{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5RB2QLZS3OA3PEXKLWGKZRSS76","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":"81e7afc6b25f012d7ee89f11055948ea877badf435074f5c5137df4a5a61186f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:55:32Z","title_canon_sha256":"7f1f52ff20489ff02c1c9d311616bc8b5332f3d842419e4b283c64fdf47dcdda"},"schema_version":"1.0","source":{"id":"2306.00964","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00964","created_at":"2026-07-05T07:50:19Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00964v1","created_at":"2026-07-05T07:50:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00964","created_at":"2026-07-05T07:50:19Z"},{"alias_kind":"pith_short_12","alias_value":"5RB2QLZS3OA3","created_at":"2026-07-05T07:50:19Z"},{"alias_kind":"pith_short_16","alias_value":"5RB2QLZS3OA3PEXK","created_at":"2026-07-05T07:50:19Z"},{"alias_kind":"pith_short_8","alias_value":"5RB2QLZS","created_at":"2026-07-05T07:50:19Z"}],"graph_snapshots":[{"event_id":"sha256:bc2cddbad3464343da1b7267c1e62f33b1a8e4073f65801534a805d000214b7d","target":"graph","created_at":"2026-07-05T07:50:19Z","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/2306.00964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-conditional diffusion models are able to generate high-fidelity images with diverse contents. However, linguistic representations frequently exhibit ambiguous descriptions of the envisioned objective imagery, requiring the incorporation of additional control signals to bolster the efficacy of text-guided diffusion models. In this work, we propose Cocktail, a pipeline to mix various modalities into one embedding, amalgamated with a generalized ControlNet (gControlNet), a controllable normalisation (ControlNorm), and a spatial guidance sampling method, to actualize multi-modal and spatially","authors_text":"Chaoyue Wang, Chuanxia Zheng, Dacheng Tao, Daqing Liu, Jianbin Zheng, Minghui Hu, Tat-Jen Cham","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:55:32Z","title":"Cocktail: Mixing Multi-Modality Controls for Text-Conditional Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00964","kind":"arxiv","version":1},"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:f2529c64e8897bdcaef9f18c6e3941b47e7957ea5870c5ec43e0080d72f5723a","target":"record","created_at":"2026-07-05T07:50:19Z","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":"81e7afc6b25f012d7ee89f11055948ea877badf435074f5c5137df4a5a61186f","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T17:55:32Z","title_canon_sha256":"7f1f52ff20489ff02c1c9d311616bc8b5332f3d842419e4b283c64fdf47dcdda"},"schema_version":"1.0","source":{"id":"2306.00964","kind":"arxiv","version":1}},"canonical_sha256":"ec43a82f32db81b792ea5d8cacc652ffa177e74aa715253ae2d5e779cafbc4a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec43a82f32db81b792ea5d8cacc652ffa177e74aa715253ae2d5e779cafbc4a9","first_computed_at":"2026-07-05T07:50:19.386436Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:50:19.386436Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TLnYBTzAZ/TTV4kmvimJ3yjvn8FOJXwTjM2DyWiZTzsra8tFqoMR+Or4qpPxJqQ0BhYVGn5d6/ve6+BMcT9LAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:50:19.386878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00964","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2529c64e8897bdcaef9f18c6e3941b47e7957ea5870c5ec43e0080d72f5723a","sha256:bc2cddbad3464343da1b7267c1e62f33b1a8e4073f65801534a805d000214b7d"],"state_sha256":"cca12401b9e7f1c27573f3ccdce1fc50cfee3750398b81c5c5cf3a1884c0d9eb"}