{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:5PQTZUYCLAJSIWXDLNEERXUSCN","short_pith_number":"pith:5PQTZUYC","schema_version":"1.0","canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","source":{"kind":"arxiv","id":"1406.1485","version":3},"attestation_state":"computed","paper":{"title":"Iterative Neural Autoregressive Distribution Estimator (NADE-k)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kyunghyun Cho, Li Yao, Tapani Raiko, Yoshua Bengio","submitted_at":"2014-06-05T19:13:51Z","abstract_excerpt":"Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in $k$ steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-predictive training: (1) Its test likelihood can be computed analytically, (2) it is easy to generate inde"},"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":"1406.1485","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-06-05T19:13:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9be11fb896fa32ab6cd823139a65723241cc74d0bd2811e6de96e2aebe332694","abstract_canon_sha256":"bc87709868f7f5c43ed8dfc04d72d05514d8f6f920010ca434c7475266fc51df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:31:59.949792Z","signature_b64":"KtA22vAtw8Bh3QDtmb4Cx8lV1V03zhckb8v3Q8Ic2Rd1TYPQSSsx3Jh4BIxJS1tlH022Vwrga+kV5t6dho9HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","last_reissued_at":"2026-05-18T02:31:59.949260Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:31:59.949260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Neural Autoregressive Distribution Estimator (NADE-k)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kyunghyun Cho, Li Yao, Tapani Raiko, Yoshua Bengio","submitted_at":"2014-06-05T19:13:51Z","abstract_excerpt":"Training of the neural autoregressive density estimator (NADE) can be viewed as doing one step of probabilistic inference on missing values in data. We propose a new model that extends this inference scheme to multiple steps, arguing that it is easier to learn to improve a reconstruction in $k$ steps rather than to learn to reconstruct in a single inference step. The proposed model is an unsupervised building block for deep learning that combines the desirable properties of NADE and multi-predictive training: (1) Its test likelihood can be computed analytically, (2) it is easy to generate inde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1485","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":"1406.1485","created_at":"2026-05-18T02:31:59.949346+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.1485v3","created_at":"2026-05-18T02:31:59.949346+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1485","created_at":"2026-05-18T02:31:59.949346+00:00"},{"alias_kind":"pith_short_12","alias_value":"5PQTZUYCLAJS","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_16","alias_value":"5PQTZUYCLAJSIWXD","created_at":"2026-05-18T12:28:14.216126+00:00"},{"alias_kind":"pith_short_8","alias_value":"5PQTZUYC","created_at":"2026-05-18T12:28:14.216126+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/5PQTZUYCLAJSIWXDLNEERXUSCN","json":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN.json","graph_json":"https://pith.science/api/pith-number/5PQTZUYCLAJSIWXDLNEERXUSCN/graph.json","events_json":"https://pith.science/api/pith-number/5PQTZUYCLAJSIWXDLNEERXUSCN/events.json","paper":"https://pith.science/paper/5PQTZUYC"},"agent_actions":{"view_html":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN","download_json":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN.json","view_paper":"https://pith.science/paper/5PQTZUYC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.1485&json=true","fetch_graph":"https://pith.science/api/pith-number/5PQTZUYCLAJSIWXDLNEERXUSCN/graph.json","fetch_events":"https://pith.science/api/pith-number/5PQTZUYCLAJSIWXDLNEERXUSCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/action/storage_attestation","attest_author":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/action/author_attestation","sign_citation":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/action/citation_signature","submit_replication":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/action/replication_record"}},"created_at":"2026-05-18T02:31:59.949346+00:00","updated_at":"2026-05-18T02:31:59.949346+00:00"}