{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4TTL7TN7FMSOICPAHDA7RPV4VX","short_pith_number":"pith:4TTL7TN7","schema_version":"1.0","canonical_sha256":"e4e6bfcdbf2b24e409e038c1f8bebcadcd29a4b61244aa68a2ca6fc7b5d54bcd","source":{"kind":"arxiv","id":"2412.01821","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01821","created_at":"2026-07-05T09:43:20.054626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01821v1","created_at":"2026-07-05T09:43:20.054626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01821","created_at":"2026-07-05T09:43:20.054626+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TTL7TN7FMSO","created_at":"2026-07-05T09:43:20.054626+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TTL7TN7FMSOICPA","created_at":"2026-07-05T09:43:20.054626+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TTL7TN7","created_at":"2026-07-05T09:43:20.054626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24321","citing_title":"Unified 3D Scene Understanding Through Physical World Modeling","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00990","citing_title":"Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX","json":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX.json","graph_json":"https://pith.science/api/pith-number/4TTL7TN7FMSOICPAHDA7RPV4VX/graph.json","events_json":"https://pith.science/api/pith-number/4TTL7TN7FMSOICPAHDA7RPV4VX/events.json","paper":"https://pith.science/paper/4TTL7TN7"},"agent_actions":{"view_html":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX","download_json":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX.json","view_paper":"https://pith.science/paper/4TTL7TN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01821&json=true","fetch_graph":"https://pith.science/api/pith-number/4TTL7TN7FMSOICPAHDA7RPV4VX/graph.json","fetch_events":"https://pith.science/api/pith-number/4TTL7TN7FMSOICPAHDA7RPV4VX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/action/storage_attestation","attest_author":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/action/author_attestation","sign_citation":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/action/citation_signature","submit_replication":"https://pith.science/pith/4TTL7TN7FMSOICPAHDA7RPV4VX/action/replication_record"}},"created_at":"2026-07-05T09:43:20.054626+00:00","updated_at":"2026-07-05T09:43:20.054626+00:00"}