{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KZFMVUQS3UTTYCICCV6IHVEROZ","short_pith_number":"pith:KZFMVUQS","canonical_record":{"source":{"id":"2408.13335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T19:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"deb2eb829cbd22b01fa7d90bee2ff08627169901ac9e348e46d9286788c9c747","abstract_canon_sha256":"d76aacc20351dfc9f5a00db8e4b0d07f8ad6b82947736a9082a07fa55c78ede6"},"schema_version":"1.0"},"canonical_sha256":"564acad212dd273c0902157c83d491764d5a60da0d58e7a4371dbed1493a5b6b","source":{"kind":"arxiv","id":"2408.13335","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13335","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13335v1","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13335","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"KZFMVUQS3UTT","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"KZFMVUQS3UTTYCIC","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"KZFMVUQS","created_at":"2026-07-05T08:58:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KZFMVUQS3UTTYCICCV6IHVEROZ","target":"record","payload":{"canonical_record":{"source":{"id":"2408.13335","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T19:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"deb2eb829cbd22b01fa7d90bee2ff08627169901ac9e348e46d9286788c9c747","abstract_canon_sha256":"d76aacc20351dfc9f5a00db8e4b0d07f8ad6b82947736a9082a07fa55c78ede6"},"schema_version":"1.0"},"canonical_sha256":"564acad212dd273c0902157c83d491764d5a60da0d58e7a4371dbed1493a5b6b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:48.995536Z","signature_b64":"xxk6VRCMaSryV/G0J2zPlgd6BFeV+t3+kjkTSkmOTXCEuugchUGkJ+LgdmSfDl33nqH22mBOH/u+XjCcEgjmBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"564acad212dd273c0902157c83d491764d5a60da0d58e7a4371dbed1493a5b6b","last_reissued_at":"2026-07-05T08:58:48.995077Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:48.995077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.13335","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PEnnftkJtK8PC7dmRk7fCx5XFLZGRqPEKeaIh5mnh5i/0Ncr60FLzJ/P1mHbysuMksoKoF/mG28rqajIXdtNDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:30:36.490320Z"},"content_sha256":"8ebb3796d5a066603d8bfc18eca72038cd1807e0378dabad4c5f332997453906","schema_version":"1.0","event_id":"sha256:8ebb3796d5a066603d8bfc18eca72038cd1807e0378dabad4c5f332997453906"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KZFMVUQS3UTTYCICCV6IHVEROZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowen Song, Chenwei Wu, Liyue Shen, Zhengxu Tang, Zitao Shuai","submitted_at":"2024-08-23T19:00:52Z","abstract_excerpt":"Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain largely unexplored. Through our investigation of DiT's latent space, we have uncovered key findings that unlock the potential for zero-shot fine-grained semantic editing: (1) Both the text and image spaces in DiTs are inherently decomposable. (2) These spaces collectively form a disentangled semantic representation space, enabling precise and fine-grained sem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13335","kind":"arxiv","version":1},"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/2408.13335/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":"2026-07-05T08:58:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jQV5Xd0Q1uW5DlNXH+loezXJhoaWxefumGP+OK/3bTTvj86q4yozpWNoxAQnLw834tKt3zMCxKFiwyj4lsJrDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:30:36.491332Z"},"content_sha256":"943ed592badda828538dbe76f9b9e803b14c8b696119453069e3a35e082edd12","schema_version":"1.0","event_id":"sha256:943ed592badda828538dbe76f9b9e803b14c8b696119453069e3a35e082edd12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/bundle.json","state_url":"https://pith.science/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/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":"2026-08-07T23:30:36Z","links":{"resolver":"https://pith.science/pith/KZFMVUQS3UTTYCICCV6IHVEROZ","bundle":"https://pith.science/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/bundle.json","state":"https://pith.science/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZFMVUQS3UTTYCICCV6IHVEROZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KZFMVUQS3UTTYCICCV6IHVEROZ","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":"d76aacc20351dfc9f5a00db8e4b0d07f8ad6b82947736a9082a07fa55c78ede6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T19:00:52Z","title_canon_sha256":"deb2eb829cbd22b01fa7d90bee2ff08627169901ac9e348e46d9286788c9c747"},"schema_version":"1.0","source":{"id":"2408.13335","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.13335","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"arxiv_version","alias_value":"2408.13335v1","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.13335","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_12","alias_value":"KZFMVUQS3UTT","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_16","alias_value":"KZFMVUQS3UTTYCIC","created_at":"2026-07-05T08:58:48Z"},{"alias_kind":"pith_short_8","alias_value":"KZFMVUQS","created_at":"2026-07-05T08:58:48Z"}],"graph_snapshots":[{"event_id":"sha256:943ed592badda828538dbe76f9b9e803b14c8b696119453069e3a35e082edd12","target":"graph","created_at":"2026-07-05T08:58:48Z","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/2408.13335/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) have achieved remarkable success in diverse and high-quality text-to-image(T2I) generation. However, how text and image latents individually and jointly contribute to the semantics of generated images, remain largely unexplored. Through our investigation of DiT's latent space, we have uncovered key findings that unlock the potential for zero-shot fine-grained semantic editing: (1) Both the text and image spaces in DiTs are inherently decomposable. (2) These spaces collectively form a disentangled semantic representation space, enabling precise and fine-grained sem","authors_text":"Bowen Song, Chenwei Wu, Liyue Shen, Zhengxu Tang, Zitao Shuai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T19:00:52Z","title":"Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.13335","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":"sha256:8ebb3796d5a066603d8bfc18eca72038cd1807e0378dabad4c5f332997453906","target":"record","created_at":"2026-07-05T08:58:48Z","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":"d76aacc20351dfc9f5a00db8e4b0d07f8ad6b82947736a9082a07fa55c78ede6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-23T19:00:52Z","title_canon_sha256":"deb2eb829cbd22b01fa7d90bee2ff08627169901ac9e348e46d9286788c9c747"},"schema_version":"1.0","source":{"id":"2408.13335","kind":"arxiv","version":1}},"canonical_sha256":"564acad212dd273c0902157c83d491764d5a60da0d58e7a4371dbed1493a5b6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"564acad212dd273c0902157c83d491764d5a60da0d58e7a4371dbed1493a5b6b","first_computed_at":"2026-07-05T08:58:48.995077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:48.995077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xxk6VRCMaSryV/G0J2zPlgd6BFeV+t3+kjkTSkmOTXCEuugchUGkJ+LgdmSfDl33nqH22mBOH/u+XjCcEgjmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:48.995536Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.13335","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ebb3796d5a066603d8bfc18eca72038cd1807e0378dabad4c5f332997453906","sha256:943ed592badda828538dbe76f9b9e803b14c8b696119453069e3a35e082edd12"],"state_sha256":"fa1c022da4a695b2807f52432f15b286094c0957b7756e066eb96dcbacec438f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEJssPumgN7/vO/elOHDHSCOx8K7jAPcuRbHgX34hTVAQAIlpIkrmHA10so1vcJr7f//wsVC9DsZ9SLDzTfPCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:30:36.498717Z","bundle_sha256":"4d2de59d4cc06d9e43923bbc940d1fab77382f3797fea3a8ac82b8305bbe5109"}}