{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JMEMFZED6ESXJBS263ODE7LMCI","short_pith_number":"pith:JMEMFZED","canonical_record":{"source":{"id":"2407.12781","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"18a08df71b10ab92b34975ec553d5addbc1e27697907ae9768c9a2f886706ad8","abstract_canon_sha256":"bd335dcb18c57697013b5137c6c064704f9692770a36f4119544ec64424dd147"},"schema_version":"1.0"},"canonical_sha256":"4b08c2e483f12574865af6dc327d6c122dfb80b9cdaf65cb1001aaba729213c4","source":{"kind":"arxiv","id":"2407.12781","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12781","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12781v3","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12781","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"JMEMFZED6ESX","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMEMFZED6ESXJBS2","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMEMFZED","created_at":"2026-07-05T10:37:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JMEMFZED6ESXJBS263ODE7LMCI","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12781","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:59:05Z","cross_cats_sorted":[],"title_canon_sha256":"18a08df71b10ab92b34975ec553d5addbc1e27697907ae9768c9a2f886706ad8","abstract_canon_sha256":"bd335dcb18c57697013b5137c6c064704f9692770a36f4119544ec64424dd147"},"schema_version":"1.0"},"canonical_sha256":"4b08c2e483f12574865af6dc327d6c122dfb80b9cdaf65cb1001aaba729213c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:31.123671Z","signature_b64":"VSyRY3G+3cz2aFrXvh/I2mhNxhgfBzrQHspJuJ933LAUMLh208pn/zkwPiI00DFdKLuETFhXk1T1mBzof4XVAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b08c2e483f12574865af6dc327d6c122dfb80b9cdaf65cb1001aaba729213c4","last_reissued_at":"2026-07-05T10:37:31.122736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:31.122736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12781","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MMoZfZzQWaTOYORiUj2nLsrtkj9jQBqtQNHPK0O1qZDrIrnEMBcOKpUBh5grjy4THOzoVpTtO4Em1by6vrGiDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:32:37.421937Z"},"content_sha256":"5dc13cd7b915fe63e07b364f82e5ae665454f3f16b1127fdd0f40fdd889eae81","schema_version":"1.0","event_id":"sha256:5dc13cd7b915fe63e07b364f82e5ae665454f3f16b1127fdd0f40fdd889eae81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JMEMFZED6ESXJBS263ODE7LMCI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aliaksandr Siarohin, Andrea Tagliasacchi, Chaoyang Wang, David B. Lindell, Guocheng Qian, Hsin-Ying Lee, Ivan Skorokhodov, Jiaxu Zou, Michael Vasilkovsky, Sergey Tulyakov, Sherwin Bahmani, Willi Menapace","submitted_at":"2024-07-17T17:59:05Z","abstract_excerpt":"Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, and 3D vision. Recently, new methods demonstrate the ability to generate videos with controllable camera poses these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation. Still, no existing approach enables camera control for new, tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12781","kind":"arxiv","version":3},"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/2407.12781/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":"2026-07-05T10:37:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7M/1a9nQtNeBgx7Brmj7PRLC2TbrANJk8SzlWcH0L/07/VjKIuProzTKIXZdB0ZIN3Al3lcDYNJG8YACspDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T07:32:37.422330Z"},"content_sha256":"1bad416224aad722cc0ad023aa8eb3d773e2fa29912b48febdbb5a2c50503d92","schema_version":"1.0","event_id":"sha256:1bad416224aad722cc0ad023aa8eb3d773e2fa29912b48febdbb5a2c50503d92"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMEMFZED6ESXJBS263ODE7LMCI/bundle.json","state_url":"https://pith.science/pith/JMEMFZED6ESXJBS263ODE7LMCI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMEMFZED6ESXJBS263ODE7LMCI/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":"2026-07-27T07:32:37Z","links":{"resolver":"https://pith.science/pith/JMEMFZED6ESXJBS263ODE7LMCI","bundle":"https://pith.science/pith/JMEMFZED6ESXJBS263ODE7LMCI/bundle.json","state":"https://pith.science/pith/JMEMFZED6ESXJBS263ODE7LMCI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMEMFZED6ESXJBS263ODE7LMCI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JMEMFZED6ESXJBS263ODE7LMCI","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":"bd335dcb18c57697013b5137c6c064704f9692770a36f4119544ec64424dd147","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:59:05Z","title_canon_sha256":"18a08df71b10ab92b34975ec553d5addbc1e27697907ae9768c9a2f886706ad8"},"schema_version":"1.0","source":{"id":"2407.12781","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12781","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12781v3","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12781","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_12","alias_value":"JMEMFZED6ESX","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMEMFZED6ESXJBS2","created_at":"2026-07-05T10:37:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMEMFZED","created_at":"2026-07-05T10:37:31Z"}],"graph_snapshots":[{"event_id":"sha256:1bad416224aad722cc0ad023aa8eb3d773e2fa29912b48febdbb5a2c50503d92","target":"graph","created_at":"2026-07-05T10:37:31Z","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/2407.12781/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is critical for downstream applications related to content creation, visual effects, and 3D vision. Recently, new methods demonstrate the ability to generate videos with controllable camera poses these techniques leverage pre-trained U-Net-based diffusion models that explicitly disentangle spatial and temporal generation. Still, no existing approach enables camera control for new, tra","authors_text":"Aliaksandr Siarohin, Andrea Tagliasacchi, Chaoyang Wang, David B. Lindell, Guocheng Qian, Hsin-Ying Lee, Ivan Skorokhodov, Jiaxu Zou, Michael Vasilkovsky, Sergey Tulyakov, Sherwin Bahmani, Willi Menapace","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:59:05Z","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12781","kind":"arxiv","version":3},"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":"sha256:5dc13cd7b915fe63e07b364f82e5ae665454f3f16b1127fdd0f40fdd889eae81","target":"record","created_at":"2026-07-05T10:37:31Z","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":"bd335dcb18c57697013b5137c6c064704f9692770a36f4119544ec64424dd147","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-17T17:59:05Z","title_canon_sha256":"18a08df71b10ab92b34975ec553d5addbc1e27697907ae9768c9a2f886706ad8"},"schema_version":"1.0","source":{"id":"2407.12781","kind":"arxiv","version":3}},"canonical_sha256":"4b08c2e483f12574865af6dc327d6c122dfb80b9cdaf65cb1001aaba729213c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b08c2e483f12574865af6dc327d6c122dfb80b9cdaf65cb1001aaba729213c4","first_computed_at":"2026-07-05T10:37:31.122736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:31.122736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VSyRY3G+3cz2aFrXvh/I2mhNxhgfBzrQHspJuJ933LAUMLh208pn/zkwPiI00DFdKLuETFhXk1T1mBzof4XVAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:31.123671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12781","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dc13cd7b915fe63e07b364f82e5ae665454f3f16b1127fdd0f40fdd889eae81","sha256:1bad416224aad722cc0ad023aa8eb3d773e2fa29912b48febdbb5a2c50503d92"],"state_sha256":"cc4f15ea4951a91f3d1b7d87b2966ecf3e496117488dbd1b06bff282013bb929"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sKEr043/RWsDQtGyvCRkQFLWqSYmErQTi+ysL9aVIZoktwvnsZqJpY/5UkuWXlwNl0IjvkuRuKigoc88+jgsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T07:32:37.424768Z","bundle_sha256":"cda58acd9c8e18244b5938304701e82c7b4826a3636ad2b25466178a4f1fe7c4"}}