{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BNTH6YSVCLVPTSVTQPM77K6WII","short_pith_number":"pith:BNTH6YSV","schema_version":"1.0","canonical_sha256":"0b667f625512eaf9cab383d9ffabd6421ded69ba99766e67293a26645636bb05","source":{"kind":"arxiv","id":"1706.00550","version":5},"attestation_state":"computed","paper":{"title":"On Unifying Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Ruslan Salakhutdinov, Zhiting Hu, Zichao Yang","submitted_at":"2017-06-02T04:15:44Z","abstract_excerpt":"Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two distinct paradigms and received extensive independent studies respectively. This paper aims to establish formal connections between GANs and VAEs through a new formulation of them. We interpret sample generation in GANs as performing posterior inference, and show that GANs and VAEs involve minimizing KL divergences of respective posterior and inference distribu"},"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":"1706.00550","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-02T04:15:44Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"24fb07786ee28a2f6ee06619275807288be6a2f846652970564613bd804010b3","abstract_canon_sha256":"c7f0dc0ddb29b07917b27a9ce9f76f9969552c4bc417f81f03ad6925cf831569"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:00.546022Z","signature_b64":"a42jo+xWQxwTtpowE81U8tfRKXdWIaZ5dBwdn4OzNLl18Agi2KmuwKxJMHtHUEGIUeQkObOT2B4zp0yYblkaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b667f625512eaf9cab383d9ffabd6421ded69ba99766e67293a26645636bb05","last_reissued_at":"2026-05-18T00:11:00.545257Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:00.545257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Unifying Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Ruslan Salakhutdinov, Zhiting Hu, Zichao Yang","submitted_at":"2017-06-02T04:15:44Z","abstract_excerpt":"Deep generative models have achieved impressive success in recent years. Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families for generative model learning, have largely been considered as two distinct paradigms and received extensive independent studies respectively. This paper aims to establish formal connections between GANs and VAEs through a new formulation of them. We interpret sample generation in GANs as performing posterior inference, and show that GANs and VAEs involve minimizing KL divergences of respective posterior and inference distribu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.00550","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":"1706.00550","created_at":"2026-05-18T00:11:00.545395+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.00550v5","created_at":"2026-05-18T00:11:00.545395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.00550","created_at":"2026-05-18T00:11:00.545395+00:00"},{"alias_kind":"pith_short_12","alias_value":"BNTH6YSVCLVP","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BNTH6YSVCLVPTSVT","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BNTH6YSV","created_at":"2026-05-18T12:31:08.081275+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":266,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII","json":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII.json","graph_json":"https://pith.science/api/pith-number/BNTH6YSVCLVPTSVTQPM77K6WII/graph.json","events_json":"https://pith.science/api/pith-number/BNTH6YSVCLVPTSVTQPM77K6WII/events.json","paper":"https://pith.science/paper/BNTH6YSV"},"agent_actions":{"view_html":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII","download_json":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII.json","view_paper":"https://pith.science/paper/BNTH6YSV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.00550&json=true","fetch_graph":"https://pith.science/api/pith-number/BNTH6YSVCLVPTSVTQPM77K6WII/graph.json","fetch_events":"https://pith.science/api/pith-number/BNTH6YSVCLVPTSVTQPM77K6WII/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII/action/storage_attestation","attest_author":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII/action/author_attestation","sign_citation":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII/action/citation_signature","submit_replication":"https://pith.science/pith/BNTH6YSVCLVPTSVTQPM77K6WII/action/replication_record"}},"created_at":"2026-05-18T00:11:00.545395+00:00","updated_at":"2026-05-18T00:11:00.545395+00:00"}