{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XJCNQVVJRWXIXRJFUELZP4VNZM","short_pith_number":"pith:XJCNQVVJ","schema_version":"1.0","canonical_sha256":"ba44d856a98dae8bc525a11797f2adcb307610af1fa11f0fc76e3d0718f60ab0","source":{"kind":"arxiv","id":"2412.03859","version":3},"attestation_state":"computed","paper":{"title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dexiang Hong, Hui Zhang, Jie Shao, Xinglong Wu, Yitong Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2024-12-05T04:09:47Z","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"},"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":"2412.03859","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T04:09:47Z","cross_cats_sorted":[],"title_canon_sha256":"904aff3e7095b37aecbbd1e15e2648412469497918dc6494505c6ded69aba63a","abstract_canon_sha256":"a01dd04e1f99f0e6136071cf828d3f71f60f7f45e3f21cf1150464597f720ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:32.186217Z","signature_b64":"boQAwqZbotG6k9nmJZO1aIpP7RFbHKiRUaXrVoLmEeICmnLveWolXXwiJ7u4ayTLNdWHcB2sQ3rt28F4ZodWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba44d856a98dae8bc525a11797f2adcb307610af1fa11f0fc76e3d0718f60ab0","last_reissued_at":"2026-07-05T11:49:32.185712Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:32.185712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dexiang Hong, Hui Zhang, Jie Shao, Xinglong Wu, Yitong Wang, Yu-Gang Jiang, Zuxuan Wu","submitted_at":"2024-12-05T04:09:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03859","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/2412.03859/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":"2412.03859","created_at":"2026-07-05T11:49:32.185782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03859v3","created_at":"2026-07-05T11:49:32.185782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03859","created_at":"2026-07-05T11:49:32.185782+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJCNQVVJRWXI","created_at":"2026-07-05T11:49:32.185782+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJCNQVVJRWXIXRJF","created_at":"2026-07-05T11:49:32.185782+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJCNQVVJ","created_at":"2026-07-05T11:49:32.185782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05031","citing_title":"MetaPoint: Unlocking Precise Spatial Control in Agentic Visual Generation","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28615","citing_title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":86,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25358","citing_title":"Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06870","citing_title":"RefineAnything: Multimodal Region-Specific Refinement for Perfect Local Details","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM","json":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM.json","graph_json":"https://pith.science/api/pith-number/XJCNQVVJRWXIXRJFUELZP4VNZM/graph.json","events_json":"https://pith.science/api/pith-number/XJCNQVVJRWXIXRJFUELZP4VNZM/events.json","paper":"https://pith.science/paper/XJCNQVVJ"},"agent_actions":{"view_html":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM","download_json":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM.json","view_paper":"https://pith.science/paper/XJCNQVVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03859&json=true","fetch_graph":"https://pith.science/api/pith-number/XJCNQVVJRWXIXRJFUELZP4VNZM/graph.json","fetch_events":"https://pith.science/api/pith-number/XJCNQVVJRWXIXRJFUELZP4VNZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM/action/storage_attestation","attest_author":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM/action/author_attestation","sign_citation":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM/action/citation_signature","submit_replication":"https://pith.science/pith/XJCNQVVJRWXIXRJFUELZP4VNZM/action/replication_record"}},"created_at":"2026-07-05T11:49:32.185782+00:00","updated_at":"2026-07-05T11:49:32.185782+00:00"}