{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CLKOT64MNPKU63AY6ITL7BWMHA","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":"3286737a909471981e2bded720c7ad2ddf177defae4fe9a0e866a18622eff99a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T09:32:23Z","title_canon_sha256":"18f94e4a5e1ac8b40d44c31ba4050595b64ddf711a7e6b872f954b2016b53c8e"},"schema_version":"1.0","source":{"id":"2412.11594","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11594","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11594v3","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11594","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_12","alias_value":"CLKOT64MNPKU","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_16","alias_value":"CLKOT64MNPKU63AY","created_at":"2026-07-05T09:54:49Z"},{"alias_kind":"pith_short_8","alias_value":"CLKOT64M","created_at":"2026-07-05T09:54:49Z"}],"graph_snapshots":[{"event_id":"sha256:8cead4aee0b8952131a813f52472222a1a54be3cb098972e7d50eeca19146b93","target":"graph","created_at":"2026-07-05T09:54:49Z","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/2412.11594/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a ge","authors_text":"Honggang Zhang, Kaiyue Pang, Ke Li, Lan Yang, Yi-Zhe Song, Yonggang Qi, Zhipeng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T09:32:23Z","title":"VersaGen: Unleashing Versatile Visual Control for Text-to-Image Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11594","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:d2bbe3426f8cfc5f653401545858ed9462e75f31987ccd32f0c908a36bc7987d","target":"record","created_at":"2026-07-05T09:54:49Z","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":"3286737a909471981e2bded720c7ad2ddf177defae4fe9a0e866a18622eff99a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T09:32:23Z","title_canon_sha256":"18f94e4a5e1ac8b40d44c31ba4050595b64ddf711a7e6b872f954b2016b53c8e"},"schema_version":"1.0","source":{"id":"2412.11594","kind":"arxiv","version":3}},"canonical_sha256":"12d4e9fb8c6bd54f6c18f226bf86cc3802440f925d63f0302fb5be1e3177897a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12d4e9fb8c6bd54f6c18f226bf86cc3802440f925d63f0302fb5be1e3177897a","first_computed_at":"2026-07-05T09:54:49.176459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:49.176459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nxTUaJIBZt+xFV5QnRKB6rXVC3XZRg1F3pnBfGmibPVWUkG4kfGXRjbP0zFGA6WDNgxtEOdnD1y1cJJrjmeRDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:49.176956Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11594","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2bbe3426f8cfc5f653401545858ed9462e75f31987ccd32f0c908a36bc7987d","sha256:8cead4aee0b8952131a813f52472222a1a54be3cb098972e7d50eeca19146b93"],"state_sha256":"886b4792ba5d675ffc39368a1688a5c5d0ae5879523ae2ffe7f798a97c9ab9e2"}