{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HHXOOKUBMMCKXM7HHJ6GM6STE6","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":"2c321bc8b9156183e6dbeb6b4cbe5b3d4764449328262d68ef77a161dfd6bd97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:01Z","title_canon_sha256":"c21b5373a445472d3771f38dd21a1f622e24a4baa0fbc17a478bd7de34109910"},"schema_version":"1.0","source":{"id":"2406.07540","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07540","created_at":"2026-07-05T09:47:30Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07540v2","created_at":"2026-07-05T09:47:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07540","created_at":"2026-07-05T09:47:30Z"},{"alias_kind":"pith_short_12","alias_value":"HHXOOKUBMMCK","created_at":"2026-07-05T09:47:30Z"},{"alias_kind":"pith_short_16","alias_value":"HHXOOKUBMMCKXM7H","created_at":"2026-07-05T09:47:30Z"},{"alias_kind":"pith_short_8","alias_value":"HHXOOKUB","created_at":"2026-07-05T09:47:30Z"}],"graph_snapshots":[{"event_id":"sha256:359400b2f84457a34d8e27267e8cbe3f3bf81b895909ecff690d0d7b6cb35bcd","target":"graph","created_at":"2026-07-05T09:47:30Z","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/2406.07540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent controllable generation approaches such as FreeControl and Diffusion Self-Guidance bring fine-grained spatial and appearance control to text-to-image (T2I) diffusion models without training auxiliary modules. However, these methods optimize the latent embedding for each type of score function with longer diffusion steps, making the generation process time-consuming and limiting their flexibility and use. This work presents Ctrl-X, a simple framework for T2I diffusion controlling structure and appearance without additional training or guidance. Ctrl-X designs feed-forward structure contr","authors_text":"Ben Klingher, Bolei Zhou, Fangzhou Mu, Kuan Heng Lin, Sicheng Mo","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:01Z","title":"Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07540","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:e3e0b8188f98b94341557185fa142d1bfca2b53c95bc8ef98f36bea18df1bc84","target":"record","created_at":"2026-07-05T09:47:30Z","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":"2c321bc8b9156183e6dbeb6b4cbe5b3d4764449328262d68ef77a161dfd6bd97","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T17:59:01Z","title_canon_sha256":"c21b5373a445472d3771f38dd21a1f622e24a4baa0fbc17a478bd7de34109910"},"schema_version":"1.0","source":{"id":"2406.07540","kind":"arxiv","version":2}},"canonical_sha256":"39eee72a816304abb3e73a7c667a5327a1b93ee1b5f69b013a005a9b1b57760e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39eee72a816304abb3e73a7c667a5327a1b93ee1b5f69b013a005a9b1b57760e","first_computed_at":"2026-07-05T09:47:30.892208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:30.892208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"39yOeb5PFNEM7V70TpdXmYP7KF6HBOxNotTO9RTFVILAuRWRcvMHt9gw6eZHwpxJUZuOqeL6SP7MP9BH/IegAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:30.892701Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07540","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3e0b8188f98b94341557185fa142d1bfca2b53c95bc8ef98f36bea18df1bc84","sha256:359400b2f84457a34d8e27267e8cbe3f3bf81b895909ecff690d0d7b6cb35bcd"],"state_sha256":"f4589f5e4852300e46f86756b91dbc46702fffc61093ce9dabab80bf131ad41d"}