{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:NIVW6KI4D3ZMDYYGKHK7HZ3XFD","short_pith_number":"pith:NIVW6KI4","canonical_record":{"source":{"id":"2606.16673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T13:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"666da84d3d84b6e1950bc95b9f635334d64a7f803344a29418ff08ac6af1695f","abstract_canon_sha256":"6a790c2860556da41ce8d96158ae4b758fdffaef7727880f6c7701d8d56200f5"},"schema_version":"1.0"},"canonical_sha256":"6a2b6f291c1ef2c1e30651d5f3e77728fed73466766a09ac608acdc08d2b8b8a","source":{"kind":"arxiv","id":"2606.16673","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16673","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16673v2","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16673","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"NIVW6KI4D3ZM","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"NIVW6KI4D3ZMDYYG","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"NIVW6KI4","created_at":"2026-07-09T01:20:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:NIVW6KI4D3ZMDYYGKHK7HZ3XFD","target":"record","payload":{"canonical_record":{"source":{"id":"2606.16673","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T13:08:06Z","cross_cats_sorted":[],"title_canon_sha256":"666da84d3d84b6e1950bc95b9f635334d64a7f803344a29418ff08ac6af1695f","abstract_canon_sha256":"6a790c2860556da41ce8d96158ae4b758fdffaef7727880f6c7701d8d56200f5"},"schema_version":"1.0"},"canonical_sha256":"6a2b6f291c1ef2c1e30651d5f3e77728fed73466766a09ac608acdc08d2b8b8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:06.601183Z","signature_b64":"Bufs2C96DEG7ZggU6Eerzq2p0Ns1cJUrTH21b+AlL9cHS6Zf+yh0iasJCo3p296pUqSOrsonT/TBVzgkenv+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a2b6f291c1ef2c1e30651d5f3e77728fed73466766a09ac608acdc08d2b8b8a","last_reissued_at":"2026-07-09T01:20:06.600705Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:06.600705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.16673","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MmoJMXnYneqk/OHERai+3PCHVxoU5toYzN4lwSt1al1xppMtOrr/3w74MOyc246r1W0PSPDIhNwvFGaypVV0CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:52:20.065003Z"},"content_sha256":"61514d9553f34d2afb1c116d0b5a0699d61a2ca824ee2f81d8f5bdd8f4c2ffb1","schema_version":"1.0","event_id":"sha256:61514d9553f34d2afb1c116d0b5a0699d61a2ca824ee2f81d8f5bdd8f4c2ffb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:NIVW6KI4D3ZMDYYGKHK7HZ3XFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMDiff: Extending Diffusion Transformers for Multi-Modal Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Christian Rupprecht, Orest Kupyn, Yagmur Akarken","submitted_at":"2026-06-15T13:08:06Z","abstract_excerpt":"Diffusion transformers have demonstrated remarkable generative capabilities, yet the rich perceptual representations computed across their denoising trajectory are discarded once the content is rendered. We present MMDiff, a framework that transforms a frozen diffusion transformer into a multi-modal generative system that jointly produces images alongside any combination of dense perceptual modalities using lightweight decoder heads. Our central finding is that perceptual information is temporally distributed along the denoising trajectory, and that multi-timestep feature fusion with spatially"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16673","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/2606.16673/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-09T01:20:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+8aMKg/5BILpR4XU584jeO0XefRkwgV7RoAuOdi/Sha70RWJpHziGvdh/meTxuEVoRAOQ4W/6sP/HP+Nd53Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:52:20.065527Z"},"content_sha256":"492901ebc06dbacf56f04fb2466414fc31dea74acbe61dd2b58a4610cdd9d9dc","schema_version":"1.0","event_id":"sha256:492901ebc06dbacf56f04fb2466414fc31dea74acbe61dd2b58a4610cdd9d9dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/bundle.json","state_url":"https://pith.science/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T17:52:20Z","links":{"resolver":"https://pith.science/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD","bundle":"https://pith.science/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/bundle.json","state":"https://pith.science/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NIVW6KI4D3ZMDYYGKHK7HZ3XFD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NIVW6KI4D3ZMDYYGKHK7HZ3XFD","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":"6a790c2860556da41ce8d96158ae4b758fdffaef7727880f6c7701d8d56200f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T13:08:06Z","title_canon_sha256":"666da84d3d84b6e1950bc95b9f635334d64a7f803344a29418ff08ac6af1695f"},"schema_version":"1.0","source":{"id":"2606.16673","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.16673","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"arxiv_version","alias_value":"2606.16673v2","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.16673","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_12","alias_value":"NIVW6KI4D3ZM","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_16","alias_value":"NIVW6KI4D3ZMDYYG","created_at":"2026-07-09T01:20:06Z"},{"alias_kind":"pith_short_8","alias_value":"NIVW6KI4","created_at":"2026-07-09T01:20:06Z"}],"graph_snapshots":[{"event_id":"sha256:492901ebc06dbacf56f04fb2466414fc31dea74acbe61dd2b58a4610cdd9d9dc","target":"graph","created_at":"2026-07-09T01:20:06Z","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/2606.16673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion transformers have demonstrated remarkable generative capabilities, yet the rich perceptual representations computed across their denoising trajectory are discarded once the content is rendered. We present MMDiff, a framework that transforms a frozen diffusion transformer into a multi-modal generative system that jointly produces images alongside any combination of dense perceptual modalities using lightweight decoder heads. Our central finding is that perceptual information is temporally distributed along the denoising trajectory, and that multi-timestep feature fusion with spatially","authors_text":"Christian Rupprecht, Orest Kupyn, Yagmur Akarken","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T13:08:06Z","title":"MMDiff: Extending Diffusion Transformers for Multi-Modal Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.16673","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":"sha256:61514d9553f34d2afb1c116d0b5a0699d61a2ca824ee2f81d8f5bdd8f4c2ffb1","target":"record","created_at":"2026-07-09T01:20:06Z","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":"6a790c2860556da41ce8d96158ae4b758fdffaef7727880f6c7701d8d56200f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-15T13:08:06Z","title_canon_sha256":"666da84d3d84b6e1950bc95b9f635334d64a7f803344a29418ff08ac6af1695f"},"schema_version":"1.0","source":{"id":"2606.16673","kind":"arxiv","version":2}},"canonical_sha256":"6a2b6f291c1ef2c1e30651d5f3e77728fed73466766a09ac608acdc08d2b8b8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a2b6f291c1ef2c1e30651d5f3e77728fed73466766a09ac608acdc08d2b8b8a","first_computed_at":"2026-07-09T01:20:06.600705Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:06.600705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bufs2C96DEG7ZggU6Eerzq2p0Ns1cJUrTH21b+AlL9cHS6Zf+yh0iasJCo3p296pUqSOrsonT/TBVzgkenv+CA==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:06.601183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.16673","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61514d9553f34d2afb1c116d0b5a0699d61a2ca824ee2f81d8f5bdd8f4c2ffb1","sha256:492901ebc06dbacf56f04fb2466414fc31dea74acbe61dd2b58a4610cdd9d9dc"],"state_sha256":"a955a99bc7f7fc776c60da1494f1d34e9781772cc43e3c5d7dc5e388d4963df7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQNSAcv2mp5U1+myDHlCa8EoJfDyszbqB99R3Db4RK6BiORhRFtHrAyQ75ry+pQ3Qy5fBrZsv6VK5d17kYKvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T17:52:20.070611Z","bundle_sha256":"8adaad8b14e84467f4b43f37af5301650e04ca3218beb31300423f958683b1fa"}}