{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:H46VK4PFP7VHHCDW4FT6FYW7NJ","short_pith_number":"pith:H46VK4PF","schema_version":"1.0","canonical_sha256":"3f3d5571e57fea738876e167e2e2df6a765e92ee6d019fb72edcc273e9369e7b","source":{"kind":"arxiv","id":"2304.06720","version":4},"attestation_state":"computed","paper":{"title":"Expressive Text-to-Image Generation with Rich Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Jun-Yan Zhu, Songwei Ge, Taesung Park","submitted_at":"2023-04-13T17:59:55Z","abstract_excerpt":"Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each wo"},"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":"2304.06720","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-13T17:59:55Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"662cab1cb6ef0c94000e9452a8fd1ef36b5167c0a55e017583728f4a98e1d57f","abstract_canon_sha256":"ca7313f15cb518a0d6ed6e1cf6285f509839cc400b3c495de9d1320ce34baeba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:00.301838Z","signature_b64":"YwAegeGiZBQHuTqw6UqZbUIXmlDGBTsZ7nH6FTqeuclxYva4yvZ8elGKIGWzuK+XolXertWybzKkg7TEjaK6Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f3d5571e57fea738876e167e2e2df6a765e92ee6d019fb72edcc273e9369e7b","last_reissued_at":"2026-07-05T10:01:00.301406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:00.301406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Expressive Text-to-Image Generation with Rich Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Jia-Bin Huang, Jun-Yan Zhu, Songwei Ge, Taesung Park","submitted_at":"2023-04-13T17:59:55Z","abstract_excerpt":"Plain text has become a prevalent interface for text-to-image synthesis. However, its limited customization options hinder users from accurately describing desired outputs. For example, plain text makes it hard to specify continuous quantities, such as the precise RGB color value or importance of each word. Furthermore, creating detailed text prompts for complex scenes is tedious for humans to write and challenging for text encoders to interpret. To address these challenges, we propose using a rich-text editor supporting formats such as font style, size, color, and footnote. We extract each wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.06720","kind":"arxiv","version":4},"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/2304.06720/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":"2304.06720","created_at":"2026-07-05T10:01:00.301465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.06720v4","created_at":"2026-07-05T10:01:00.301465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.06720","created_at":"2026-07-05T10:01:00.301465+00:00"},{"alias_kind":"pith_short_12","alias_value":"H46VK4PFP7VH","created_at":"2026-07-05T10:01:00.301465+00:00"},{"alias_kind":"pith_short_16","alias_value":"H46VK4PFP7VHHCDW","created_at":"2026-07-05T10:01:00.301465+00:00"},{"alias_kind":"pith_short_8","alias_value":"H46VK4PF","created_at":"2026-07-05T10:01:00.301465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ","json":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ.json","graph_json":"https://pith.science/api/pith-number/H46VK4PFP7VHHCDW4FT6FYW7NJ/graph.json","events_json":"https://pith.science/api/pith-number/H46VK4PFP7VHHCDW4FT6FYW7NJ/events.json","paper":"https://pith.science/paper/H46VK4PF"},"agent_actions":{"view_html":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ","download_json":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ.json","view_paper":"https://pith.science/paper/H46VK4PF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.06720&json=true","fetch_graph":"https://pith.science/api/pith-number/H46VK4PFP7VHHCDW4FT6FYW7NJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H46VK4PFP7VHHCDW4FT6FYW7NJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ/action/storage_attestation","attest_author":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ/action/author_attestation","sign_citation":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ/action/citation_signature","submit_replication":"https://pith.science/pith/H46VK4PFP7VHHCDW4FT6FYW7NJ/action/replication_record"}},"created_at":"2026-07-05T10:01:00.301465+00:00","updated_at":"2026-07-05T10:01:00.301465+00:00"}