{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4TTL7TN7FMSOICPAHDA7RPV4VX","short_pith_number":"pith:4TTL7TN7","canonical_record":{"source":{"id":"2412.01821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"e5c49069e3cb04abbe72e986fe549bfe2f1916e41927eb49f02dbcd7242664ad","abstract_canon_sha256":"772e96a7a42feb3a3391df191f573694fabd64d28e37cf7f73b12bba6c0a0a2f"},"schema_version":"1.0"},"canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","source":{"kind":"arxiv","id":"2412.01821","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4TTL7TN7FMSOICPAHDA7RPV4VX","target":"record","payload":{"canonical_record":{"source":{"id":"2412.01821","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-02T18:58:23Z","cross_cats_sorted":[],"title_canon_sha256":"e5c49069e3cb04abbe72e986fe549bfe2f1916e41927eb49f02dbcd7242664ad","abstract_canon_sha256":"772e96a7a42feb3a3391df191f573694fabd64d28e37cf7f73b12bba6c0a0a2f"},"schema_version":"1.0"},"canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:20.055057Z","signature_b64":"0FKPycT+WrFRWSFiyubfbOleaJIKzmJ1lGRFIB3DUmYk25ebdSOmeQxavl/0C5XhFcrmbQpMdd21yrdcFxWQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","last_reissued_at":"2026-07-05T09:43:20.054566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:20.054566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.01821","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":"2026-07-05T09:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4GVaGqnlG/LAtre6JKMcxpkoL4CUSRQIF9Yx8DPl8qHh6BWndWf6L9fVF9JcLD4HtgzHPDyfTTN0m+biS0LvDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:20:21.468840Z"},"content_sha256":"df5cc1a33011958e9cb624d2ad06e82c288206269b5f9d84c0b02d68785d1c4b","schema_version":"1.0","event_id":"sha256:df5cc1a33011958e9cb624d2ad06e82c288206269b5f9d84c0b02d68785d1c4b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4TTL7TN7FMSOICPAHDA7RPV4VX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"World-consistent Video Diffusion with Explicit 3D Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Jiatao Gu, Joshua Susskind, Kevin Miao, Miguel Angel Bautista, Qihang Zhang, Shuangfei Zhai","submitted_at":"2024-12-02T18:58:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01821","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/2412.01821/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":"2026-07-05T09:43:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6VwyTzQq+Sm3E57fuTKB9B8rbBbY0f4aQ2HKCqekicyEiT2hf/2anaWYwwlj6VVOi+2i6PnkmX2bC+Q++YgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:20:21.470373Z"},"content_sha256":"0fff49e996adbe8653d53fa0c4b1f73c66864d542f0fc4c1fc7ef01bf698d98d","schema_version":"1.0","event_id":"sha256:0fff49e996adbe8653d53fa0c4b1f73c66864d542f0fc4c1fc7ef01bf698d98d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/bundle.json","state_url":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/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":"2026-08-08T11:20:21Z","links":{"resolver":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX","bundle":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/bundle.json","state":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"64d/tCfk91bZrlJmVwKy3ndNCAFmzT2US0PWwJ+UGtjDtd7X+Suf6/qbYqzKbAXHvnrLCRYk6WXkMuV4ZNRzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:20:21.478771Z","bundle_sha256":"88ccc36a6ac6b6e853fb74c19678f785b92fbb217431dc33800d761e25f669b9"}}