{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ADMA5NN7TM6JTOUYIBTY5XH3WV","short_pith_number":"pith:ADMA5NN7","schema_version":"1.0","canonical_sha256":"00d80eb5bf9b3c99ba9840678edcfbb54c27c61c7f90fd4a89bb99a25d862d1b","source":{"kind":"arxiv","id":"2304.05568","version":1},"attestation_state":"computed","paper":{"title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bairu Hou, Brian Price, Guanhua Zhang, Jiabao Ji, Shiyu Chang, Zhaowen Wang, Zhifei Zhang","submitted_at":"2023-04-12T02:08:34Z","abstract_excerpt":"Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop out text regions and feed them into image transfer models, such as GANs. However, these methods are limited in their ability to change text style and are unable to insert texts into images. Recent advances in diffusion models have shown promise in overcoming these limitations with text-conditional image editing. However, our empirical analysis reveals that s"},"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":"2304.05568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-12T02:08:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbd4e246dca5849051b0d546a61561390f1f90c40c5ac0d8e6256ef860ddf57f","abstract_canon_sha256":"7b1e37218408b71a7382e4e773ef3793b53205aa20d3e0fca5b135269459b878"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:00:20.464304Z","signature_b64":"Bq7SvQh/OinNS6GUF1gSefcjKBO/qfJQmkk4IMVx7OadZV3TSp1vaBejpcCDIIuaQwrZ4OO3lcUe42uvyW+IAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00d80eb5bf9b3c99ba9840678edcfbb54c27c61c7f90fd4a89bb99a25d862d1b","last_reissued_at":"2026-07-05T06:00:20.463891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:00:20.463891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Diffusion Models for Scene Text Editing with Dual Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bairu Hou, Brian Price, Guanhua Zhang, Jiabao Ji, Shiyu Chang, Zhaowen Wang, Zhifei Zhang","submitted_at":"2023-04-12T02:08:34Z","abstract_excerpt":"Scene text editing is a challenging task that involves modifying or inserting specified texts in an image while maintaining its natural and realistic appearance. Most previous approaches to this task rely on style-transfer models that crop out text regions and feed them into image transfer models, such as GANs. However, these methods are limited in their ability to change text style and are unable to insert texts into images. Recent advances in diffusion models have shown promise in overcoming these limitations with text-conditional image editing. However, our empirical analysis reveals that s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05568","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/2304.05568/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":"2304.05568","created_at":"2026-07-05T06:00:20.463952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05568v1","created_at":"2026-07-05T06:00:20.463952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05568","created_at":"2026-07-05T06:00:20.463952+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADMA5NN7TM6J","created_at":"2026-07-05T06:00:20.463952+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADMA5NN7TM6JTOUY","created_at":"2026-07-05T06:00:20.463952+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADMA5NN7","created_at":"2026-07-05T06:00:20.463952+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05730","citing_title":"TextWand: A Unified Framework for Scene Text Editing","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2511.13285","citing_title":"SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24171","citing_title":"POCA: Pareto-Optimal Curriculum Alignment for Visual Text Generation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV","json":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV.json","graph_json":"https://pith.science/api/pith-number/ADMA5NN7TM6JTOUYIBTY5XH3WV/graph.json","events_json":"https://pith.science/api/pith-number/ADMA5NN7TM6JTOUYIBTY5XH3WV/events.json","paper":"https://pith.science/paper/ADMA5NN7"},"agent_actions":{"view_html":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV","download_json":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV.json","view_paper":"https://pith.science/paper/ADMA5NN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05568&json=true","fetch_graph":"https://pith.science/api/pith-number/ADMA5NN7TM6JTOUYIBTY5XH3WV/graph.json","fetch_events":"https://pith.science/api/pith-number/ADMA5NN7TM6JTOUYIBTY5XH3WV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV/action/storage_attestation","attest_author":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV/action/author_attestation","sign_citation":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV/action/citation_signature","submit_replication":"https://pith.science/pith/ADMA5NN7TM6JTOUYIBTY5XH3WV/action/replication_record"}},"created_at":"2026-07-05T06:00:20.463952+00:00","updated_at":"2026-07-05T06:00:20.463952+00:00"}