{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7GGXPAKEZKDGETOV6AWT7WAKGO","short_pith_number":"pith:7GGXPAKE","schema_version":"1.0","canonical_sha256":"f98d778144ca86624dd5f02d3fd80a339a495aca7ac77ca028231e498ece17c1","source":{"kind":"arxiv","id":"2507.00992","version":2},"attestation_state":"computed","paper":{"title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Cong Han, Liu Lin, Shuanglong Li, Sinan Du, Wen Tao, Xiawei Li, Yafei Li, Yi Yang, Yuanrui Wang, Zhipeng Jin","submitted_at":"2025-07-01T17:42:19Z","abstract_excerpt":"Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited style control. Existing methods often rely on pre-rendered glyph images as conditions, but these struggle to retain original font styles and color cues, necessitating complex multi-branch designs that increase model overhead and reduce flexibility. To address these issues, we propose a segmentation-guided framework that uses pixel-level visual text masks -- rich in glyph shape, color, and spatial detail -- as unified con"},"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":"2507.00992","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-01T17:42:19Z","cross_cats_sorted":[],"title_canon_sha256":"711377d33f9c01894f515d79afbb184d84cd82be2d9249ad80f82170ed6e8748","abstract_canon_sha256":"341951cf25e324439aab9dbbec29b137f28e0f485c16ffc77c8f7e09c66d467c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:46.354527Z","signature_b64":"IZOHGg6k+eqBcRp1WAgEEG8Q/k5kx7YiN9Y/eRVn5HShikbZbFH8qNVc8Ng+VLoy89h1cqoLtQOEW9ODm04iBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f98d778144ca86624dd5f02d3fd80a339a495aca7ac77ca028231e498ece17c1","last_reissued_at":"2026-07-05T11:30:46.353957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:46.353957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chun Yuan, Cong Han, Liu Lin, Shuanglong Li, Sinan Du, Wen Tao, Xiawei Li, Yafei Li, Yi Yang, Yuanrui Wang, Zhipeng Jin","submitted_at":"2025-07-01T17:42:19Z","abstract_excerpt":"Text-to-image generation has greatly advanced content creation, yet accurately rendering visual text remains a key challenge due to blurred glyphs, semantic drift, and limited style control. Existing methods often rely on pre-rendered glyph images as conditions, but these struggle to retain original font styles and color cues, necessitating complex multi-branch designs that increase model overhead and reduce flexibility. To address these issues, we propose a segmentation-guided framework that uses pixel-level visual text masks -- rich in glyph shape, color, and spatial detail -- as unified con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00992","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/2507.00992/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":"2507.00992","created_at":"2026-07-05T11:30:46.354017+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.00992v2","created_at":"2026-07-05T11:30:46.354017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00992","created_at":"2026-07-05T11:30:46.354017+00:00"},{"alias_kind":"pith_short_12","alias_value":"7GGXPAKEZKDG","created_at":"2026-07-05T11:30:46.354017+00:00"},{"alias_kind":"pith_short_16","alias_value":"7GGXPAKEZKDGETOV","created_at":"2026-07-05T11:30:46.354017+00:00"},{"alias_kind":"pith_short_8","alias_value":"7GGXPAKE","created_at":"2026-07-05T11:30:46.354017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO","json":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO.json","graph_json":"https://pith.science/api/pith-number/7GGXPAKEZKDGETOV6AWT7WAKGO/graph.json","events_json":"https://pith.science/api/pith-number/7GGXPAKEZKDGETOV6AWT7WAKGO/events.json","paper":"https://pith.science/paper/7GGXPAKE"},"agent_actions":{"view_html":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO","download_json":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO.json","view_paper":"https://pith.science/paper/7GGXPAKE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.00992&json=true","fetch_graph":"https://pith.science/api/pith-number/7GGXPAKEZKDGETOV6AWT7WAKGO/graph.json","fetch_events":"https://pith.science/api/pith-number/7GGXPAKEZKDGETOV6AWT7WAKGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO/action/storage_attestation","attest_author":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO/action/author_attestation","sign_citation":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO/action/citation_signature","submit_replication":"https://pith.science/pith/7GGXPAKEZKDGETOV6AWT7WAKGO/action/replication_record"}},"created_at":"2026-07-05T11:30:46.354017+00:00","updated_at":"2026-07-05T11:30:46.354017+00:00"}