{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z5K23A37Z42UK5PZLY3DF4GUWJ","short_pith_number":"pith:Z5K23A37","schema_version":"1.0","canonical_sha256":"cf55ad837fcf354575f95e3632f0d4b27a4b5c55d3cf7213ebad79672401ef3b","source":{"kind":"arxiv","id":"2501.00289","version":2},"attestation_state":"computed","paper":{"title":"Dual Diffusion for Unified Image Generation and Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Barati Farimani, Henry Li, Linjie Yang, Peng Wang, Yichun Shi, Yuval Kluger, Zijie Li","submitted_at":"2024-12-31T05:49:00Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.00289","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-31T05:49:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6321e5a9f9b279f836396972eb34b51fbbfe2263e0301dd58354d27d5a1ab4ea","abstract_canon_sha256":"606403f1d185a9abf0e0dd0399abbc2691413c40a4b210c8df79f4be8cabd57e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:04.152585Z","signature_b64":"HqwevmFLmu4NEugtHcJBnTmh+1UcksD5+lGSds7G0VkFcJKc84J0jcjp9yt4oMw8yYcKdz/fLIUT2J2lv1YWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf55ad837fcf354575f95e3632f0d4b27a4b5c55d3cf7213ebad79672401ef3b","last_reissued_at":"2026-07-05T10:43:04.152073Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:04.152073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Diffusion for Unified Image Generation and Understanding","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Amir Barati Farimani, Henry Li, Linjie Yang, Peng Wang, Yichun Shi, Yuval Kluger, Zijie Li","submitted_at":"2024-12-31T05:49:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.00289","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2501.00289/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.00289","created_at":"2026-07-05T10:43:04.152138+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.00289v2","created_at":"2026-07-05T10:43:04.152138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.00289","created_at":"2026-07-05T10:43:04.152138+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z5K23A37Z42U","created_at":"2026-07-05T10:43:04.152138+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z5K23A37Z42UK5PZ","created_at":"2026-07-05T10:43:04.152138+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z5K23A37","created_at":"2026-07-05T10:43:04.152138+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.23606","citing_title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2505.05472","citing_title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07265","citing_title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17811","citing_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ","json":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ.json","graph_json":"https://pith.science/api/pith-number/Z5K23A37Z42UK5PZLY3DF4GUWJ/graph.json","events_json":"https://pith.science/api/pith-number/Z5K23A37Z42UK5PZLY3DF4GUWJ/events.json","paper":"https://pith.science/paper/Z5K23A37"},"agent_actions":{"view_html":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ","download_json":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ.json","view_paper":"https://pith.science/paper/Z5K23A37","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.00289&json=true","fetch_graph":"https://pith.science/api/pith-number/Z5K23A37Z42UK5PZLY3DF4GUWJ/graph.json","fetch_events":"https://pith.science/api/pith-number/Z5K23A37Z42UK5PZLY3DF4GUWJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ/action/storage_attestation","attest_author":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ/action/author_attestation","sign_citation":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ/action/citation_signature","submit_replication":"https://pith.science/pith/Z5K23A37Z42UK5PZLY3DF4GUWJ/action/replication_record"}},"created_at":"2026-07-05T10:43:04.152138+00:00","updated_at":"2026-07-05T10:43:04.152138+00:00"}