{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IUY7P6GJPOX24RZLX4EHA22WH7","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":"393d2687d507802ca3acb423fee0b6f74924b755397b3c9065b49d884ea5e921","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-02T06:13:01Z","title_canon_sha256":"06512ccbbce79cc63e90af3045f3ec875f33f6eba47397c4276197e709522f49"},"schema_version":"1.0","source":{"id":"2412.01169","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01169","created_at":"2026-07-05T10:36:32Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01169v2","created_at":"2026-07-05T10:36:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01169","created_at":"2026-07-05T10:36:32Z"},{"alias_kind":"pith_short_12","alias_value":"IUY7P6GJPOX2","created_at":"2026-07-05T10:36:32Z"},{"alias_kind":"pith_short_16","alias_value":"IUY7P6GJPOX24RZL","created_at":"2026-07-05T10:36:32Z"},{"alias_kind":"pith_short_8","alias_value":"IUY7P6GJ","created_at":"2026-07-05T10:36:32Z"}],"graph_snapshots":[{"event_id":"sha256:b99d3b97c23a8e6c95bae02ee827484ce403ee401d6976fd40745c5cda0ca242","target":"graph","created_at":"2026-07-05T10:36:32Z","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/2412.01169/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce OmniFlow, a novel generative model designed for any-to-any generation tasks such as text-to-image, text-to-audio, and audio-to-image synthesis. OmniFlow advances the rectified flow (RF) framework used in text-to-image models to handle the joint distribution of multiple modalities. It outperforms previous any-to-any models on a wide range of tasks, such as text-to-image and text-to-audio synthesis. Our work offers three key contributions: First, we extend RF to a multi-modal setting and introduce a novel guidance mechanism, enabling users to flexibly control the alignment between d","authors_text":"Aditya Grover, Akash Gokul, Kazuki Kozuka, Konstantinos Kallidromitis, Shufan Li, Yusuke Kato, Zichun Liao","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-02T06:13:01Z","title":"OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01169","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:b34e6514c10b9782ab7dedf19d747b1f5193dc342ebdd04067a24f79953e30dd","target":"record","created_at":"2026-07-05T10:36:32Z","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":"393d2687d507802ca3acb423fee0b6f74924b755397b3c9065b49d884ea5e921","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-12-02T06:13:01Z","title_canon_sha256":"06512ccbbce79cc63e90af3045f3ec875f33f6eba47397c4276197e709522f49"},"schema_version":"1.0","source":{"id":"2412.01169","kind":"arxiv","version":2}},"canonical_sha256":"4531f7f8c97bafae472bbf08706b563ffd29fd3637aa69102483ea6613dc4537","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4531f7f8c97bafae472bbf08706b563ffd29fd3637aa69102483ea6613dc4537","first_computed_at":"2026-07-05T10:36:32.127147Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:36:32.127147Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XmS8d2EeBEOGpw/5yhbCh70vSgmhAla51aO+CZyvz2DiwOwXnsypisa0pxaXzAW5PNUo7I+6Rp8PMb5CA1KMDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:36:32.127723Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01169","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b34e6514c10b9782ab7dedf19d747b1f5193dc342ebdd04067a24f79953e30dd","sha256:b99d3b97c23a8e6c95bae02ee827484ce403ee401d6976fd40745c5cda0ca242"],"state_sha256":"64e1cec0b1e764a8b40189bda058e152bb786941fd18bcb7385123ec5965332d"}