{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XJCNQVVJRWXIXRJFUELZP4VNZM","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":"a01dd04e1f99f0e6136071cf828d3f71f60f7f45e3f21cf1150464597f720ec9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T04:09:47Z","title_canon_sha256":"904aff3e7095b37aecbbd1e15e2648412469497918dc6494505c6ded69aba63a"},"schema_version":"1.0","source":{"id":"2412.03859","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03859","created_at":"2026-07-05T11:49:32Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03859v3","created_at":"2026-07-05T11:49:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03859","created_at":"2026-07-05T11:49:32Z"},{"alias_kind":"pith_short_12","alias_value":"XJCNQVVJRWXI","created_at":"2026-07-05T11:49:32Z"},{"alias_kind":"pith_short_16","alias_value":"XJCNQVVJRWXIXRJF","created_at":"2026-07-05T11:49:32Z"},{"alias_kind":"pith_short_8","alias_value":"XJCNQVVJ","created_at":"2026-07-05T11:49:32Z"}],"graph_snapshots":[{"event_id":"sha256:bf353107623d5150c671feb98645fd28bb5a35ad42b1ebf8bd240a96e1f4d4b3","target":"graph","created_at":"2026-07-05T11:49:32Z","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/2412.03859/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have been recognized for their ability to generate images that are not only visually appealing but also of high artistic quality. As a result, Layout-to-Image (L2I) generation has been proposed to leverage region-specific positions and descriptions to enable more precise and controllable generation. However, previous methods primarily focus on UNet-based models (\\eg SD1.5 and SDXL), and limited effort has explored Multimodal Diffusion Transformers (MM-DiTs), which have demonstrated powerful image generation capabilities. Enabling MM-DiT for layout-to-image generation seems str","authors_text":"Dexiang Hong, Hui Zhang, Jie Shao, Xinglong Wu, Yitong Wang, Yu-Gang Jiang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T04:09:47Z","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03859","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":"sha256:1c2061aef0fe53fad5ef610d28144ca0fbd1e22c813f20a31c1a62b229d4ec03","target":"record","created_at":"2026-07-05T11:49:32Z","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":"a01dd04e1f99f0e6136071cf828d3f71f60f7f45e3f21cf1150464597f720ec9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T04:09:47Z","title_canon_sha256":"904aff3e7095b37aecbbd1e15e2648412469497918dc6494505c6ded69aba63a"},"schema_version":"1.0","source":{"id":"2412.03859","kind":"arxiv","version":3}},"canonical_sha256":"ba44d856a98dae8bc525a11797f2adcb307610af1fa11f0fc76e3d0718f60ab0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba44d856a98dae8bc525a11797f2adcb307610af1fa11f0fc76e3d0718f60ab0","first_computed_at":"2026-07-05T11:49:32.185712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:32.185712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"boQAwqZbotG6k9nmJZO1aIpP7RFbHKiRUaXrVoLmEeICmnLveWolXXwiJ7u4ayTLNdWHcB2sQ3rt28F4ZodWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:32.186217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03859","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c2061aef0fe53fad5ef610d28144ca0fbd1e22c813f20a31c1a62b229d4ec03","sha256:bf353107623d5150c671feb98645fd28bb5a35ad42b1ebf8bd240a96e1f4d4b3"],"state_sha256":"0f0d4f7a80315e9c75ab077ed21dd8bff1b7cf837932b95ea44e06193f00a0c6"}