{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z5K23A37Z42UK5PZLY3DF4GUWJ","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":"606403f1d185a9abf0e0dd0399abbc2691413c40a4b210c8df79f4be8cabd57e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T05:49:00Z","title_canon_sha256":"6321e5a9f9b279f836396972eb34b51fbbfe2263e0301dd58354d27d5a1ab4ea"},"schema_version":"1.0","source":{"id":"2501.00289","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.00289","created_at":"2026-07-05T10:43:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.00289v2","created_at":"2026-07-05T10:43:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00289","created_at":"2026-07-05T10:43:04Z"},{"alias_kind":"pith_short_12","alias_value":"Z5K23A37Z42U","created_at":"2026-07-05T10:43:04Z"},{"alias_kind":"pith_short_16","alias_value":"Z5K23A37Z42UK5PZ","created_at":"2026-07-05T10:43:04Z"},{"alias_kind":"pith_short_8","alias_value":"Z5K23A37","created_at":"2026-07-05T10:43:04Z"}],"graph_snapshots":[{"event_id":"sha256:c93889044327131e8146e2f9a805f13c951cd92e939c2329c37822855bc61ed6","target":"graph","created_at":"2026-07-05T10:43:04Z","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/2501.00289/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end diffusion model for multi-modal understanding and generation that significantly improves on existing diffusion-based multimodal models, and is the first of its kind to support the full suite of vision-language modeling capabilities. Inspired by the multimodal diffusion transformer (MM-DiT) and recent advances in discrete diffusion language modeling, we leverage","authors_text":"Amir Barati Farimani, Henry Li, Linjie Yang, Peng Wang, Yichun Shi, Yuval Kluger, Zijie Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T05:49:00Z","title":"Dual Diffusion for Unified Image Generation and Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00289","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:e33ea539a26e6febba13729bd60d832e2238884c59b65c2d71445a66c9ef979d","target":"record","created_at":"2026-07-05T10:43:04Z","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":"606403f1d185a9abf0e0dd0399abbc2691413c40a4b210c8df79f4be8cabd57e","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T05:49:00Z","title_canon_sha256":"6321e5a9f9b279f836396972eb34b51fbbfe2263e0301dd58354d27d5a1ab4ea"},"schema_version":"1.0","source":{"id":"2501.00289","kind":"arxiv","version":2}},"canonical_sha256":"cf55ad837fcf354575f95e3632f0d4b27a4b5c55d3cf7213ebad79672401ef3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf55ad837fcf354575f95e3632f0d4b27a4b5c55d3cf7213ebad79672401ef3b","first_computed_at":"2026-07-05T10:43:04.152073Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:04.152073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HqwevmFLmu4NEugtHcJBnTmh+1UcksD5+lGSds7G0VkFcJKc84J0jcjp9yt4oMw8yYcKdz/fLIUT2J2lv1YWDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:04.152585Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.00289","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e33ea539a26e6febba13729bd60d832e2238884c59b65c2d71445a66c9ef979d","sha256:c93889044327131e8146e2f9a805f13c951cd92e939c2329c37822855bc61ed6"],"state_sha256":"6b1b28e039962184810d5307ad88e77b17a2d0d0725703d757d2b5655399a3d4"}