{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PLUUODBCGHELA7TEQLA54273DN","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":"833c824125563742c2f1d223bd211edee8283e01eed3677f28d2ba00f13e2346","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-02T13:04:47Z","title_canon_sha256":"789eb2a1883f0da3ab46aaba103240bbbfa168317bce27c19311ca0d7ac6d501"},"schema_version":"1.0","source":{"id":"2601.00678","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.00678","created_at":"2026-05-20T00:00:31Z"},{"alias_kind":"arxiv_version","alias_value":"2601.00678v3","created_at":"2026-05-20T00:00:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.00678","created_at":"2026-05-20T00:00:31Z"},{"alias_kind":"pith_short_12","alias_value":"PLUUODBCGHEL","created_at":"2026-05-20T00:00:31Z"},{"alias_kind":"pith_short_16","alias_value":"PLUUODBCGHELA7TE","created_at":"2026-05-20T00:00:31Z"},{"alias_kind":"pith_short_8","alias_value":"PLUUODBC","created_at":"2026-05-20T00:00:31Z"}],"graph_snapshots":[{"event_id":"sha256:64e432a67382ffcab575785390d6f7ba458a624ff4724f5e13b912b029d2c58f","target":"graph","created_at":"2026-05-20T00:00:31Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass."}],"snapshot_sha256":"024267b2deef697a55d825b93499a445927c43dbc65c677cf09bd9159cf5ec07"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"203fea5536753bc95fa3d789080eabf1b6a2a225a4d6a209c5c3dffd008f6d29"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.00678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humans excel at forecasting the future dynamics of a scene given just a single image. Video generation models that can mimic this ability are an essential component for intelligent systems. Recent approaches have improved temporal coherence and 3D consistency in single-image-conditioned video generation. However, these methods often lack robust user controllability, such as modifying the camera path, limiting their applicability in real-world applications. Most existing camera-controlled image-to-video models struggle with accurately modeling camera motion, maintaining temporal consistency, an","authors_text":"Daniela Ivanova, John H. Williamson, Melonie de Almeida, Paul Henderson, Tong Shi","cross_cats":[],"headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-02T13:04:47Z","title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.00678","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T18:16:01.870709Z","id":"3a99a645-2cc1-4cb4-81cd-e05d2bc3844d","model_set":{"reader":"grok-4.3"},"one_line_summary":"A unified single-pass framework using dynamic 3D Gaussians generates temporally consistent camera-controlled videos from a single image.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single image generates camera-controlled 4D video by building dynamic 3D Gaussians in one forward pass.","strongest_claim":"We propose a novel framework that constructs a 3D Gaussian scene representation and samples plausible object motion, given a single image in a single forward pass. This enables fast, camera-guided video generation without the need for iterative denoising to inject object motion into render frames.","weakest_assumption":"That a single static image contains enough information to construct an accurate 3D Gaussian representation and to sample plausible, temporally consistent object motions that align with an arbitrary camera trajectory."}},"verdict_id":"3a99a645-2cc1-4cb4-81cd-e05d2bc3844d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ccd5a24550bf370f2cfa25092f04f0133964d7dc3071d5a41363246d0c8d79ff","target":"record","created_at":"2026-05-20T00:00:31Z","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":"833c824125563742c2f1d223bd211edee8283e01eed3677f28d2ba00f13e2346","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-02T13:04:47Z","title_canon_sha256":"789eb2a1883f0da3ab46aaba103240bbbfa168317bce27c19311ca0d7ac6d501"},"schema_version":"1.0","source":{"id":"2601.00678","kind":"arxiv","version":3}},"canonical_sha256":"7ae9470c2231c8b07e6482c1de6bfb1b7859c17f6a18bf49f43a968811250699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ae9470c2231c8b07e6482c1de6bfb1b7859c17f6a18bf49f43a968811250699","first_computed_at":"2026-05-20T00:00:31.597676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:31.597676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x/D/awwKgQy11mbe5nrrTyCCyWWNi+4g0W4i/w3qnjt0PwDj/eipMULhArhEMwjhd5em5i3VxxB6Omh3rs8yBw==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:31.598471Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.00678","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccd5a24550bf370f2cfa25092f04f0133964d7dc3071d5a41363246d0c8d79ff","sha256:64e432a67382ffcab575785390d6f7ba458a624ff4724f5e13b912b029d2c58f"],"state_sha256":"e219338ab32c927a90566899f6481f92b300fc12be3e3335c2ae5c3120e4958a"}