{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:5PQTZUYCLAJSIWXDLNEERXUSCN","short_pith_number":"pith:5PQTZUYC","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"},"canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","source":{"kind":"arxiv","id":"1406.1485","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1485","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1485v3","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1485","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"5PQTZUYCLAJS","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"5PQTZUYCLAJSIWXD","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"5PQTZUYC","created_at":"2026-05-18T12:28:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:5PQTZUYCLAJSIWXDLNEERXUSCN","target":"record","payload":{"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"},"canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","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"},"source_kind":"arxiv","source_id":"1406.1485","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kl2iW89q6Eyk/G3ak3ol6Cm8ghOeiRqmNm5tIH1xFpEwi2UAQWwFSPJf660M7DINPvB8xxO37O42RmQ+092MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T04:19:18.403562Z"},"content_sha256":"b0161c64550a982e603989cd28cf1525889d2e770f231548d93292b34b000568","schema_version":"1.0","event_id":"sha256:b0161c64550a982e603989cd28cf1525889d2e770f231548d93292b34b000568"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:5PQTZUYCLAJSIWXDLNEERXUSCN","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:31:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xjAjrT0Na/whLhz653rBkcuZ6UoJ0Fv59UfyMd3c5ax5KIVOWvw3AE3pN9oMYiQ7OqmaYfUzVdeL2jgLu9swBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T04:19:18.404260Z"},"content_sha256":"3be74741cc54e5d5407f359cbee91d9d1a2dae1b61858d8d3850d537cf06cd2a","schema_version":"1.0","event_id":"sha256:3be74741cc54e5d5407f359cbee91d9d1a2dae1b61858d8d3850d537cf06cd2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/bundle.json","state_url":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T04:19:18Z","links":{"resolver":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN","bundle":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/bundle.json","state":"https://pith.science/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PQTZUYCLAJSIWXDLNEERXUSCN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:5PQTZUYCLAJSIWXDLNEERXUSCN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bc87709868f7f5c43ed8dfc04d72d05514d8f6f920010ca434c7475266fc51df","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-06-05T19:13:51Z","title_canon_sha256":"9be11fb896fa32ab6cd823139a65723241cc74d0bd2811e6de96e2aebe332694"},"schema_version":"1.0","source":{"id":"1406.1485","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1406.1485","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"arxiv_version","alias_value":"1406.1485v3","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.1485","created_at":"2026-05-18T02:31:59Z"},{"alias_kind":"pith_short_12","alias_value":"5PQTZUYCLAJS","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_16","alias_value":"5PQTZUYCLAJSIWXD","created_at":"2026-05-18T12:28:14Z"},{"alias_kind":"pith_short_8","alias_value":"5PQTZUYC","created_at":"2026-05-18T12:28:14Z"}],"graph_snapshots":[{"event_id":"sha256:3be74741cc54e5d5407f359cbee91d9d1a2dae1b61858d8d3850d537cf06cd2a","target":"graph","created_at":"2026-05-18T02:31:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Kyunghyun Cho, Li Yao, Tapani Raiko, Yoshua Bengio","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-06-05T19:13:51Z","title":"Iterative Neural Autoregressive Distribution Estimator (NADE-k)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.1485","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b0161c64550a982e603989cd28cf1525889d2e770f231548d93292b34b000568","target":"record","created_at":"2026-05-18T02:31:59Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bc87709868f7f5c43ed8dfc04d72d05514d8f6f920010ca434c7475266fc51df","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-06-05T19:13:51Z","title_canon_sha256":"9be11fb896fa32ab6cd823139a65723241cc74d0bd2811e6de96e2aebe332694"},"schema_version":"1.0","source":{"id":"1406.1485","kind":"arxiv","version":3}},"canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebe13cd3025813245ae35b4848de92134e34acb035ff91cc4c0e3627ff1006a5","first_computed_at":"2026-05-18T02:31:59.949260Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:31:59.949260Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KtA22vAtw8Bh3QDtmb4Cx8lV1V03zhckb8v3Q8Ic2Rd1TYPQSSsx3Jh4BIxJS1tlH022Vwrga+kV5t6dho9HCA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:31:59.949792Z","signed_message":"canonical_sha256_bytes"},"source_id":"1406.1485","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0161c64550a982e603989cd28cf1525889d2e770f231548d93292b34b000568","sha256:3be74741cc54e5d5407f359cbee91d9d1a2dae1b61858d8d3850d537cf06cd2a"],"state_sha256":"386c609e503faa564b9e2e0e6fc8f4de8ac73e3ce87f594e7cfa86a8c7f33786"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cDQrugtAQuPocu6xFI/TI9wD8ENi2jR2MtQRWidBXpEJRpVyw2o6tAs7SfSo8zO7Zbxl5W31vMBPgvRdIgH2CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T04:19:18.408081Z","bundle_sha256":"5470e5d6a9c1b2044f463c1e92c7ddd097cd437ce0966cfa9e32f36a67e180b9"}}