{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3XJZHRV7TXE7E44FMHVSYVYUS","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":"96a1fd89f493f2660bd4c0036a803e2af4600b73eba4d679e7159c497f76e3d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:55:33Z","title_canon_sha256":"6493ad88523f5ee25cebcfba7f2b822f08976edd320143a84d76d159ce5f8ba8"},"schema_version":"1.0","source":{"id":"2403.09622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.09622","created_at":"2026-07-05T08:43:09Z"},{"alias_kind":"arxiv_version","alias_value":"2403.09622v2","created_at":"2026-07-05T08:43:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.09622","created_at":"2026-07-05T08:43:09Z"},{"alias_kind":"pith_short_12","alias_value":"Q3XJZHRV7TXE","created_at":"2026-07-05T08:43:09Z"},{"alias_kind":"pith_short_16","alias_value":"Q3XJZHRV7TXE7E44","created_at":"2026-07-05T08:43:09Z"},{"alias_kind":"pith_short_8","alias_value":"Q3XJZHRV","created_at":"2026-07-05T08:43:09Z"}],"graph_snapshots":[{"event_id":"sha256:954c38f70c1dafae5c879c5572d2cfc4e9e50f98fe08c9d1d63b9d244b2a7f74","target":"graph","created_at":"2026-07-05T08:43:09Z","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/2403.09622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chong Luo, Gao Huang, Ji Li, Weicong Liang, Yuhui Yuan, Zeyu Liu, Zhanhao Liang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:55:33Z","title":"Glyph-ByT5: A Customized Text Encoder for Accurate Visual Text Rendering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.09622","kind":"arxiv","version":2},"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":"sha256:195706045dc5f02759ad7fcb76888000775d51d66895e2a6f7119a1ccc7c5b50","target":"record","created_at":"2026-07-05T08:43:09Z","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":"96a1fd89f493f2660bd4c0036a803e2af4600b73eba4d679e7159c497f76e3d6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-14T17:55:33Z","title_canon_sha256":"6493ad88523f5ee25cebcfba7f2b822f08976edd320143a84d76d159ce5f8ba8"},"schema_version":"1.0","source":{"id":"2403.09622","kind":"arxiv","version":2}},"canonical_sha256":"86ee9c9e35fcee4f939c2b0f5962b8a4a2332fba8fcbb62569e2f5d9e99633e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86ee9c9e35fcee4f939c2b0f5962b8a4a2332fba8fcbb62569e2f5d9e99633e7","first_computed_at":"2026-07-05T08:43:09.208051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:09.208051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k87n+6vcptu9EJjFsndfEF/xOyWczh8aASwUXdRsXf3mas552AwMnbUkphSmSvlU/dVg207dFuGKQYQjQtuGBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:09.208508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.09622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:195706045dc5f02759ad7fcb76888000775d51d66895e2a6f7119a1ccc7c5b50","sha256:954c38f70c1dafae5c879c5572d2cfc4e9e50f98fe08c9d1d63b9d244b2a7f74"],"state_sha256":"b6a31d14be1b734b78e3f98060e4dc4abbd03b4cce084e8627f3763b7cff23f8"}