{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3XJZHRV7TXE7E44FMHVSYVYUS","short_pith_number":"pith:Q3XJZHRV","schema_version":"1.0","canonical_sha256":"86ee9c9e35fcee4f939c2b0f5962b8a4a2332fba8fcbb62569e2f5d9e99633e7","source":{"kind":"arxiv","id":"2403.09622","version":2},"attestation_state":"computed","paper":{"title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Gao Huang, Ji Li, Weicong Liang, Yuhui Yuan, Zeyu Liu, Zhanhao Liang","submitted_at":"2024-03-14T17:55:33Z","abstract_excerpt":"Visual text rendering poses a fundamental challenge for contemporary text-to-image generation models, with the core problem lying in text encoder deficiencies. To achieve accurate text rendering, we identify two crucial requirements for text encoders: character awareness and alignment with glyphs. Our solution involves crafting a series of customized text encoder, Glyph-ByT5, by fine-tuning the character-aware ByT5 encoder using a meticulously curated paired glyph-text dataset. We present an effective method for integrating Glyph-ByT5 with SDXL, resulting in the creation of the Glyph-SDXL mode"},"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":"2403.09622","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:55:33Z","cross_cats_sorted":[],"title_canon_sha256":"6493ad88523f5ee25cebcfba7f2b822f08976edd320143a84d76d159ce5f8ba8","abstract_canon_sha256":"96a1fd89f493f2660bd4c0036a803e2af4600b73eba4d679e7159c497f76e3d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:09.208508Z","signature_b64":"k87n+6vcptu9EJjFsndfEF/xOyWczh8aASwUXdRsXf3mas552AwMnbUkphSmSvlU/dVg207dFuGKQYQjQtuGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86ee9c9e35fcee4f939c2b0f5962b8a4a2332fba8fcbb62569e2f5d9e99633e7","last_reissued_at":"2026-07-05T08:43:09.208051Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:09.208051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chong Luo, Gao Huang, Ji Li, Weicong Liang, Yuhui Yuan, Zeyu Liu, Zhanhao Liang","submitted_at":"2024-03-14T17:55:33Z","abstract_excerpt":"Visual text rendering poses a fundamental challenge for contemporary text-to-image generation models, with the core problem lying in text encoder deficiencies. To achieve accurate text rendering, we identify two crucial requirements for text encoders: character awareness and alignment with glyphs. Our solution involves crafting a series of customized text encoder, Glyph-ByT5, by fine-tuning the character-aware ByT5 encoder using a meticulously curated paired glyph-text dataset. We present an effective method for integrating Glyph-ByT5 with SDXL, resulting in the creation of the Glyph-SDXL mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09622","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/2403.09622/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":"2403.09622","created_at":"2026-07-05T08:43:09.208108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.09622v2","created_at":"2026-07-05T08:43:09.208108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09622","created_at":"2026-07-05T08:43:09.208108+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3XJZHRV7TXE","created_at":"2026-07-05T08:43:09.208108+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3XJZHRV7TXE7E44","created_at":"2026-07-05T08:43:09.208108+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3XJZHRV","created_at":"2026-07-05T08:43:09.208108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14708","citing_title":"StyleTextGen: Style-Conditioned Multilingual Scene Text Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18870","citing_title":"HunyuanVideo 1.5 Technical Report","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS","json":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS.json","graph_json":"https://pith.science/api/pith-number/Q3XJZHRV7TXE7E44FMHVSYVYUS/graph.json","events_json":"https://pith.science/api/pith-number/Q3XJZHRV7TXE7E44FMHVSYVYUS/events.json","paper":"https://pith.science/paper/Q3XJZHRV"},"agent_actions":{"view_html":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS","download_json":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS.json","view_paper":"https://pith.science/paper/Q3XJZHRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.09622&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3XJZHRV7TXE7E44FMHVSYVYUS/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3XJZHRV7TXE7E44FMHVSYVYUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS/action/storage_attestation","attest_author":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS/action/author_attestation","sign_citation":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS/action/citation_signature","submit_replication":"https://pith.science/pith/Q3XJZHRV7TXE7E44FMHVSYVYUS/action/replication_record"}},"created_at":"2026-07-05T08:43:09.208108+00:00","updated_at":"2026-07-05T08:43:09.208108+00:00"}