{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6GVPMW3DOT7KHK4UORTJBYZMK2","short_pith_number":"pith:6GVPMW3D","schema_version":"1.0","canonical_sha256":"f1aaf65b6374fea3ab94746690e32c5692572b55611466a83e3c3e70f95b2af8","source":{"kind":"arxiv","id":"2403.16422","version":2},"attestation_state":"computed","paper":{"title":"Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aman Chadha, Man Luo, Sanyam Lakhanpal, Shivang Chopra, Vinija Jain","submitted_at":"2024-03-25T04:54:49Z","abstract_excerpt":"Over the past few years, Text-to-Image (T2I) generation approaches based on diffusion models have gained significant attention. However, vanilla diffusion models often suffer from spelling inaccuracies in the text displayed within the generated images. The capability to generate visual text is crucial, offering both academic interest and a wide range of practical applications. To produce accurate visual text images, state-of-the-art techniques adopt a glyph-controlled image generation approach, consisting of a text layout generator followed by an image generator that is conditioned on the gene"},"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":"2403.16422","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-25T04:54:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ca18037da363e400e4dffa6824ab33e8f9df025d93443433235c5bbc9cbba66b","abstract_canon_sha256":"bfdd8326885eb5689cbd3fe1ebfd8d3d455672e28be4eb6bbdb3570f18907295"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:21.104275Z","signature_b64":"UfdMLvdLuDXV7YeDoCEMldghzqtq9qf6xQMB3YpuSvqWlbhqeq28ZHS0sXlDh2CG0BnaFjSOT98TBGThFGcbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1aaf65b6374fea3ab94746690e32c5692572b55611466a83e3c3e70f95b2af8","last_reissued_at":"2026-07-05T09:27:21.103784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:21.103784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining Text-to-Image Generation: Towards Accurate Training-Free Glyph-Enhanced Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Aman Chadha, Man Luo, Sanyam Lakhanpal, Shivang Chopra, Vinija Jain","submitted_at":"2024-03-25T04:54:49Z","abstract_excerpt":"Over the past few years, Text-to-Image (T2I) generation approaches based on diffusion models have gained significant attention. However, vanilla diffusion models often suffer from spelling inaccuracies in the text displayed within the generated images. The capability to generate visual text is crucial, offering both academic interest and a wide range of practical applications. To produce accurate visual text images, state-of-the-art techniques adopt a glyph-controlled image generation approach, consisting of a text layout generator followed by an image generator that is conditioned on the gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16422","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/2403.16422/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":"2403.16422","created_at":"2026-07-05T09:27:21.103841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16422v2","created_at":"2026-07-05T09:27:21.103841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16422","created_at":"2026-07-05T09:27:21.103841+00:00"},{"alias_kind":"pith_short_12","alias_value":"6GVPMW3DOT7K","created_at":"2026-07-05T09:27:21.103841+00:00"},{"alias_kind":"pith_short_16","alias_value":"6GVPMW3DOT7KHK4U","created_at":"2026-07-05T09:27:21.103841+00:00"},{"alias_kind":"pith_short_8","alias_value":"6GVPMW3D","created_at":"2026-07-05T09:27:21.103841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.18159","citing_title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2","json":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2.json","graph_json":"https://pith.science/api/pith-number/6GVPMW3DOT7KHK4UORTJBYZMK2/graph.json","events_json":"https://pith.science/api/pith-number/6GVPMW3DOT7KHK4UORTJBYZMK2/events.json","paper":"https://pith.science/paper/6GVPMW3D"},"agent_actions":{"view_html":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2","download_json":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2.json","view_paper":"https://pith.science/paper/6GVPMW3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16422&json=true","fetch_graph":"https://pith.science/api/pith-number/6GVPMW3DOT7KHK4UORTJBYZMK2/graph.json","fetch_events":"https://pith.science/api/pith-number/6GVPMW3DOT7KHK4UORTJBYZMK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2/action/storage_attestation","attest_author":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2/action/author_attestation","sign_citation":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2/action/citation_signature","submit_replication":"https://pith.science/pith/6GVPMW3DOT7KHK4UORTJBYZMK2/action/replication_record"}},"created_at":"2026-07-05T09:27:21.103841+00:00","updated_at":"2026-07-05T09:27:21.103841+00:00"}