{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:453INXJZ5IZ56F3YCMYB2DA6CT","short_pith_number":"pith:453INXJZ","schema_version":"1.0","canonical_sha256":"e77686dd39ea33df177813301d0c1e14f308b8c33bd94b28e128c006be8da35b","source":{"kind":"arxiv","id":"2411.18159","version":2},"attestation_state":"computed","paper":{"title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Haraguchi, Hayato Mitani, Kota Yamaguchi, Naoto Inoue, Seiichi Uchida, Wataru Shimoda","submitted_at":"2024-11-27T09:11:45Z","abstract_excerpt":"While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-ima"},"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":"2411.18159","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T09:11:45Z","cross_cats_sorted":[],"title_canon_sha256":"a060669fadb944c5c97e44f6b8cce6259a3be13a1bc7412c685a295e11e2a96c","abstract_canon_sha256":"b5c9fcfd1fae5de80b3d5d7d3b28b8d2a78004a5f624f620b2de255bb3b7ca4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:56:12.675239Z","signature_b64":"tMYPJoNQCOdQG1FL7IswOkYLXWGJ8BzekR5dMr2Lx9QUKHyswWgB7ouiqp8Ex2pf5ARTaAgirjDnESaxsoa4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e77686dd39ea33df177813301d0c1e14f308b8c33bd94b28e128c006be8da35b","last_reissued_at":"2026-07-05T10:56:12.674702Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:56:12.674702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daichi Haraguchi, Hayato Mitani, Kota Yamaguchi, Naoto Inoue, Seiichi Uchida, Wataru Shimoda","submitted_at":"2024-11-27T09:11:45Z","abstract_excerpt":"While recent text-to-image models can generate photorealistic images from text prompts that reflect detailed instructions, they still face significant challenges in accurately rendering words in the image. In this paper, we propose to retouch erroneous text renderings in the post-processing pipeline. Our approach, called Type-R, identifies typographical errors in the generated image, erases the erroneous text, regenerates text boxes for missing words, and finally corrects typos in the rendered words. Through extensive experiments, we show that Type-R, in combination with the latest text-to-ima"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18159","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/2411.18159/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":"2411.18159","created_at":"2026-07-05T10:56:12.674769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18159v2","created_at":"2026-07-05T10:56:12.674769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18159","created_at":"2026-07-05T10:56:12.674769+00:00"},{"alias_kind":"pith_short_12","alias_value":"453INXJZ5IZ5","created_at":"2026-07-05T10:56:12.674769+00:00"},{"alias_kind":"pith_short_16","alias_value":"453INXJZ5IZ56F3Y","created_at":"2026-07-05T10:56:12.674769+00:00"},{"alias_kind":"pith_short_8","alias_value":"453INXJZ","created_at":"2026-07-05T10:56:12.674769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10077","citing_title":"DocRevive: A Unified Pipeline for Document Text Restoration","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10077","citing_title":"DocRevive: A Unified Pipeline for Document Text Restoration","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT","json":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT.json","graph_json":"https://pith.science/api/pith-number/453INXJZ5IZ56F3YCMYB2DA6CT/graph.json","events_json":"https://pith.science/api/pith-number/453INXJZ5IZ56F3YCMYB2DA6CT/events.json","paper":"https://pith.science/paper/453INXJZ"},"agent_actions":{"view_html":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT","download_json":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT.json","view_paper":"https://pith.science/paper/453INXJZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18159&json=true","fetch_graph":"https://pith.science/api/pith-number/453INXJZ5IZ56F3YCMYB2DA6CT/graph.json","fetch_events":"https://pith.science/api/pith-number/453INXJZ5IZ56F3YCMYB2DA6CT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT/action/storage_attestation","attest_author":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT/action/author_attestation","sign_citation":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT/action/citation_signature","submit_replication":"https://pith.science/pith/453INXJZ5IZ56F3YCMYB2DA6CT/action/replication_record"}},"created_at":"2026-07-05T10:56:12.674769+00:00","updated_at":"2026-07-05T10:56:12.674769+00:00"}