{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LCCYRP2ZZQX65VY2WPYXOAFFNF","short_pith_number":"pith:LCCYRP2Z","schema_version":"1.0","canonical_sha256":"588588bf59cc2feed71ab3f17700a5696da58639d9e81a2ffe51f44b8a373ef7","source":{"kind":"arxiv","id":"2506.07903","version":2},"attestation_state":"computed","paper":{"title":"Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Felix X.-F. Ye, Kevin Rojas, Molei Tao, Sichen Zhu, Yuchen Zhu","submitted_at":"2025-06-09T16:20:20Z","abstract_excerpt":"Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation. On the contrary, the joint generation of multimodal data through diffusion models is still in the early stages of exploration. Existing approaches heavily rely on external preprocessing protocols, such as tokenizers and variational autoencoders, to harmonize varied data representations into a unified, unimodal format. This process heavily demands the high accuracy of encoders and decoders, which can be problematic for applications with limited"},"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":"2506.07903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T16:20:20Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"440a39f7036eca35e1864f603b4b10bc29840e9a0ec6e9985957efc7e0e2618c","abstract_canon_sha256":"d23209b0589b130ec73a1945d9677e01e408e62715bb92912bf1b85992ee3388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:55.899105Z","signature_b64":"ik88k/PLPqJHvRWK9QLsBc1ZM/ozHyvqdlJrqR6Z01rKzJKgoepUrYl7C8VRyffm4EMRoLLjEsA0EHropI8UBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"588588bf59cc2feed71ab3f17700a5696da58639d9e81a2ffe51f44b8a373ef7","last_reissued_at":"2026-07-05T11:20:55.898509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:55.898509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Felix X.-F. Ye, Kevin Rojas, Molei Tao, Sichen Zhu, Yuchen Zhu","submitted_at":"2025-06-09T16:20:20Z","abstract_excerpt":"Diffusion models have demonstrated remarkable performance in generating unimodal data across various tasks, including image, video, and text generation. On the contrary, the joint generation of multimodal data through diffusion models is still in the early stages of exploration. Existing approaches heavily rely on external preprocessing protocols, such as tokenizers and variational autoencoders, to harmonize varied data representations into a unified, unimodal format. This process heavily demands the high accuracy of encoders and decoders, which can be problematic for applications with limited"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07903","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/2506.07903/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":"2506.07903","created_at":"2026-07-05T11:20:55.898575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07903v2","created_at":"2026-07-05T11:20:55.898575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07903","created_at":"2026-07-05T11:20:55.898575+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCCYRP2ZZQX6","created_at":"2026-07-05T11:20:55.898575+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCCYRP2ZZQX65VY2","created_at":"2026-07-05T11:20:55.898575+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCCYRP2Z","created_at":"2026-07-05T11:20:55.898575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07079","citing_title":"AsyncPatch Diffusion: spatially-flexible image generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31063","citing_title":"Free energy Estimation on Any State Space","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16603","citing_title":"Controlla: Learning Controllability via Graph-Constrained Latent Geometry","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23606","citing_title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03206","citing_title":"Coevolutionary Continuous Discrete Diffusion: Make Your Diffusion Language Model a Latent Reasoner","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11748","citing_title":"LangFlow: Continuous Diffusion Rivals Discrete in Language Modeling","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF","json":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF.json","graph_json":"https://pith.science/api/pith-number/LCCYRP2ZZQX65VY2WPYXOAFFNF/graph.json","events_json":"https://pith.science/api/pith-number/LCCYRP2ZZQX65VY2WPYXOAFFNF/events.json","paper":"https://pith.science/paper/LCCYRP2Z"},"agent_actions":{"view_html":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF","download_json":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF.json","view_paper":"https://pith.science/paper/LCCYRP2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07903&json=true","fetch_graph":"https://pith.science/api/pith-number/LCCYRP2ZZQX65VY2WPYXOAFFNF/graph.json","fetch_events":"https://pith.science/api/pith-number/LCCYRP2ZZQX65VY2WPYXOAFFNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF/action/storage_attestation","attest_author":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF/action/author_attestation","sign_citation":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF/action/citation_signature","submit_replication":"https://pith.science/pith/LCCYRP2ZZQX65VY2WPYXOAFFNF/action/replication_record"}},"created_at":"2026-07-05T11:20:55.898575+00:00","updated_at":"2026-07-05T11:20:55.898575+00:00"}