{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDKAVF2GIXPGB4SNBSZHF2DRFI","short_pith_number":"pith:PDKAVF2G","schema_version":"1.0","canonical_sha256":"78d40a974645de60f24d0cb272e8712a10149c80f9a3ee5f443937d44a5e9035","source":{"kind":"arxiv","id":"2406.12044","version":3},"attestation_state":"computed","paper":{"title":"ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Curtis Wigington, Jianyi Zhang, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yiran Chen, Yufan Zhou","submitted_at":"2024-06-17T19:31:24Z","abstract_excerpt":"Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend well with the underlying image. To address these shortcomings, we introduce a novel framework named, ARTIST, which incorporates a dedicated textual diffusion model to focus on the learning of text structures specifically. Initially, we pretrain this textual model to capture the intricacies of text representation. Subsequently, we finetune a visual diffusion mo"},"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":"2406.12044","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T19:31:24Z","cross_cats_sorted":[],"title_canon_sha256":"ce31f57043ce4260485222361f3a14e9955adc3db5195a5175690b3de2a94e8d","abstract_canon_sha256":"37ee15b080373dfd3c7d8386c4b493b5586f10a4da67cb5f3efbebc3954dd213"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:26.754156Z","signature_b64":"5Hlx5TKal8AaO955uy+E8XYQG4PtPCPtyB7Uqohn8nXX056AOLM7KMWqNp02mr9yjzQ/4dPSMv/wxoArf2yjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78d40a974645de60f24d0cb272e8712a10149c80f9a3ee5f443937d44a5e9035","last_reissued_at":"2026-07-05T09:42:26.753630Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:26.753630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Curtis Wigington, Jianyi Zhang, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yiran Chen, Yufan Zhou","submitted_at":"2024-06-17T19:31:24Z","abstract_excerpt":"Diffusion models have demonstrated exceptional capabilities in generating a broad spectrum of visual content, yet their proficiency in rendering text is still limited: they often generate inaccurate characters or words that fail to blend well with the underlying image. To address these shortcomings, we introduce a novel framework named, ARTIST, which incorporates a dedicated textual diffusion model to focus on the learning of text structures specifically. Initially, we pretrain this textual model to capture the intricacies of text representation. Subsequently, we finetune a visual diffusion mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12044","kind":"arxiv","version":3},"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/2406.12044/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":"2406.12044","created_at":"2026-07-05T09:42:26.753689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.12044v3","created_at":"2026-07-05T09:42:26.753689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12044","created_at":"2026-07-05T09:42:26.753689+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDKAVF2GIXPG","created_at":"2026-07-05T09:42:26.753689+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDKAVF2GIXPGB4SN","created_at":"2026-07-05T09:42:26.753689+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDKAVF2G","created_at":"2026-07-05T09:42:26.753689+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/PDKAVF2GIXPGB4SNBSZHF2DRFI","json":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI.json","graph_json":"https://pith.science/api/pith-number/PDKAVF2GIXPGB4SNBSZHF2DRFI/graph.json","events_json":"https://pith.science/api/pith-number/PDKAVF2GIXPGB4SNBSZHF2DRFI/events.json","paper":"https://pith.science/paper/PDKAVF2G"},"agent_actions":{"view_html":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI","download_json":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI.json","view_paper":"https://pith.science/paper/PDKAVF2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.12044&json=true","fetch_graph":"https://pith.science/api/pith-number/PDKAVF2GIXPGB4SNBSZHF2DRFI/graph.json","fetch_events":"https://pith.science/api/pith-number/PDKAVF2GIXPGB4SNBSZHF2DRFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI/action/storage_attestation","attest_author":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI/action/author_attestation","sign_citation":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI/action/citation_signature","submit_replication":"https://pith.science/pith/PDKAVF2GIXPGB4SNBSZHF2DRFI/action/replication_record"}},"created_at":"2026-07-05T09:42:26.753689+00:00","updated_at":"2026-07-05T09:42:26.753689+00:00"}