, Fei Huang, Feiyu Gao, Jiawei Liu, Peng Wang, Wenyu Liu, Xinggang Wang, Yuanzhi Zhu, Zhibo Yang","submitted_at":"2024-07-19T09:08:20Z","abstract_excerpt":"Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (e.g., text de"},"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":"2407.14138","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-19T09:08:20Z","cross_cats_sorted":[],"title_canon_sha256":"435a2f10807f0c3fbaad57ba7005522883e3a750260f1fecbe79839e9a07e296","abstract_canon_sha256":"134b5026fa0cc62fbf59badab7fd9fc89e324c6569271500ab444562b08551cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:19.195836Z","signature_b64":"I77RaajLhpVfKptCcgZUsWLYV9w0uFNzMbCPfKRpPvY9P0VVcUx8R4DHo+vIYIe3wpoplQNsJzkMHOmPdLoLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"562138f800000842a64d0f35546e968550ebd9a7535d49856efd4891d25f5990","last_reissued_at":"2026-07-05T09:30:19.195313Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:19.195313Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Text Generation in the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cong Yao, Fei Huang, Feiyu Gao, Jiawei Liu, Peng Wang, Wenyu Liu, Xinggang Wang, Yuanzhi Zhu, Zhibo Yang","submitted_at":"2024-07-19T09:08:20Z","abstract_excerpt":"Recently, with the rapid advancements of generative models, the field of visual text generation has witnessed significant progress. However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (e.g., text de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.14138","kind":"arxiv","version":2},"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/2407.14138/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":"2407.14138","created_at":"2026-07-05T09:30:19.195381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.14138v2","created_at":"2026-07-05T09:30:19.195381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.14138","created_at":"2026-07-05T09:30:19.195381+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYQTR6AAAAEE","created_at":"2026-07-05T09:30:19.195381+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYQTR6AAAAEEFJSN","created_at":"2026-07-05T09:30:19.195381+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYQTR6AA","created_at":"2026-07-05T09:30:19.195381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03799","citing_title":"ConText: Driving In-context Learning for Text Removal and Segmentation","ref_index":96,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV","json":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV.json","graph_json":"https://pith.science/api/pith-number/KYQTR6AAAAEEFJSNB42VI3UWQV/graph.json","events_json":"https://pith.science/api/pith-number/KYQTR6AAAAEEFJSNB42VI3UWQV/events.json","paper":"https://pith.science/paper/KYQTR6AA"},"agent_actions":{"view_html":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV","download_json":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV.json","view_paper":"https://pith.science/paper/KYQTR6AA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.14138&json=true","fetch_graph":"https://pith.science/api/pith-number/KYQTR6AAAAEEFJSNB42VI3UWQV/graph.json","fetch_events":"https://pith.science/api/pith-number/KYQTR6AAAAEEFJSNB42VI3UWQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV/action/storage_attestation","attest_author":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV/action/author_attestation","sign_citation":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV/action/citation_signature","submit_replication":"https://pith.science/pith/KYQTR6AAAAEEFJSNB42VI3UWQV/action/replication_record"}},"created_at":"2026-07-05T09:30:19.195381+00:00","updated_at":"2026-07-05T09:30:19.195381+00:00"}