{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PDKAVF2GIXPGB4SNBSZHF2DRFI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"37ee15b080373dfd3c7d8386c4b493b5586f10a4da67cb5f3efbebc3954dd213","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T19:31:24Z","title_canon_sha256":"ce31f57043ce4260485222361f3a14e9955adc3db5195a5175690b3de2a94e8d"},"schema_version":"1.0","source":{"id":"2406.12044","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12044","created_at":"2026-07-05T09:42:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12044v3","created_at":"2026-07-05T09:42:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12044","created_at":"2026-07-05T09:42:26Z"},{"alias_kind":"pith_short_12","alias_value":"PDKAVF2GIXPG","created_at":"2026-07-05T09:42:26Z"},{"alias_kind":"pith_short_16","alias_value":"PDKAVF2GIXPGB4SN","created_at":"2026-07-05T09:42:26Z"},{"alias_kind":"pith_short_8","alias_value":"PDKAVF2G","created_at":"2026-07-05T09:42:26Z"}],"graph_snapshots":[{"event_id":"sha256:61928f45a9ac85aaee8fbe0169ecd94d15c5d5ab7fc8c8f3a29635b482612ee0","target":"graph","created_at":"2026-07-05T09:42:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.12044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Curtis Wigington, Jianyi Zhang, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yiran Chen, Yufan Zhou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T19:31:24Z","title":"ARTIST: Improving the Generation of Text-rich Images with Disentangled Diffusion Models and Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12044","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6db9cc62d1c36265ad1a2efe3dfe0e915a527bab88131637b3606c64cf522df9","target":"record","created_at":"2026-07-05T09:42:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"37ee15b080373dfd3c7d8386c4b493b5586f10a4da67cb5f3efbebc3954dd213","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T19:31:24Z","title_canon_sha256":"ce31f57043ce4260485222361f3a14e9955adc3db5195a5175690b3de2a94e8d"},"schema_version":"1.0","source":{"id":"2406.12044","kind":"arxiv","version":3}},"canonical_sha256":"78d40a974645de60f24d0cb272e8712a10149c80f9a3ee5f443937d44a5e9035","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78d40a974645de60f24d0cb272e8712a10149c80f9a3ee5f443937d44a5e9035","first_computed_at":"2026-07-05T09:42:26.753630Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:26.753630Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5Hlx5TKal8AaO955uy+E8XYQG4PtPCPtyB7Uqohn8nXX056AOLM7KMWqNp02mr9yjzQ/4dPSMv/wxoArf2yjAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:26.754156Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12044","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6db9cc62d1c36265ad1a2efe3dfe0e915a527bab88131637b3606c64cf522df9","sha256:61928f45a9ac85aaee8fbe0169ecd94d15c5d5ab7fc8c8f3a29635b482612ee0"],"state_sha256":"5484b19be3485341e69c1e6c3924a9869785100b29db48bcaba7a18f30edb404"}