{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MKY5RZCQW7IA6XA5SS5ZSCOTHL","short_pith_number":"pith:MKY5RZCQ","schema_version":"1.0","canonical_sha256":"62b1d8e450b7d00f5c1d94bb9909d33afeb1593efec0447d3ab7409a158d5863","source":{"kind":"arxiv","id":"2501.08331","version":5},"attestation_state":"computed","paper":{"title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Ma, Lingxiao Li, Michael Ryoo, Mingming He, Mohsen Mousavi, Ning Yu, Oliver Pilarski, Pascal Clausen, Paul Debevec, Ryan Burgert, Wenqi Xian, Yitong Deng, Yuancheng Xu","submitted_at":"2025-01-14T18:59:10Z","abstract_excerpt":"Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequently, our method is agnostic to diffusion model design, requiring no changes to model architectures or training pipelines. Specifically, we propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise derived from opti"},"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":"2501.08331","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T18:59:10Z","cross_cats_sorted":[],"title_canon_sha256":"934ec097a3e095cd5215f1e88db5c4ff9b6d9531aaebeb085fed3e9b429fa333","abstract_canon_sha256":"bcaffc5b4080cddff9aa4207e348718675f81dd98621df63cc07d6b2ae1b6006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:06.246788Z","signature_b64":"iF2mGKiU+yl5zTy8BSi+IxZSZmMmWUcfxXixe6H3fPt/RR3Th9tbyTNTjtkc2dIRT1Ugad5y6ZQf4pBVsZnxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62b1d8e450b7d00f5c1d94bb9909d33afeb1593efec0447d3ab7409a158d5863","last_reissued_at":"2026-07-05T11:49:06.246301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:06.246301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Li Ma, Lingxiao Li, Michael Ryoo, Mingming He, Mohsen Mousavi, Ning Yu, Oliver Pilarski, Pascal Clausen, Paul Debevec, Ryan Burgert, Wenqi Xian, Yitong Deng, Yuancheng Xu","submitted_at":"2025-01-14T18:59:10Z","abstract_excerpt":"Generative modeling aims to transform random noise into structured outputs. In this work, we enhance video diffusion models by allowing motion control via structured latent noise sampling. This is achieved by just a change in data: we pre-process training videos to yield structured noise. Consequently, our method is agnostic to diffusion model design, requiring no changes to model architectures or training pipelines. Specifically, we propose a novel noise warping algorithm, fast enough to run in real time, that replaces random temporal Gaussianity with correlated warped noise derived from opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08331","kind":"arxiv","version":5},"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/2501.08331/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":"2501.08331","created_at":"2026-07-05T11:49:06.246365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08331v5","created_at":"2026-07-05T11:49:06.246365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08331","created_at":"2026-07-05T11:49:06.246365+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKY5RZCQW7IA","created_at":"2026-07-05T11:49:06.246365+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKY5RZCQW7IA6XA5","created_at":"2026-07-05T11:49:06.246365+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKY5RZCQ","created_at":"2026-07-05T11:49:06.246365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.19840","citing_title":"GenHSI: Controllable Generation of Human-Scene Interaction Videos","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05961","citing_title":"HumANDiff: Articulated Noise Diffusion for Motion-Consistent Human Video Generation","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL","json":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL.json","graph_json":"https://pith.science/api/pith-number/MKY5RZCQW7IA6XA5SS5ZSCOTHL/graph.json","events_json":"https://pith.science/api/pith-number/MKY5RZCQW7IA6XA5SS5ZSCOTHL/events.json","paper":"https://pith.science/paper/MKY5RZCQ"},"agent_actions":{"view_html":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL","download_json":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL.json","view_paper":"https://pith.science/paper/MKY5RZCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08331&json=true","fetch_graph":"https://pith.science/api/pith-number/MKY5RZCQW7IA6XA5SS5ZSCOTHL/graph.json","fetch_events":"https://pith.science/api/pith-number/MKY5RZCQW7IA6XA5SS5ZSCOTHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL/action/storage_attestation","attest_author":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL/action/author_attestation","sign_citation":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL/action/citation_signature","submit_replication":"https://pith.science/pith/MKY5RZCQW7IA6XA5SS5ZSCOTHL/action/replication_record"}},"created_at":"2026-07-05T11:49:06.246365+00:00","updated_at":"2026-07-05T11:49:06.246365+00:00"}