{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:IDP5UPPKXDZITZNN4UXILHGAWU","short_pith_number":"pith:IDP5UPPK","schema_version":"1.0","canonical_sha256":"40dfda3deab8f289e5ade52e859cc0b51099e6d9345c45e560c24ff0267d70d7","source":{"kind":"arxiv","id":"1506.03877","version":5},"attestation_state":"computed","paper":{"title":"Bidirectional Helmholtz Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Asja Fischer, Jorg Bornschein, Samira Shabanian, Yoshua Bengio","submitted_at":"2015-06-12T00:08:20Z","abstract_excerpt":"Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down directed generative model together with a bottom-up auxiliary model used for approximate inference. Recent results indicate that better generative models can be obtained with better approximate inference procedures. Instead of improving the inference procedure, we here propose a new model which guarantees that the top-down and bottom-up distributions can efficiently invert each other. We achieve this by interpreting bo"},"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":"1506.03877","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-06-12T00:08:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a50e483d60ed5477fb6f81f87b2df68a90e63d1481d07db229820eec7bd15201","abstract_canon_sha256":"59be68a64e05cf7110f9de339193c9206ce87b6f058df75c060626b3d1dc22e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:44.823670Z","signature_b64":"hZM9z0GSnwOCHNRIV14DZBwGz7V5lV4egDYar7lYcvCNM0iBKTG3KfOEn7Vtl25FfcnD1jXMaZ9Spg1lL/W9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40dfda3deab8f289e5ade52e859cc0b51099e6d9345c45e560c24ff0267d70d7","last_reissued_at":"2026-05-18T01:13:44.822970Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:44.822970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional Helmholtz Machines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Asja Fischer, Jorg Bornschein, Samira Shabanian, Yoshua Bengio","submitted_at":"2015-06-12T00:08:20Z","abstract_excerpt":"Efficient unsupervised training and inference in deep generative models remains a challenging problem. One basic approach, called Helmholtz machine, involves training a top-down directed generative model together with a bottom-up auxiliary model used for approximate inference. Recent results indicate that better generative models can be obtained with better approximate inference procedures. Instead of improving the inference procedure, we here propose a new model which guarantees that the top-down and bottom-up distributions can efficiently invert each other. We achieve this by interpreting bo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1506.03877","kind":"arxiv","version":5},"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":"1506.03877","created_at":"2026-05-18T01:13:44.823075+00:00"},{"alias_kind":"arxiv_version","alias_value":"1506.03877v5","created_at":"2026-05-18T01:13:44.823075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1506.03877","created_at":"2026-05-18T01:13:44.823075+00:00"},{"alias_kind":"pith_short_12","alias_value":"IDP5UPPKXDZI","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_16","alias_value":"IDP5UPPKXDZITZNN","created_at":"2026-05-18T12:29:25.134429+00:00"},{"alias_kind":"pith_short_8","alias_value":"IDP5UPPK","created_at":"2026-05-18T12:29:25.134429+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/IDP5UPPKXDZITZNN4UXILHGAWU","json":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU.json","graph_json":"https://pith.science/api/pith-number/IDP5UPPKXDZITZNN4UXILHGAWU/graph.json","events_json":"https://pith.science/api/pith-number/IDP5UPPKXDZITZNN4UXILHGAWU/events.json","paper":"https://pith.science/paper/IDP5UPPK"},"agent_actions":{"view_html":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU","download_json":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU.json","view_paper":"https://pith.science/paper/IDP5UPPK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1506.03877&json=true","fetch_graph":"https://pith.science/api/pith-number/IDP5UPPKXDZITZNN4UXILHGAWU/graph.json","fetch_events":"https://pith.science/api/pith-number/IDP5UPPKXDZITZNN4UXILHGAWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU/action/storage_attestation","attest_author":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU/action/author_attestation","sign_citation":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU/action/citation_signature","submit_replication":"https://pith.science/pith/IDP5UPPKXDZITZNN4UXILHGAWU/action/replication_record"}},"created_at":"2026-05-18T01:13:44.823075+00:00","updated_at":"2026-05-18T01:13:44.823075+00:00"}