{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RYUDMKE26RQGHWKMBHJVHTVH4A","short_pith_number":"pith:RYUDMKE2","schema_version":"1.0","canonical_sha256":"8e2836289af46063d94c09d353cea7e0334bbd7ac7bc2400832f26e39b2b99c7","source":{"kind":"arxiv","id":"2203.10528","version":2},"attestation_state":"computed","paper":{"title":"Stochastic Video Prediction with Structure and Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adil Kaan Akan, Fatma G\\\"uney, Sadra Safadoust","submitted_at":"2022-03-20T11:29:46Z","abstract_excerpt":"While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera and independently moving foreground objects in driving scenarios. The existing methods fail to fully capture the dynamics of the structured world by only focusing on changes in pixels. In this paper, we assume that there is an underlying process creating observations in a video and propose to factorize it into static and dynamic components. We model the stat"},"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":"2203.10528","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-03-20T11:29:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6dfac50dacfc8bdb0b0813e22279ea1229a3a1a404a90bc62076653a7a67ec30","abstract_canon_sha256":"2027dcd1071eebc8693ff005fed3f4e7cdbe98e5fbf737e890d433d61043977a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:51.638193Z","signature_b64":"1NuOnD/9jO84Kpi4jtkV/U2v9vUvV0b4CwS+euj1fjsVh0aepBZBoe/OyIX4sjw34kpeyTTFgv8+2x3CZXR+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e2836289af46063d94c09d353cea7e0334bbd7ac7bc2400832f26e39b2b99c7","last_reissued_at":"2026-07-05T04:18:51.637809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:51.637809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Video Prediction with Structure and Motion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Adil Kaan Akan, Fatma G\\\"uney, Sadra Safadoust","submitted_at":"2022-03-20T11:29:46Z","abstract_excerpt":"While stochastic video prediction models enable future prediction under uncertainty, they mostly fail to model the complex dynamics of real-world scenes. For example, they cannot provide reliable predictions for scenes with a moving camera and independently moving foreground objects in driving scenarios. The existing methods fail to fully capture the dynamics of the structured world by only focusing on changes in pixels. In this paper, we assume that there is an underlying process creating observations in a video and propose to factorize it into static and dynamic components. We model the stat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10528","kind":"arxiv","version":2},"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/2203.10528/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":"2203.10528","created_at":"2026-07-05T04:18:51.637859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10528v2","created_at":"2026-07-05T04:18:51.637859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10528","created_at":"2026-07-05T04:18:51.637859+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYUDMKE26RQG","created_at":"2026-07-05T04:18:51.637859+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYUDMKE26RQGHWKM","created_at":"2026-07-05T04:18:51.637859+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYUDMKE2","created_at":"2026-07-05T04:18:51.637859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A","json":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A.json","graph_json":"https://pith.science/api/pith-number/RYUDMKE26RQGHWKMBHJVHTVH4A/graph.json","events_json":"https://pith.science/api/pith-number/RYUDMKE26RQGHWKMBHJVHTVH4A/events.json","paper":"https://pith.science/paper/RYUDMKE2"},"agent_actions":{"view_html":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A","download_json":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A.json","view_paper":"https://pith.science/paper/RYUDMKE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10528&json=true","fetch_graph":"https://pith.science/api/pith-number/RYUDMKE26RQGHWKMBHJVHTVH4A/graph.json","fetch_events":"https://pith.science/api/pith-number/RYUDMKE26RQGHWKMBHJVHTVH4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A/action/storage_attestation","attest_author":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A/action/author_attestation","sign_citation":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A/action/citation_signature","submit_replication":"https://pith.science/pith/RYUDMKE26RQGHWKMBHJVHTVH4A/action/replication_record"}},"created_at":"2026-07-05T04:18:51.637859+00:00","updated_at":"2026-07-05T04:18:51.637859+00:00"}