{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2X2J5YXFLQMOB67SQN4NFEA4N3","short_pith_number":"pith:2X2J5YXF","schema_version":"1.0","canonical_sha256":"d5f49ee2e55c18e0fbf28378d2901c6ec2bff805fb62b4c3e3234e8cf67be825","source":{"kind":"arxiv","id":"1810.02789","version":2},"attestation_state":"computed","paper":{"title":"Doubly Semi-Implicit Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artem Sobolev, Dmitry Molchanov, Dmitry Vetrov, Valery Kharitonov","submitted_at":"2018-10-05T16:54:18Z","abstract_excerpt":"We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approximate posterior and the prior distribution are semi-implicit. In other words, DSIVI performs inference in models where the prior and the posterior can be expressed as an intractable infinite mixture of some analytic density with a highly flexible implicit mixing distribution. We provide a sandwich bound on the evidence lower bound (ELBO) objective that can be made arbitrarily tigh"},"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":"1810.02789","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-10-05T16:54:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16f7483f620ac65dab9a2cd062f33dccbd09da930f31fc6b860a69eb89ca1746","abstract_canon_sha256":"2d2a0f2f7bb0e193c7c70ec8d7f172d021194b792b3226c96bb4b72609e5257d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:09.577088Z","signature_b64":"mwnob+mtw3CGc5VLQq2tGHvxI2qHG5hOcqnoPTYXtnS0uO/U6k0/+VZhfRfLY2IJ9ZpIOd3XrrPr9ZUdaCDxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5f49ee2e55c18e0fbf28378d2901c6ec2bff805fb62b4c3e3234e8cf67be825","last_reissued_at":"2026-05-17T23:51:09.576427Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:09.576427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Doubly Semi-Implicit Variational Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Artem Sobolev, Dmitry Molchanov, Dmitry Vetrov, Valery Kharitonov","submitted_at":"2018-10-05T16:54:18Z","abstract_excerpt":"We extend the existing framework of semi-implicit variational inference (SIVI) and introduce doubly semi-implicit variational inference (DSIVI), a way to perform variational inference and learning when both the approximate posterior and the prior distribution are semi-implicit. In other words, DSIVI performs inference in models where the prior and the posterior can be expressed as an intractable infinite mixture of some analytic density with a highly flexible implicit mixing distribution. We provide a sandwich bound on the evidence lower bound (ELBO) objective that can be made arbitrarily tigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02789","kind":"arxiv","version":2},"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":"1810.02789","created_at":"2026-05-17T23:51:09.576536+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02789v2","created_at":"2026-05-17T23:51:09.576536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02789","created_at":"2026-05-17T23:51:09.576536+00:00"},{"alias_kind":"pith_short_12","alias_value":"2X2J5YXFLQMO","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2X2J5YXFLQMOB67S","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2X2J5YXF","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.09710","citing_title":"Variational Graph Recurrent Neural Networks","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3","json":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3.json","graph_json":"https://pith.science/api/pith-number/2X2J5YXFLQMOB67SQN4NFEA4N3/graph.json","events_json":"https://pith.science/api/pith-number/2X2J5YXFLQMOB67SQN4NFEA4N3/events.json","paper":"https://pith.science/paper/2X2J5YXF"},"agent_actions":{"view_html":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3","download_json":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3.json","view_paper":"https://pith.science/paper/2X2J5YXF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02789&json=true","fetch_graph":"https://pith.science/api/pith-number/2X2J5YXFLQMOB67SQN4NFEA4N3/graph.json","fetch_events":"https://pith.science/api/pith-number/2X2J5YXFLQMOB67SQN4NFEA4N3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3/action/storage_attestation","attest_author":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3/action/author_attestation","sign_citation":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3/action/citation_signature","submit_replication":"https://pith.science/pith/2X2J5YXFLQMOB67SQN4NFEA4N3/action/replication_record"}},"created_at":"2026-05-17T23:51:09.576536+00:00","updated_at":"2026-05-17T23:51:09.576536+00:00"}