{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPO73ZTMSRS4RSMLYU6K44Z2KS","short_pith_number":"pith:XPO73ZTM","schema_version":"1.0","canonical_sha256":"bbddfde66c9465c8c98bc53cae733a549a3fc2203b60c6fc811f05013df4e65f","source":{"kind":"arxiv","id":"2507.02713","version":2},"attestation_state":"computed","paper":{"title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Ceyuan Yang, Dan Xu, Dongxu Yue, Fei Shen, Hanzhong Guo, Qin Guo, Wei Liu, Xihui Liu, Yang Cao","submitted_at":"2025-07-03T15:27:28Z","abstract_excerpt":"Although significant advancements have been achieved in the progress of keypoint-guided Text-to-Image diffusion models, existing mainstream keypoint-guided models encounter challenges in controlling the generation of more general non-rigid objects beyond humans (e.g., animals). Moreover, it is difficult to generate multiple overlapping humans and animals based on keypoint controls solely. These challenges arise from two main aspects: the inherent limitations of existing controllable methods and the lack of suitable datasets. First, we design a DiT-based framework, named UniMC, to explore unify"},"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":"2507.02713","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T15:27:28Z","cross_cats_sorted":[],"title_canon_sha256":"e0ec55e9860a4ec373a656761869792eaffa19b3868a2da4ec24b9089969edb8","abstract_canon_sha256":"be577daf2d2769d8f0dcf8f622b2405876d030613e83131cfd205be65ffdb77c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:47.723103Z","signature_b64":"qI9872Vm9xnR9Ybdn76FpnhILcycFe2iBB29S07DzM7y9ajSpWDbVzZJE+7+eWPHhUyy0psZdv3emhmanhhZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbddfde66c9465c8c98bc53cae733a549a3fc2203b60c6fc811f05013df4e65f","last_reissued_at":"2026-07-05T11:31:47.722572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:47.722572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ailing Zeng, Ceyuan Yang, Dan Xu, Dongxu Yue, Fei Shen, Hanzhong Guo, Qin Guo, Wei Liu, Xihui Liu, Yang Cao","submitted_at":"2025-07-03T15:27:28Z","abstract_excerpt":"Although significant advancements have been achieved in the progress of keypoint-guided Text-to-Image diffusion models, existing mainstream keypoint-guided models encounter challenges in controlling the generation of more general non-rigid objects beyond humans (e.g., animals). Moreover, it is difficult to generate multiple overlapping humans and animals based on keypoint controls solely. These challenges arise from two main aspects: the inherent limitations of existing controllable methods and the lack of suitable datasets. First, we design a DiT-based framework, named UniMC, to explore unify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02713","kind":"arxiv","version":2},"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/2507.02713/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":"2507.02713","created_at":"2026-07-05T11:31:47.722640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02713v2","created_at":"2026-07-05T11:31:47.722640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02713","created_at":"2026-07-05T11:31:47.722640+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPO73ZTMSRS4","created_at":"2026-07-05T11:31:47.722640+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPO73ZTMSRS4RSML","created_at":"2026-07-05T11:31:47.722640+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPO73ZTM","created_at":"2026-07-05T11:31:47.722640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31029","citing_title":"TerraDiT-$\\Omega$: Unified Spatial Control for Satellite Image Synthesis with Any Geospatial Primitive","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS","json":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS.json","graph_json":"https://pith.science/api/pith-number/XPO73ZTMSRS4RSMLYU6K44Z2KS/graph.json","events_json":"https://pith.science/api/pith-number/XPO73ZTMSRS4RSMLYU6K44Z2KS/events.json","paper":"https://pith.science/paper/XPO73ZTM"},"agent_actions":{"view_html":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS","download_json":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS.json","view_paper":"https://pith.science/paper/XPO73ZTM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02713&json=true","fetch_graph":"https://pith.science/api/pith-number/XPO73ZTMSRS4RSMLYU6K44Z2KS/graph.json","fetch_events":"https://pith.science/api/pith-number/XPO73ZTMSRS4RSMLYU6K44Z2KS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS/action/storage_attestation","attest_author":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS/action/author_attestation","sign_citation":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS/action/citation_signature","submit_replication":"https://pith.science/pith/XPO73ZTMSRS4RSMLYU6K44Z2KS/action/replication_record"}},"created_at":"2026-07-05T11:31:47.722640+00:00","updated_at":"2026-07-05T11:31:47.722640+00:00"}