{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:YHFOILJWEVFGHKVJYKCXXSKFP6","short_pith_number":"pith:YHFOILJW","schema_version":"1.0","canonical_sha256":"c1cae42d36254a63aaa9c2857bc9457fb61bf80b5c4bf3a7d18e63386470f955","source":{"kind":"arxiv","id":"1406.2751","version":4},"attestation_state":"computed","paper":{"title":"Reweighted Wake-Sleep","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"J\\\"org Bornschein, Yoshua Bengio","submitted_at":"2014-06-11T00:44:31Z","abstract_excerpt":"Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been proposed to train them. The wake-sleep algorithm relies on training not just the directed generative model but also a conditional generative model (the inference network) that runs backward from visible to latent, estimating the posterior distribution of latent given visible. We propose a novel interpretation of the wake-sleep algorithm which suggests that better estimators of th"},"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":"1406.2751","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-06-11T00:44:31Z","cross_cats_sorted":[],"title_canon_sha256":"4ad89f791ae384144bb7f84e9d06d86ea0c3c6d1a4bffcc9f4e31d62ac565856","abstract_canon_sha256":"c63d0d5e1ed8b2ef1665b438864cb24b771a7e3ba8df30a98211d62e715d0542"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:21.261963Z","signature_b64":"zn0XNeofw+M6+xnBJfAufHYP6sXu64OPRX9qIJ91GOJwHmgd/GAtbUjOAqUHdFUjJQc2ogHn7NsWk9PClo6JDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1cae42d36254a63aaa9c2857bc9457fb61bf80b5c4bf3a7d18e63386470f955","last_reissued_at":"2026-05-18T01:20:21.261531Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:21.261531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reweighted Wake-Sleep","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"J\\\"org Bornschein, Yoshua Bengio","submitted_at":"2014-06-11T00:44:31Z","abstract_excerpt":"Training deep directed graphical models with many hidden variables and performing inference remains a major challenge. Helmholtz machines and deep belief networks are such models, and the wake-sleep algorithm has been proposed to train them. The wake-sleep algorithm relies on training not just the directed generative model but also a conditional generative model (the inference network) that runs backward from visible to latent, estimating the posterior distribution of latent given visible. We propose a novel interpretation of the wake-sleep algorithm which suggests that better estimators of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1406.2751","kind":"arxiv","version":4},"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":"1406.2751","created_at":"2026-05-18T01:20:21.261597+00:00"},{"alias_kind":"arxiv_version","alias_value":"1406.2751v4","created_at":"2026-05-18T01:20:21.261597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1406.2751","created_at":"2026-05-18T01:20:21.261597+00:00"},{"alias_kind":"pith_short_12","alias_value":"YHFOILJWEVFG","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_16","alias_value":"YHFOILJWEVFGHKVJ","created_at":"2026-05-18T12:28:57.508820+00:00"},{"alias_kind":"pith_short_8","alias_value":"YHFOILJW","created_at":"2026-05-18T12:28:57.508820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2601.22367","citing_title":"Amortized Simulation-Based Inference in Generalized Bayes via Neural Posterior Estimation","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2510.12916","citing_title":"Efficient Inference for Coupled Hidden Markov Models in Continuous Time and Discrete Space","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2512.11415","citing_title":"Emergence of Nonequilibrium Latent Cycles in Unsupervised Generative Modeling","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6","json":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6.json","graph_json":"https://pith.science/api/pith-number/YHFOILJWEVFGHKVJYKCXXSKFP6/graph.json","events_json":"https://pith.science/api/pith-number/YHFOILJWEVFGHKVJYKCXXSKFP6/events.json","paper":"https://pith.science/paper/YHFOILJW"},"agent_actions":{"view_html":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6","download_json":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6.json","view_paper":"https://pith.science/paper/YHFOILJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1406.2751&json=true","fetch_graph":"https://pith.science/api/pith-number/YHFOILJWEVFGHKVJYKCXXSKFP6/graph.json","fetch_events":"https://pith.science/api/pith-number/YHFOILJWEVFGHKVJYKCXXSKFP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6/action/storage_attestation","attest_author":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6/action/author_attestation","sign_citation":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6/action/citation_signature","submit_replication":"https://pith.science/pith/YHFOILJWEVFGHKVJYKCXXSKFP6/action/replication_record"}},"created_at":"2026-05-18T01:20:21.261597+00:00","updated_at":"2026-05-18T01:20:21.261597+00:00"}