{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I6GC5LUVVEBMTF732TQBRTU6M5","short_pith_number":"pith:I6GC5LUV","schema_version":"1.0","canonical_sha256":"478c2eae95a902c997fbd4e018ce9e67679780f84a63333e6b0ac60c7e844217","source":{"kind":"arxiv","id":"1904.12165","version":1},"attestation_state":"computed","paper":{"title":"Improved Conditional VRNNs for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Lluis Castrejon, Nicolas Ballas","submitted_at":"2019-04-27T15:07:12Z","abstract_excerpt":"Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model multiple possible future outcomes, they have a tendency to produce blurry predictions. In this work we argue that this is a sign of underfitting. To address this issue, we propose to increase the expressiveness of the latent distributions and to use higher capacity likelihood models. Our approach relies on a hierarchy of latent variables, which defines a family"},"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":"1904.12165","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-27T15:07:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2c29e818ba42bd11bc79cd6ac22a0ed08a0f237c1a98dc029b8fbb4a169e6059","abstract_canon_sha256":"6c8fd0a51786fe0c9a2ba694a009a4d6011a8c00ed7acecaa8ef6a5f6b38e981"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:38.787409Z","signature_b64":"SOkAzvyOSs/Hlv8WKbby4mGO4n7tUprvOzlyFp1bY6y+Pjk+oJyWIO75/LVHz8BrqUQSLy1vQR+0HU1GWf4+Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"478c2eae95a902c997fbd4e018ce9e67679780f84a63333e6b0ac60c7e844217","last_reissued_at":"2026-05-17T23:47:38.786901Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:38.786901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Conditional VRNNs for Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron Courville, Lluis Castrejon, Nicolas Ballas","submitted_at":"2019-04-27T15:07:12Z","abstract_excerpt":"Predicting future frames for a video sequence is a challenging generative modeling task. Promising approaches include probabilistic latent variable models such as the Variational Auto-Encoder. While VAEs can handle uncertainty and model multiple possible future outcomes, they have a tendency to produce blurry predictions. In this work we argue that this is a sign of underfitting. To address this issue, we propose to increase the expressiveness of the latent distributions and to use higher capacity likelihood models. Our approach relies on a hierarchy of latent variables, which defines a family"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.12165","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":"1904.12165","created_at":"2026-05-17T23:47:38.786978+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.12165v1","created_at":"2026-05-17T23:47:38.786978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.12165","created_at":"2026-05-17T23:47:38.786978+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6GC5LUVVEBM","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6GC5LUVVEBMTF73","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6GC5LUV","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5","json":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5.json","graph_json":"https://pith.science/api/pith-number/I6GC5LUVVEBMTF732TQBRTU6M5/graph.json","events_json":"https://pith.science/api/pith-number/I6GC5LUVVEBMTF732TQBRTU6M5/events.json","paper":"https://pith.science/paper/I6GC5LUV"},"agent_actions":{"view_html":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5","download_json":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5.json","view_paper":"https://pith.science/paper/I6GC5LUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.12165&json=true","fetch_graph":"https://pith.science/api/pith-number/I6GC5LUVVEBMTF732TQBRTU6M5/graph.json","fetch_events":"https://pith.science/api/pith-number/I6GC5LUVVEBMTF732TQBRTU6M5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5/action/storage_attestation","attest_author":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5/action/author_attestation","sign_citation":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5/action/citation_signature","submit_replication":"https://pith.science/pith/I6GC5LUVVEBMTF732TQBRTU6M5/action/replication_record"}},"created_at":"2026-05-17T23:47:38.786978+00:00","updated_at":"2026-05-17T23:47:38.786978+00:00"}