{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ATFJD7V43TN26Z3TB5HNOKU4XV","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":"c99e8cf7a6477847c031e7e9897b712d0169f08816c6c32e770e5a7d138014be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T02:52:25Z","title_canon_sha256":"2f7dfa7ddf40d611c7a4b87db98cfb3a71da6270d4eb1ded369ec88440d7fc71"},"schema_version":"1.0","source":{"id":"2502.05415","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05415","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05415v2","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05415","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"ATFJD7V43TN2","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"ATFJD7V43TN26Z3T","created_at":"2026-07-05T11:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"ATFJD7V4","created_at":"2026-07-05T11:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:7dce9d2b0e86572951b723efd15e4ab827e32ab5f9a4449f4cfc2df3c51d4e17","target":"graph","created_at":"2026-07-05T11:04:45Z","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/2502.05415/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Consistency models (CMs) have shown promise in the efficient generation of both image and text. This raises the natural question of whether we can learn a unified CM for efficient multimodal generation (e.g., text-to-image) and understanding (e.g., image-to-text). Intuitively, such a model could be acquired by applying the consistency distillation (CD) to existing unified multimodal models. However, the key challenge is establishing a unified denoising perspective for both image and text generation, which is essential for establishing the consistency mapping. To tackle this, at the representat","authors_text":"Chenkai Xu, TianQi Hou, Xu Wang, Yishun Li, Zhenyi Liao, Zhijie Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T02:52:25Z","title":"UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05415","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:c9acaace443c0f055757455ab286836d5d5e1e74f896b45cf4c21d8469f3b532","target":"record","created_at":"2026-07-05T11:04:45Z","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":"c99e8cf7a6477847c031e7e9897b712d0169f08816c6c32e770e5a7d138014be","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T02:52:25Z","title_canon_sha256":"2f7dfa7ddf40d611c7a4b87db98cfb3a71da6270d4eb1ded369ec88440d7fc71"},"schema_version":"1.0","source":{"id":"2502.05415","kind":"arxiv","version":2}},"canonical_sha256":"04ca91febcdcdbaf67730f4ed72a9cbd61e2db89584aea1c08e604f942cff0d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04ca91febcdcdbaf67730f4ed72a9cbd61e2db89584aea1c08e604f942cff0d1","first_computed_at":"2026-07-05T11:04:45.347452Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:45.347452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqXyDNvmIViEgmxpWkbbrnjDw+5X96jxJH+oAbApnTCR+/UG/r2TTsPnGi/NDwzCMfzlPZbNaCkQ2drT9Lr9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:45.347997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05415","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9acaace443c0f055757455ab286836d5d5e1e74f896b45cf4c21d8469f3b532","sha256:7dce9d2b0e86572951b723efd15e4ab827e32ab5f9a4449f4cfc2df3c51d4e17"],"state_sha256":"0a1b0389cd27ae3927136ad7fc5f3112bb499e9df5aaaba8675f966b5d72bc28"}