{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GWZKJPPHA3C4GQLCMJK7JKIKME","short_pith_number":"pith:GWZKJPPH","schema_version":"1.0","canonical_sha256":"35b2a4bde706c5c341626255f4a90a61135106cbc2cc0756f21a4684b5309504","source":{"kind":"arxiv","id":"2506.21276","version":1},"attestation_state":"computed","paper":{"title":"WordCon: Word-level Typography Control in Scene Text Rendering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengming Zhang, Jiaming Liu, Wenda Shi, Xingxing Zou, Yiren Song, Zihan Rao","submitted_at":"2025-06-26T14:00:38Z","abstract_excerpt":"Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset and introduce the Text-Image Alignment (TIA) framework. This framework leverages cross-modal correspondence between text and local image regions provided by grounding models to enhance the Text-to-Image (T2I) model training. Furthermore, we propose WordCon, a hybrid parameter-efficient fine-tuning (PEFT) method. WordCon reparameterizes selective key parameters, improving both efficiency and portability. This allows "},"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":"2506.21276","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-26T14:00:38Z","cross_cats_sorted":[],"title_canon_sha256":"1c2ca0fd37ec5b2876af13453a28ad22514628f0a76865ede0214f510917d97d","abstract_canon_sha256":"b09abc9fa1e025ba9f9abc2ac3efb631daad3205da4fb45b0fce27f3d4dee244"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:42.715364Z","signature_b64":"xB9fbxpXTw9NYbKdru9YldTzVUC1JMM/sPYY3SyaikPBoMHm/ihq441HDntW/cGTaoFDzmpRkpFKBiVmcL1ODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35b2a4bde706c5c341626255f4a90a61135106cbc2cc0756f21a4684b5309504","last_reissued_at":"2026-07-05T11:27:42.714476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:42.714476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WordCon: Word-level Typography Control in Scene Text Rendering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dengming Zhang, Jiaming Liu, Wenda Shi, Xingxing Zou, Yiren Song, Zihan Rao","submitted_at":"2025-06-26T14:00:38Z","abstract_excerpt":"Achieving precise word-level typography control within generated images remains a persistent challenge. To address it, we newly construct a word-level controlled scene text dataset and introduce the Text-Image Alignment (TIA) framework. This framework leverages cross-modal correspondence between text and local image regions provided by grounding models to enhance the Text-to-Image (T2I) model training. Furthermore, we propose WordCon, a hybrid parameter-efficient fine-tuning (PEFT) method. WordCon reparameterizes selective key parameters, improving both efficiency and portability. This allows "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21276","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/2506.21276/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":"2506.21276","created_at":"2026-07-05T11:27:42.714581+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21276v1","created_at":"2026-07-05T11:27:42.714581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21276","created_at":"2026-07-05T11:27:42.714581+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWZKJPPHA3C4","created_at":"2026-07-05T11:27:42.714581+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWZKJPPHA3C4GQLC","created_at":"2026-07-05T11:27:42.714581+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWZKJPPH","created_at":"2026-07-05T11:27:42.714581+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08163","citing_title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME","json":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME.json","graph_json":"https://pith.science/api/pith-number/GWZKJPPHA3C4GQLCMJK7JKIKME/graph.json","events_json":"https://pith.science/api/pith-number/GWZKJPPHA3C4GQLCMJK7JKIKME/events.json","paper":"https://pith.science/paper/GWZKJPPH"},"agent_actions":{"view_html":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME","download_json":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME.json","view_paper":"https://pith.science/paper/GWZKJPPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21276&json=true","fetch_graph":"https://pith.science/api/pith-number/GWZKJPPHA3C4GQLCMJK7JKIKME/graph.json","fetch_events":"https://pith.science/api/pith-number/GWZKJPPHA3C4GQLCMJK7JKIKME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME/action/storage_attestation","attest_author":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME/action/author_attestation","sign_citation":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME/action/citation_signature","submit_replication":"https://pith.science/pith/GWZKJPPHA3C4GQLCMJK7JKIKME/action/replication_record"}},"created_at":"2026-07-05T11:27:42.714581+00:00","updated_at":"2026-07-05T11:27:42.714581+00:00"}