{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPO73ZTMSRS4RSMLYU6K44Z2KS","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":"be577daf2d2769d8f0dcf8f622b2405876d030613e83131cfd205be65ffdb77c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T15:27:28Z","title_canon_sha256":"e0ec55e9860a4ec373a656761869792eaffa19b3868a2da4ec24b9089969edb8"},"schema_version":"1.0","source":{"id":"2507.02713","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02713","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02713v2","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02713","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_12","alias_value":"XPO73ZTMSRS4","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_16","alias_value":"XPO73ZTMSRS4RSML","created_at":"2026-07-05T11:31:47Z"},{"alias_kind":"pith_short_8","alias_value":"XPO73ZTM","created_at":"2026-07-05T11:31:47Z"}],"graph_snapshots":[{"event_id":"sha256:71ed855a6b560840282adb8365c254b559c54cfb01f51632ae978aadb0e7eb20","target":"graph","created_at":"2026-07-05T11:31:47Z","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/2507.02713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ailing Zeng, Ceyuan Yang, Dan Xu, Dongxu Yue, Fei Shen, Hanzhong Guo, Qin Guo, Wei Liu, Xihui Liu, Yang Cao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T15:27:28Z","title":"UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02713","kind":"arxiv","version":2},"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:f0a28505837622146688f1828952e455cb66ed49c357c908edb6655b285021bc","target":"record","created_at":"2026-07-05T11:31:47Z","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":"be577daf2d2769d8f0dcf8f622b2405876d030613e83131cfd205be65ffdb77c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T15:27:28Z","title_canon_sha256":"e0ec55e9860a4ec373a656761869792eaffa19b3868a2da4ec24b9089969edb8"},"schema_version":"1.0","source":{"id":"2507.02713","kind":"arxiv","version":2}},"canonical_sha256":"bbddfde66c9465c8c98bc53cae733a549a3fc2203b60c6fc811f05013df4e65f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbddfde66c9465c8c98bc53cae733a549a3fc2203b60c6fc811f05013df4e65f","first_computed_at":"2026-07-05T11:31:47.722572Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:47.722572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qI9872Vm9xnR9Ybdn76FpnhILcycFe2iBB29S07DzM7y9ajSpWDbVzZJE+7+eWPHhUyy0psZdv3emhmanhhZAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:47.723103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02713","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0a28505837622146688f1828952e455cb66ed49c357c908edb6655b285021bc","sha256:71ed855a6b560840282adb8365c254b559c54cfb01f51632ae978aadb0e7eb20"],"state_sha256":"48139a0ce5b5a078326768eb68c0fa7f641e607ecbe3b490351e311dd94322fc"}