{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E2Q6H4VVIN4QTLKCMA4TCTZMYM","short_pith_number":"pith:E2Q6H4VV","schema_version":"1.0","canonical_sha256":"26a1e3f2b5437909ad426039314f2cc321119f3c47612dcfd3ece22551370e20","source":{"kind":"arxiv","id":"2505.06543","version":1},"attestation_state":"computed","paper":{"title":"HDGlyph: A Hierarchical Disentangled Glyph-Based Framework for Long-Tail Text Rendering in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Lei, Fengyi Fu, Mengqi Huang, Nan Chen, Shuhan Zhuang, Zhendong Mao","submitted_at":"2025-05-10T07:05:43Z","abstract_excerpt":"Visual text rendering, which aims to accurately integrate specified textual content within generated images, is critical for various applications such as commercial design. Despite recent advances, current methods struggle with long-tail text cases, particularly when handling unseen or small-sized text. In this work, we propose a novel Hierarchical Disentangled Glyph-Based framework (HDGlyph) that hierarchically decouples text generation from non-text visual synthesis, enabling joint optimization of both common and long-tail text rendering. At the training stage, HDGlyph disentangles pixel-lev"},"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":"2505.06543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-10T07:05:43Z","cross_cats_sorted":[],"title_canon_sha256":"fd28718d21edcb02538cbb747676c69dc2bf42c2305d8432895e0f78e5c494ee","abstract_canon_sha256":"815f17fb22d209ebb95b8cd30577bb293f44c98bf5aab043a380b76dd26a7d62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:11.859134Z","signature_b64":"IgjsLIvcnjQAjDm+EfNcU6Im8lFrWigrC9tIdCWZjTM5XIvN18NYa1k/qTSZjbhdGMUQ8huM4cqgmNPVb3NbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26a1e3f2b5437909ad426039314f2cc321119f3c47612dcfd3ece22551370e20","last_reissued_at":"2026-07-05T11:01:11.858640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:11.858640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HDGlyph: A Hierarchical Disentangled Glyph-Based Framework for Long-Tail Text Rendering in Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Lei, Fengyi Fu, Mengqi Huang, Nan Chen, Shuhan Zhuang, Zhendong Mao","submitted_at":"2025-05-10T07:05:43Z","abstract_excerpt":"Visual text rendering, which aims to accurately integrate specified textual content within generated images, is critical for various applications such as commercial design. Despite recent advances, current methods struggle with long-tail text cases, particularly when handling unseen or small-sized text. In this work, we propose a novel Hierarchical Disentangled Glyph-Based framework (HDGlyph) that hierarchically decouples text generation from non-text visual synthesis, enabling joint optimization of both common and long-tail text rendering. At the training stage, HDGlyph disentangles pixel-lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.06543","kind":"arxiv","version":1},"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/2505.06543/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":"2505.06543","created_at":"2026-07-05T11:01:11.858698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.06543v1","created_at":"2026-07-05T11:01:11.858698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.06543","created_at":"2026-07-05T11:01:11.858698+00:00"},{"alias_kind":"pith_short_12","alias_value":"E2Q6H4VVIN4Q","created_at":"2026-07-05T11:01:11.858698+00:00"},{"alias_kind":"pith_short_16","alias_value":"E2Q6H4VVIN4QTLKC","created_at":"2026-07-05T11:01:11.858698+00:00"},{"alias_kind":"pith_short_8","alias_value":"E2Q6H4VV","created_at":"2026-07-05T11:01:11.858698+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12280","citing_title":"Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUs","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM","json":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM.json","graph_json":"https://pith.science/api/pith-number/E2Q6H4VVIN4QTLKCMA4TCTZMYM/graph.json","events_json":"https://pith.science/api/pith-number/E2Q6H4VVIN4QTLKCMA4TCTZMYM/events.json","paper":"https://pith.science/paper/E2Q6H4VV"},"agent_actions":{"view_html":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM","download_json":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM.json","view_paper":"https://pith.science/paper/E2Q6H4VV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.06543&json=true","fetch_graph":"https://pith.science/api/pith-number/E2Q6H4VVIN4QTLKCMA4TCTZMYM/graph.json","fetch_events":"https://pith.science/api/pith-number/E2Q6H4VVIN4QTLKCMA4TCTZMYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM/action/storage_attestation","attest_author":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM/action/author_attestation","sign_citation":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM/action/citation_signature","submit_replication":"https://pith.science/pith/E2Q6H4VVIN4QTLKCMA4TCTZMYM/action/replication_record"}},"created_at":"2026-07-05T11:01:11.858698+00:00","updated_at":"2026-07-05T11:01:11.858698+00:00"}