{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:JNQ7XYFB6MFYWQB7UHB7YOOZPS","short_pith_number":"pith:JNQ7XYFB","schema_version":"1.0","canonical_sha256":"4b61fbe0a1f30b8b403fa1c3fc39d97ca8590eb73d0301f2ff7c1c360cbada02","source":{"kind":"arxiv","id":"1609.02612","version":3},"attestation_state":"computed","paper":{"title":"Generating Videos with Scene Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash","submitted_at":"2016-09-08T22:29:52Z","abstract_excerpt":"We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene's foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualiz"},"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":"1609.02612","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-09-08T22:29:52Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"9b089d676be6581ae777dc8009004e9859dd16f2e2a659ce8370083a72907748","abstract_canon_sha256":"9b29315205cc21c4a54f001c36f94d582c478451b9e177d952b2219d23d220d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:15.394928Z","signature_b64":"noJuHZBj4RJesC22RGDzwzvNYSh+6F1E+RM2pFlElGzh9I6mDpWa0be2Dhc5vwgMyYjNeBrA1swbfe/juGVIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b61fbe0a1f30b8b403fa1c3fc39d97ca8590eb73d0301f2ff7c1c360cbada02","last_reissued_at":"2026-05-18T01:01:15.394252Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:15.394252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Videos with Scene Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antonio Torralba, Carl Vondrick, Hamed Pirsiavash","submitted_at":"2016-09-08T22:29:52Z","abstract_excerpt":"We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative adversarial network for video with a spatio-temporal convolutional architecture that untangles the scene's foreground from the background. Experiments suggest this model can generate tiny videos up to a second at full frame rate better than simple baselines, and we show its utility at predicting plausible futures of static images. Moreover, experiments and visualiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.02612","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1609.02612","created_at":"2026-05-18T01:01:15.394365+00:00"},{"alias_kind":"arxiv_version","alias_value":"1609.02612v3","created_at":"2026-05-18T01:01:15.394365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.02612","created_at":"2026-05-18T01:01:15.394365+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNQ7XYFB6MFY","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNQ7XYFB6MFYWQB7","created_at":"2026-05-18T12:30:25.849896+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNQ7XYFB","created_at":"2026-05-18T12:30:25.849896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10182","citing_title":"Planning Robot Motion using Deep Visual Prediction","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2210.02399","citing_title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2210.02303","citing_title":"Imagen Video: High Definition Video Generation with Diffusion Models","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS","json":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS.json","graph_json":"https://pith.science/api/pith-number/JNQ7XYFB6MFYWQB7UHB7YOOZPS/graph.json","events_json":"https://pith.science/api/pith-number/JNQ7XYFB6MFYWQB7UHB7YOOZPS/events.json","paper":"https://pith.science/paper/JNQ7XYFB"},"agent_actions":{"view_html":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS","download_json":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS.json","view_paper":"https://pith.science/paper/JNQ7XYFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1609.02612&json=true","fetch_graph":"https://pith.science/api/pith-number/JNQ7XYFB6MFYWQB7UHB7YOOZPS/graph.json","fetch_events":"https://pith.science/api/pith-number/JNQ7XYFB6MFYWQB7UHB7YOOZPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS/action/storage_attestation","attest_author":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS/action/author_attestation","sign_citation":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS/action/citation_signature","submit_replication":"https://pith.science/pith/JNQ7XYFB6MFYWQB7UHB7YOOZPS/action/replication_record"}},"created_at":"2026-05-18T01:01:15.394365+00:00","updated_at":"2026-05-18T01:01:15.394365+00:00"}