{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7SW5K7XMSCHTRPORNFIRGJXIXI","short_pith_number":"pith:7SW5K7XM","schema_version":"1.0","canonical_sha256":"fcadd57eec908f38bdd169511326e8ba1dbd76be62f4e8cfb552e1a55d029b41","source":{"kind":"arxiv","id":"2605.21090","version":1},"attestation_state":"computed","paper":{"title":"TextSculptor: Training and Benchmarking Scene Text Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Yu, Heyun Chen, Jinghuan Chen, Moran Li, Qi She, Siyu Jiao, Wei Zhou, Xiaohan Lan, Yao Zhao, Yiheng Lin, Yingchen Yu, Yujie Zhong, Yunchao Wei, Zhengwei Wang, Zijian Feng","submitted_at":"2026-05-20T12:22:26Z","abstract_excerpt":"Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data cons"},"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":"2605.21090","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T12:22:26Z","cross_cats_sorted":[],"title_canon_sha256":"5d43fd132f1c95d4a3f9735c9f962bccbbec76ec5128571a69a64fa5c9951a92","abstract_canon_sha256":"74091f88298f3d6362ce70b8334956cf06bfbcbddd99f780f0a943428c482c1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:36.642711Z","signature_b64":"ZL2wy6eaYw/6iO75n12JhOHoMLkF43F89jaUHh52YKKWT2EL/r4MsJBoUyV5VuiL0N/EiszV7D4E5IFM7DiDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcadd57eec908f38bdd169511326e8ba1dbd76be62f4e8cfb552e1a55d029b41","last_reissued_at":"2026-05-21T01:05:36.641763Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:36.641763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextSculptor: Training and Benchmarking Scene Text Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Yu, Heyun Chen, Jinghuan Chen, Moran Li, Qi She, Siyu Jiao, Wei Zhou, Xiaohan Lan, Yao Zhao, Yiheng Lin, Yingchen Yu, Yujie Zhong, Yunchao Wei, Zhengwei Wang, Zijian Feng","submitted_at":"2026-05-20T12:22:26Z","abstract_excerpt":"Recent advances in Multimodal Large Language Models (MLLMs) and diffusion-based generative models have substantially improved prompt-driven image editing. However, scene text editing remains challenging, as it requires models to precisely modify textual content while preserving visual realism and non-target regions. Current open-source models still lag behind proprietary systems, largely due to the scarcity of high-quality training data and the lack of standardized benchmarks tailored to text editing. To address these challenges, we present TextSculptor, a comprehensive framework for data cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21090","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/2605.21090/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":"2605.21090","created_at":"2026-05-21T01:05:36.641908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21090v1","created_at":"2026-05-21T01:05:36.641908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21090","created_at":"2026-05-21T01:05:36.641908+00:00"},{"alias_kind":"pith_short_12","alias_value":"7SW5K7XMSCHT","created_at":"2026-05-21T01:05:36.641908+00:00"},{"alias_kind":"pith_short_16","alias_value":"7SW5K7XMSCHTRPOR","created_at":"2026-05-21T01:05:36.641908+00:00"},{"alias_kind":"pith_short_8","alias_value":"7SW5K7XM","created_at":"2026-05-21T01:05:36.641908+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/7SW5K7XMSCHTRPORNFIRGJXIXI","json":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI.json","graph_json":"https://pith.science/api/pith-number/7SW5K7XMSCHTRPORNFIRGJXIXI/graph.json","events_json":"https://pith.science/api/pith-number/7SW5K7XMSCHTRPORNFIRGJXIXI/events.json","paper":"https://pith.science/paper/7SW5K7XM"},"agent_actions":{"view_html":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI","download_json":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI.json","view_paper":"https://pith.science/paper/7SW5K7XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21090&json=true","fetch_graph":"https://pith.science/api/pith-number/7SW5K7XMSCHTRPORNFIRGJXIXI/graph.json","fetch_events":"https://pith.science/api/pith-number/7SW5K7XMSCHTRPORNFIRGJXIXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI/action/storage_attestation","attest_author":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI/action/author_attestation","sign_citation":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI/action/citation_signature","submit_replication":"https://pith.science/pith/7SW5K7XMSCHTRPORNFIRGJXIXI/action/replication_record"}},"created_at":"2026-05-21T01:05:36.641908+00:00","updated_at":"2026-05-21T01:05:36.641908+00:00"}