{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GO4DU2VNNTOPRK5E2JJ5I6MSA5","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":"2622380ede51d2bdbe9368fba9df1a47fcc7c1ee978f5a16a01bbbfacb836230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-27T14:46:01Z","title_canon_sha256":"5470701881622441f68854a0f324cafb243fd277ed552715cfaa8d5ddfaf1d3b"},"schema_version":"1.0","source":{"id":"2211.14842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.14842","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2211.14842v1","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.14842","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"GO4DU2VNNTOP","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"GO4DU2VNNTOPRK5E","created_at":"2026-07-05T05:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"GO4DU2VN","created_at":"2026-07-05T05:19:44Z"}],"graph_snapshots":[{"event_id":"sha256:7a8c90e0d81b29d2d84f0fd5a116109ccc18d15ca918280f2f1378a40d543168","target":"graph","created_at":"2026-07-05T05:19:44Z","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/2211.14842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present a unified multimodal generation model that can conduct both the \"modality translation\" and \"multi-modality generation\" tasks using a single model, performing text-based, image-based, and even vision-language simultaneous generation. Specifically, we unify the discrete diffusion process for multimodal signals by proposing a unified transition matrix. Moreover, we design a mu","authors_text":"Chaoyue Wang, Chuanxia Zheng, Dacheng Tao, Heliang Zheng, Minghui Hu, Ponnuthurai N. Suganthan, Tat-Jen Cham, Zuopeng Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-27T14:46:01Z","title":"Unified Discrete Diffusion for Simultaneous Vision-Language Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.14842","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":"sha256:51917a29a7a51f39d6d60f6a1a9e1faaf779a5c0207de8fb259844a16404ea04","target":"record","created_at":"2026-07-05T05:19:44Z","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":"2622380ede51d2bdbe9368fba9df1a47fcc7c1ee978f5a16a01bbbfacb836230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-27T14:46:01Z","title_canon_sha256":"5470701881622441f68854a0f324cafb243fd277ed552715cfaa8d5ddfaf1d3b"},"schema_version":"1.0","source":{"id":"2211.14842","kind":"arxiv","version":1}},"canonical_sha256":"33b83a6aad6cdcf8aba4d253d479920754f917160631fffb5195995c652b17ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33b83a6aad6cdcf8aba4d253d479920754f917160631fffb5195995c652b17ac","first_computed_at":"2026-07-05T05:19:44.441531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:19:44.441531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgMugRKJlbidXaB4aP18gXEK7f+ZKR3HDvi935JyyPJKQxoq0qR21i2ipPeePrDefT4HagMrvtnlR0Q9i0AsBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:19:44.441955Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.14842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51917a29a7a51f39d6d60f6a1a9e1faaf779a5c0207de8fb259844a16404ea04","sha256:7a8c90e0d81b29d2d84f0fd5a116109ccc18d15ca918280f2f1378a40d543168"],"state_sha256":"221d5884dd6697dd2a448bd7df9ec7324bea75bafc771e434553917e703a58e8"}