{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JVYF24XJ45EBAWLLB2HBONXLZ4","short_pith_number":"pith:JVYF24XJ","schema_version":"1.0","canonical_sha256":"4d705d72e9e74810596b0e8e1736ebcf133d93a0e4b0de99fb468332f32bd523","source":{"kind":"arxiv","id":"2510.16325","version":3},"attestation_state":"computed","paper":{"title":"UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yu-Wing Tai, Yuyao Zhang","submitted_at":"2025-10-18T03:15:26Z","abstract_excerpt":"Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined to sub 2MP (< $1K\\times2K$) resolutions due to the quadratic complexity of attention mechanisms and the scarcity of high-quality high-resolution training data. We present UltraImageGen, a novel framework that introduces hierarchical local attention with low-resolution global guidance, enabling efficient, scalable, and semantically coherent image synthesis at "},"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":"2510.16325","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-18T03:15:26Z","cross_cats_sorted":[],"title_canon_sha256":"f52d27469e90e6bd7320628bdc46ac01e5ae793896a7d4bfe1d97b73120218f0","abstract_canon_sha256":"612fd2a8669800ae314f3a7867a9d48a55843ad9f65c93aefa74544a5fdf175d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:18:17.796155Z","signature_b64":"jcUSHIH2iD3bslSY4Ez7Rk+Kz4xdnsUB2zvm5xx7eGtPzGqwbIYdVxZEVj3RqT0tIiAVb/CTNhmxe62vB8xYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d705d72e9e74810596b0e8e1736ebcf133d93a0e4b0de99fb468332f32bd523","last_reissued_at":"2026-06-30T01:18:17.795377Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:18:17.795377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yu-Wing Tai, Yuyao Zhang","submitted_at":"2025-10-18T03:15:26Z","abstract_excerpt":"Ultra-high-resolution text-to-image generation is increasingly vital for applications requiring fine-grained textures and global structural fidelity, yet state-of-the-art text-to-image diffusion models such as FLUX and SD3 remain confined to sub 2MP (< $1K\\times2K$) resolutions due to the quadratic complexity of attention mechanisms and the scarcity of high-quality high-resolution training data. We present UltraImageGen, a novel framework that introduces hierarchical local attention with low-resolution global guidance, enabling efficient, scalable, and semantically coherent image synthesis at "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.16325","kind":"arxiv","version":3},"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/2510.16325/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":"2510.16325","created_at":"2026-06-30T01:18:17.795487+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.16325v3","created_at":"2026-06-30T01:18:17.795487+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.16325","created_at":"2026-06-30T01:18:17.795487+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVYF24XJ45EB","created_at":"2026-06-30T01:18:17.795487+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVYF24XJ45EBAWLL","created_at":"2026-06-30T01:18:17.795487+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVYF24XJ","created_at":"2026-06-30T01:18:17.795487+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.17294","citing_title":"HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing","ref_index":76,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4","json":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4.json","graph_json":"https://pith.science/api/pith-number/JVYF24XJ45EBAWLLB2HBONXLZ4/graph.json","events_json":"https://pith.science/api/pith-number/JVYF24XJ45EBAWLLB2HBONXLZ4/events.json","paper":"https://pith.science/paper/JVYF24XJ"},"agent_actions":{"view_html":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4","download_json":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4.json","view_paper":"https://pith.science/paper/JVYF24XJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.16325&json=true","fetch_graph":"https://pith.science/api/pith-number/JVYF24XJ45EBAWLLB2HBONXLZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/JVYF24XJ45EBAWLLB2HBONXLZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4/action/storage_attestation","attest_author":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4/action/author_attestation","sign_citation":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4/action/citation_signature","submit_replication":"https://pith.science/pith/JVYF24XJ45EBAWLLB2HBONXLZ4/action/replication_record"}},"created_at":"2026-06-30T01:18:17.795487+00:00","updated_at":"2026-06-30T01:18:17.795487+00:00"}