{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TUU7SHDR6NAY5EU6VSRLYYA3GG","short_pith_number":"pith:TUU7SHDR","canonical_record":{"source":{"id":"2411.08196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T21:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"1ec121e3c63aeb88f74d8cec33aaa5f95ae4b21e8d5e16cb4208b6c27e1b0ec8","abstract_canon_sha256":"27b2be4cfadf2645e0671dc4af779fd4d4ec9de3171fff01dd5df698d6331ace"},"schema_version":"1.0"},"canonical_sha256":"9d29f91c71f3418e929eaca2bc601b31a8572231f0cc0641adcba95e945475dc","source":{"kind":"arxiv","id":"2411.08196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08196","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08196v1","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08196","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"TUU7SHDR6NAY","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"TUU7SHDR6NAY5EU6","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"TUU7SHDR","created_at":"2026-07-05T09:34:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TUU7SHDR6NAY5EU6VSRLYYA3GG","target":"record","payload":{"canonical_record":{"source":{"id":"2411.08196","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T21:34:30Z","cross_cats_sorted":[],"title_canon_sha256":"1ec121e3c63aeb88f74d8cec33aaa5f95ae4b21e8d5e16cb4208b6c27e1b0ec8","abstract_canon_sha256":"27b2be4cfadf2645e0671dc4af779fd4d4ec9de3171fff01dd5df698d6331ace"},"schema_version":"1.0"},"canonical_sha256":"9d29f91c71f3418e929eaca2bc601b31a8572231f0cc0641adcba95e945475dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:34:43.081827Z","signature_b64":"7x/0FMddGZMQr36X0eW9ZTjX7Z6RqQovJTDizWQ+fDd8z+Xzrp69dHmqpDQqyXbNAIRWU160TsYn0CQCh943DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d29f91c71f3418e929eaca2bc601b31a8572231f0cc0641adcba95e945475dc","last_reissued_at":"2026-07-05T09:34:43.081300Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:34:43.081300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.08196","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":"2026-07-05T09:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T55voZ6q+DmWEW/+gvifSNu941fcI8+p0NhY/MFtxccoSTniw3S4TLVM3r6XMCRSaQHl5urgeADfF66MU2KZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:51:42.123312Z"},"content_sha256":"780c6cfa367e0c48f2c7f6335ad06fe3592de55f318d93527e277e1b528833a7","schema_version":"1.0","event_id":"sha256:780c6cfa367e0c48f2c7f6335ad06fe3592de55f318d93527e277e1b528833a7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TUU7SHDR6NAY5EU6VSRLYYA3GG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot 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":"2024-11-12T21:34:30Z","abstract_excerpt":"Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images. However, it remains largely unexplored how multimodal information collectively forms this joint space and how they guide the semantics of the synthesized images. In this paper, we investigate the latent space of DiT models and uncover two key properties: First, DiT's latent space is inherently semantically disentangled, where different semantic attributes can be co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08196","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/2411.08196/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":"2026-07-05T09:34:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NfjBhuIDyCm1GC6VKOSty2uLnjMiDVJgOslN+EYGT4xxviT1PKVKHM4f7RyNvMX2BfYiJdftWmPAHbyOUJg4BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:51:42.124339Z"},"content_sha256":"46308f211d8c5b5b6c7c1ad2e2c1c1a1fc4c64439430808199a3ef8c0c34af6d","schema_version":"1.0","event_id":"sha256:46308f211d8c5b5b6c7c1ad2e2c1c1a1fc4c64439430808199a3ef8c0c34af6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/bundle.json","state_url":"https://pith.science/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/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":"2026-08-11T19:51:42Z","links":{"resolver":"https://pith.science/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG","bundle":"https://pith.science/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/bundle.json","state":"https://pith.science/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUU7SHDR6NAY5EU6VSRLYYA3GG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TUU7SHDR6NAY5EU6VSRLYYA3GG","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":"27b2be4cfadf2645e0671dc4af779fd4d4ec9de3171fff01dd5df698d6331ace","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T21:34:30Z","title_canon_sha256":"1ec121e3c63aeb88f74d8cec33aaa5f95ae4b21e8d5e16cb4208b6c27e1b0ec8"},"schema_version":"1.0","source":{"id":"2411.08196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08196","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08196v1","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08196","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_12","alias_value":"TUU7SHDR6NAY","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_16","alias_value":"TUU7SHDR6NAY5EU6","created_at":"2026-07-05T09:34:43Z"},{"alias_kind":"pith_short_8","alias_value":"TUU7SHDR","created_at":"2026-07-05T09:34:43Z"}],"graph_snapshots":[{"event_id":"sha256:46308f211d8c5b5b6c7c1ad2e2c1c1a1fc4c64439430808199a3ef8c0c34af6d","target":"graph","created_at":"2026-07-05T09:34:43Z","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/2411.08196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) have recently achieved remarkable success in text-guided image generation. In image editing, DiTs project text and image inputs to a joint latent space, from which they decode and synthesize new images. However, it remains largely unexplored how multimodal information collectively forms this joint space and how they guide the semantics of the synthesized images. In this paper, we investigate the latent space of DiT models and uncover two key properties: First, DiT's latent space is inherently semantically disentangled, where different semantic attributes can be co","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":"2024-11-12T21:34:30Z","title":"Latent Space Disentanglement in Diffusion Transformers Enables Precise Zero-shot Semantic Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08196","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":"sha256:780c6cfa367e0c48f2c7f6335ad06fe3592de55f318d93527e277e1b528833a7","target":"record","created_at":"2026-07-05T09:34:43Z","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":"27b2be4cfadf2645e0671dc4af779fd4d4ec9de3171fff01dd5df698d6331ace","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-12T21:34:30Z","title_canon_sha256":"1ec121e3c63aeb88f74d8cec33aaa5f95ae4b21e8d5e16cb4208b6c27e1b0ec8"},"schema_version":"1.0","source":{"id":"2411.08196","kind":"arxiv","version":1}},"canonical_sha256":"9d29f91c71f3418e929eaca2bc601b31a8572231f0cc0641adcba95e945475dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d29f91c71f3418e929eaca2bc601b31a8572231f0cc0641adcba95e945475dc","first_computed_at":"2026-07-05T09:34:43.081300Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:34:43.081300Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7x/0FMddGZMQr36X0eW9ZTjX7Z6RqQovJTDizWQ+fDd8z+Xzrp69dHmqpDQqyXbNAIRWU160TsYn0CQCh943DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:34:43.081827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:780c6cfa367e0c48f2c7f6335ad06fe3592de55f318d93527e277e1b528833a7","sha256:46308f211d8c5b5b6c7c1ad2e2c1c1a1fc4c64439430808199a3ef8c0c34af6d"],"state_sha256":"2682bbc7156b249901ae02584aaeb1ab82e7480798491c925fd59b0f24d20fac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qEEo+GkkEwxamtAwEV2L2FmErHzQt1bwl8B/2xPnnRkMSykG9UtJ075hIZTh/B3QdkRgFcjYdheZZkdshWodAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:51:42.135996Z","bundle_sha256":"bd70b9b5e94a5b440d644031b777b4288aa007a94d0e3107afffd6420e315f3a"}}