{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MDF3X56GIY6XA4PKT4XZ37JJIM","short_pith_number":"pith:MDF3X56G","schema_version":"1.0","canonical_sha256":"60cbbbf7c6463d7071ea9f2f9dfd294334fb9a9e6fb16321cf406d78b375ea68","source":{"kind":"arxiv","id":"1610.00527","version":1},"attestation_state":"computed","paper":{"title":"Video Pixel Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron van den Oord, Alex Graves, Ivo Danihelka, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Oriol Vinyals","submitted_at":"2016-10-03T13:06:40Z","abstract_excerpt":"We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and "},"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":"1610.00527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-10-03T13:06:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ae2cb278b3258b7b611d886e01083b0392a2ec446537deb67c69dd251835399f","abstract_canon_sha256":"12c65f6c111ee7c40778852a849f15bdc15ea1b82dcd6232ecdb7036915e9e28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:13.377223Z","signature_b64":"wbWvPMbOzSfLYBPwNigcPyzwKvEFF7AS24ZFtlXwpK2uBlo3Q2ZwTCWK7adFSuB9Pmd0u+NX3oXadjYQdmQBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60cbbbf7c6463d7071ea9f2f9dfd294334fb9a9e6fb16321cf406d78b375ea68","last_reissued_at":"2026-05-18T01:03:13.376719Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:13.376719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video Pixel Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron van den Oord, Alex Graves, Ivo Danihelka, Karen Simonyan, Koray Kavukcuoglu, Nal Kalchbrenner, Oriol Vinyals","submitted_at":"2016-10-03T13:06:40Z","abstract_excerpt":"We propose a probabilistic video model, the Video Pixel Network (VPN), that estimates the discrete joint distribution of the raw pixel values in a video. The model and the neural architecture reflect the time, space and color structure of video tensors and encode it as a four-dimensional dependency chain. The VPN approaches the best possible performance on the Moving MNIST benchmark, a leap over the previous state of the art, and the generated videos show only minor deviations from the ground truth. The VPN also produces detailed samples on the action-conditional Robotic Pushing benchmark and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.00527","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":""},"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":"1610.00527","created_at":"2026-05-18T01:03:13.376798+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.00527v1","created_at":"2026-05-18T01:03:13.376798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.00527","created_at":"2026-05-18T01:03:13.376798+00:00"},{"alias_kind":"pith_short_12","alias_value":"MDF3X56GIY6X","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MDF3X56GIY6XA4PK","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MDF3X56G","created_at":"2026-05-18T12:30:32.724797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM","json":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM.json","graph_json":"https://pith.science/api/pith-number/MDF3X56GIY6XA4PKT4XZ37JJIM/graph.json","events_json":"https://pith.science/api/pith-number/MDF3X56GIY6XA4PKT4XZ37JJIM/events.json","paper":"https://pith.science/paper/MDF3X56G"},"agent_actions":{"view_html":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM","download_json":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM.json","view_paper":"https://pith.science/paper/MDF3X56G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.00527&json=true","fetch_graph":"https://pith.science/api/pith-number/MDF3X56GIY6XA4PKT4XZ37JJIM/graph.json","fetch_events":"https://pith.science/api/pith-number/MDF3X56GIY6XA4PKT4XZ37JJIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM/action/storage_attestation","attest_author":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM/action/author_attestation","sign_citation":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM/action/citation_signature","submit_replication":"https://pith.science/pith/MDF3X56GIY6XA4PKT4XZ37JJIM/action/replication_record"}},"created_at":"2026-05-18T01:03:13.376798+00:00","updated_at":"2026-05-18T01:03:13.376798+00:00"}