{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QIKIARC5SWBBINX4DOZGVXNQ4S","short_pith_number":"pith:QIKIARC5","schema_version":"1.0","canonical_sha256":"821480445d95821436fc1bb26addb0e4ac2c5d6dcd9c10398e0babe95f88661f","source":{"kind":"arxiv","id":"1804.01523","version":1},"attestation_state":"computed","paper":{"title":"Stochastic Adversarial Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alex X. Lee, Chelsea Finn, Frederik Ebert, Pieter Abbeel, Richard Zhang, Sergey Levine","submitted_at":"2018-04-04T17:55:40Z","abstract_excerpt":"Being able to predict what may happen in the future requires an in-depth understanding of the physical and causal rules that govern the world. A model that is able to do so has a number of appealing applications, from robotic planning to representation learning. However, learning to predict raw future observations, such as frames in a video, is exceedingly challenging -- the ambiguous nature of the problem can cause a naively designed model to average together possible futures into a single, blurry prediction. Recently, this has been addressed by two distinct approaches: (a) latent variational"},"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":"1804.01523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-04T17:55:40Z","cross_cats_sorted":["cs.AI","cs.LG","cs.RO"],"title_canon_sha256":"d2b61b6b67274fa7f69a9d9844a976155e45303dff7979d78894b35e834877d6","abstract_canon_sha256":"ad72eca4302e1126dff9fa6161635b789d28bf9d1043142c8286cb6573c6f0a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:14.765229Z","signature_b64":"P7X4aPsF19E7F6mRsFHZAMCTgqlhBjvrZXLwnYIxUjt6IIlTMkkkEo2hGVM3Fr/qOQ2ytrLw7LcRXCAJDqEZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"821480445d95821436fc1bb26addb0e4ac2c5d6dcd9c10398e0babe95f88661f","last_reissued_at":"2026-05-18T00:19:14.764394Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:14.764394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stochastic Adversarial Video Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.RO"],"primary_cat":"cs.CV","authors_text":"Alex X. Lee, Chelsea Finn, Frederik Ebert, Pieter Abbeel, Richard Zhang, Sergey Levine","submitted_at":"2018-04-04T17:55:40Z","abstract_excerpt":"Being able to predict what may happen in the future requires an in-depth understanding of the physical and causal rules that govern the world. A model that is able to do so has a number of appealing applications, from robotic planning to representation learning. However, learning to predict raw future observations, such as frames in a video, is exceedingly challenging -- the ambiguous nature of the problem can cause a naively designed model to average together possible futures into a single, blurry prediction. Recently, this has been addressed by two distinct approaches: (a) latent variational"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.01523","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":"1804.01523","created_at":"2026-05-18T00:19:14.764547+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.01523v1","created_at":"2026-05-18T00:19:14.764547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.01523","created_at":"2026-05-18T00:19:14.764547+00:00"},{"alias_kind":"pith_short_12","alias_value":"QIKIARC5SWBB","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QIKIARC5SWBBINX4","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QIKIARC5","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1907.08845","citing_title":"Order Matters: Shuffling Sequence Generation for Video Prediction","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2304.11193","citing_title":"Multi-Modal World Model for Physical Robot Interactions: Simultaneous Visual and Tactile Predictions for Enhanced Accuracy","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"1910.11215","citing_title":"RoboNet: Large-Scale Multi-Robot Learning","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":234,"is_internal_anchor":true},{"citing_arxiv_id":"2310.06114","citing_title":"Learning Interactive Real-World Simulators","ref_index":267,"is_internal_anchor":true},{"citing_arxiv_id":"2508.00795","citing_title":"Video Generators are Robot Policies","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20537","citing_title":"PFGNet: A Fully Convolutional Frequency-Guided Peripheral Gating Network for Efficient Spatiotemporal Predictive Learning","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2211.15657","citing_title":"Is Conditional Generative Modeling all you need for Decision-Making?","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2104.10157","citing_title":"VideoGPT: Video Generation using VQ-VAE and Transformers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2311.15127","citing_title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S","json":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S.json","graph_json":"https://pith.science/api/pith-number/QIKIARC5SWBBINX4DOZGVXNQ4S/graph.json","events_json":"https://pith.science/api/pith-number/QIKIARC5SWBBINX4DOZGVXNQ4S/events.json","paper":"https://pith.science/paper/QIKIARC5"},"agent_actions":{"view_html":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S","download_json":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S.json","view_paper":"https://pith.science/paper/QIKIARC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.01523&json=true","fetch_graph":"https://pith.science/api/pith-number/QIKIARC5SWBBINX4DOZGVXNQ4S/graph.json","fetch_events":"https://pith.science/api/pith-number/QIKIARC5SWBBINX4DOZGVXNQ4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S/action/storage_attestation","attest_author":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S/action/author_attestation","sign_citation":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S/action/citation_signature","submit_replication":"https://pith.science/pith/QIKIARC5SWBBINX4DOZGVXNQ4S/action/replication_record"}},"created_at":"2026-05-18T00:19:14.764547+00:00","updated_at":"2026-05-18T00:19:14.764547+00:00"}