{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SYDCHUEW4PLIBUQ5WSJWK54DDI","short_pith_number":"pith:SYDCHUEW","schema_version":"1.0","canonical_sha256":"960623d096e3d680d21db4936577831a0a3e83cbc6a1e06862ff514d01dee65a","source":{"kind":"arxiv","id":"2305.11147","version":3},"attestation_state":"computed","paper":{"title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Can Qin, Huan Wang, Juan Carlos Niebles, Ning Yu, Ran Xu, Shu Zhang, Silvio Savarese, Stefano Ermon, Xinyi Yang, Yihao Feng, Yingbo Zhou, Yun Fu","submitted_at":"2023-05-18T17:41:34Z","abstract_excerpt":"Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages. However, they often fall short in generating images with spatial, structural, or geometric controls. The integration of such controls, which can accommodate various visual conditions in a single unified model, remains an unaddressed challenge. In response, we introduce UniControl, a new generative foundation model that cons"},"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":"2305.11147","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T17:41:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff110dad14d52759156e205f85de0a7829e89eccea991d8c132eaf026a79e2bf","abstract_canon_sha256":"016fd9c6a2978fd5e53d0fd54d473f5c3c4e4a419121aa8fb5826663d0e94942"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:07.291870Z","signature_b64":"0TwV/j+0lmqSd6XXCfEGBtW0Bm63sZMoXDD+s33e+OkTqiTwIzsOvx8lOG2sQZZia3lHFeYdT+a7jKoZ1yYRAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"960623d096e3d680d21db4936577831a0a3e83cbc6a1e06862ff514d01dee65a","last_reissued_at":"2026-07-05T07:08:07.291408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:07.291408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Caiming Xiong, Can Qin, Huan Wang, Juan Carlos Niebles, Ning Yu, Ran Xu, Shu Zhang, Silvio Savarese, Stefano Ermon, Xinyi Yang, Yihao Feng, Yingbo Zhou, Yun Fu","submitted_at":"2023-05-18T17:41:34Z","abstract_excerpt":"Achieving machine autonomy and human control often represent divergent objectives in the design of interactive AI systems. Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages. However, they often fall short in generating images with spatial, structural, or geometric controls. The integration of such controls, which can accommodate various visual conditions in a single unified model, remains an unaddressed challenge. In response, we introduce UniControl, a new generative foundation model that cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11147","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/2305.11147/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":"2305.11147","created_at":"2026-07-05T07:08:07.291471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11147v3","created_at":"2026-07-05T07:08:07.291471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11147","created_at":"2026-07-05T07:08:07.291471+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYDCHUEW4PLI","created_at":"2026-07-05T07:08:07.291471+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYDCHUEW4PLIBUQ5","created_at":"2026-07-05T07:08:07.291471+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYDCHUEW","created_at":"2026-07-05T07:08:07.291471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20971","citing_title":"UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19103","citing_title":"ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09156","citing_title":"OmniGen-AR: AutoRegressive Any-to-Image Generation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31924","citing_title":"InstanceControl: Controllable Complex Image Generation without Instance Labeling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20090","citing_title":"MetaEarth-MM: Unified Multimodal Remote Sensing Image Generation with Scene-centered Joint Modeling","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2508.14461","citing_title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18169","citing_title":"PiERN: Token-Level Routing for Integrating High-Precision Computation and Reasoning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26341","citing_title":"SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00526","citing_title":"IdentiFace: Multi-Modal Iterative Diffusion Framework for Identifiable Suspect Face Generation in Crime Investigations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00658","citing_title":"UniVidX: A Unified Multimodal Framework for Versatile Video Generation via Diffusion Priors","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI","json":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI.json","graph_json":"https://pith.science/api/pith-number/SYDCHUEW4PLIBUQ5WSJWK54DDI/graph.json","events_json":"https://pith.science/api/pith-number/SYDCHUEW4PLIBUQ5WSJWK54DDI/events.json","paper":"https://pith.science/paper/SYDCHUEW"},"agent_actions":{"view_html":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI","download_json":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI.json","view_paper":"https://pith.science/paper/SYDCHUEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11147&json=true","fetch_graph":"https://pith.science/api/pith-number/SYDCHUEW4PLIBUQ5WSJWK54DDI/graph.json","fetch_events":"https://pith.science/api/pith-number/SYDCHUEW4PLIBUQ5WSJWK54DDI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI/action/storage_attestation","attest_author":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI/action/author_attestation","sign_citation":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI/action/citation_signature","submit_replication":"https://pith.science/pith/SYDCHUEW4PLIBUQ5WSJWK54DDI/action/replication_record"}},"created_at":"2026-07-05T07:08:07.291471+00:00","updated_at":"2026-07-05T07:08:07.291471+00:00"}