{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QQ7AA3RYU6MQDC37HGOPSV5VLE","short_pith_number":"pith:QQ7AA3RY","schema_version":"1.0","canonical_sha256":"843e006e38a799018b7f399cf957b559173a653b7ffe57bdd4868040577be0bf","source":{"kind":"arxiv","id":"1711.04994","version":3},"attestation_state":"computed","paper":{"title":"Prediction Under Uncertainty with Error-Encoding Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junbo Zhao, Mikael Henaff, Yann LeCun","submitted_at":"2017-11-14T08:32:43Z","abstract_excerpt":"In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future state which are predictable from those which are inherently unpredictable, and encoding the unpredictable components into a low-dimensional latent variable which is fed into a forward model. Our method uses a supervised training objective which is fast and easy to train. We evaluate it in the context of video prediction on multiple datasets and show that it is able to consistently generate diverse predictions withou"},"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":"1711.04994","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-11-14T08:32:43Z","cross_cats_sorted":[],"title_canon_sha256":"ef59bc070e8db9509a301e8e9d119731c573a1cac3e3097a3f256a4f3601bad9","abstract_canon_sha256":"36e847210e10fd035aa0edcd199b83b6005bd2fd117c6692e726b30320db4b26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:07.967756Z","signature_b64":"zWJ3PontV4KXuYvisJ1tWObMIKUEZazleXc0T38E6GNcd46ecd8Jw7nNkSayW2FB13JvNq1TEYvK8RPA+ujGBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"843e006e38a799018b7f399cf957b559173a653b7ffe57bdd4868040577be0bf","last_reissued_at":"2026-05-18T00:29:07.967015Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:07.967015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prediction Under Uncertainty with Error-Encoding Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junbo Zhao, Mikael Henaff, Yann LeCun","submitted_at":"2017-11-14T08:32:43Z","abstract_excerpt":"In this work we introduce a new framework for performing temporal predictions in the presence of uncertainty. It is based on a simple idea of disentangling components of the future state which are predictable from those which are inherently unpredictable, and encoding the unpredictable components into a low-dimensional latent variable which is fed into a forward model. Our method uses a supervised training objective which is fast and easy to train. We evaluate it in the context of video prediction on multiple datasets and show that it is able to consistently generate diverse predictions withou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04994","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":"1711.04994","created_at":"2026-05-18T00:29:07.967129+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04994v3","created_at":"2026-05-18T00:29:07.967129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04994","created_at":"2026-05-18T00:29:07.967129+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQ7AA3RYU6MQ","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQ7AA3RYU6MQDC37","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQ7AA3RY","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.10101","citing_title":"LMVP: Video Predictor with Leaked Motion Information","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15411","citing_title":"A Hybrid Modeling Framework for Crop Prediction Tasks via Dynamic Parameter Calibration and Multi-Task Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE","json":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE.json","graph_json":"https://pith.science/api/pith-number/QQ7AA3RYU6MQDC37HGOPSV5VLE/graph.json","events_json":"https://pith.science/api/pith-number/QQ7AA3RYU6MQDC37HGOPSV5VLE/events.json","paper":"https://pith.science/paper/QQ7AA3RY"},"agent_actions":{"view_html":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE","download_json":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE.json","view_paper":"https://pith.science/paper/QQ7AA3RY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04994&json=true","fetch_graph":"https://pith.science/api/pith-number/QQ7AA3RYU6MQDC37HGOPSV5VLE/graph.json","fetch_events":"https://pith.science/api/pith-number/QQ7AA3RYU6MQDC37HGOPSV5VLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE/action/storage_attestation","attest_author":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE/action/author_attestation","sign_citation":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE/action/citation_signature","submit_replication":"https://pith.science/pith/QQ7AA3RYU6MQDC37HGOPSV5VLE/action/replication_record"}},"created_at":"2026-05-18T00:29:07.967129+00:00","updated_at":"2026-05-18T00:29:07.967129+00:00"}