{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4TTL7TN7FMSOICPAHDA7RPV4VX","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":"772e96a7a42feb3a3391df191f573694fabd64d28e37cf7f73b12bba6c0a0a2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:58:23Z","title_canon_sha256":"e5c49069e3cb04abbe72e986fe549bfe2f1916e41927eb49f02dbcd7242664ad"},"schema_version":"1.0","source":{"id":"2412.01821","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01821","created_at":"2026-07-05T09:43:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01821v1","created_at":"2026-07-05T09:43:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01821","created_at":"2026-07-05T09:43:20Z"},{"alias_kind":"pith_short_12","alias_value":"4TTL7TN7FMSO","created_at":"2026-07-05T09:43:20Z"},{"alias_kind":"pith_short_16","alias_value":"4TTL7TN7FMSOICPA","created_at":"2026-07-05T09:43:20Z"},{"alias_kind":"pith_short_8","alias_value":"4TTL7TN7","created_at":"2026-07-05T09:43:20Z"}],"graph_snapshots":[{"event_id":"sha256:0fff49e996adbe8653d53fa0c4b1f73c66864d542f0fc4c1fc7ef01bf698d98d","target":"graph","created_at":"2026-07-05T09:43:20Z","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/2412.01821/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in diffusion models have set new benchmarks in image and video generation, enabling realistic visual synthesis across single- and multi-frame contexts. However, these models still struggle with efficiently and explicitly generating 3D-consistent content. To address this, we propose World-consistent Video Diffusion (WVD), a novel framework that incorporates explicit 3D supervision using XYZ images, which encode global 3D coordinates for each image pixel. More specifically, we train a diffusion transformer to learn the joint distribution of RGB and XYZ frames. This approach s","authors_text":"Alexander Toshev, Jiatao Gu, Joshua Susskind, Kevin Miao, Miguel Angel Bautista, Qihang Zhang, Shuangfei Zhai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:58:23Z","title":"World-consistent Video Diffusion with Explicit 3D Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01821","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:df5cc1a33011958e9cb624d2ad06e82c288206269b5f9d84c0b02d68785d1c4b","target":"record","created_at":"2026-07-05T09:43:20Z","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":"772e96a7a42feb3a3391df191f573694fabd64d28e37cf7f73b12bba6c0a0a2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:58:23Z","title_canon_sha256":"e5c49069e3cb04abbe72e986fe549bfe2f1916e41927eb49f02dbcd7242664ad"},"schema_version":"1.0","source":{"id":"2412.01821","kind":"arxiv","version":1}},"canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","first_computed_at":"2026-07-05T09:43:20.054566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:20.054566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0FKPycT+WrFRWSFiyubfbOleaJIKzmJ1lGRFIB3DUmYk25ebdSOmeQxavl/0C5XhFcrmbQpMdd21yrdcFxWQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:20.055057Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01821","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df5cc1a33011958e9cb624d2ad06e82c288206269b5f9d84c0b02d68785d1c4b","sha256:0fff49e996adbe8653d53fa0c4b1f73c66864d542f0fc4c1fc7ef01bf698d98d"],"state_sha256":"2f94704466ee8f951e163262162a9ac9b87fe7741a8fcda572f1b113a472f2ca"}