{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:BK5Q2CUZNWG3H4KYOFTAQHTRPP","short_pith_number":"pith:BK5Q2CUZ","schema_version":"1.0","canonical_sha256":"0abb0d0a996d8db3f1587166081e717bcc4dcb2ec90b15a7634c438708399b10","source":{"kind":"arxiv","id":"1606.04934","version":2},"attestation_state":"computed","paper":{"title":"Improving Variational Inference with Inverse Autoregressive Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Diederik P. Kingma, Ilya Sutskever, Max Welling, Rafal Jozefowicz, Tim Salimans, Xi Chen","submitted_at":"2016-06-15T19:46:36Z","abstract_excerpt":"The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of v"},"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":"1606.04934","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-06-15T19:46:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"eede44712849d3a955da8a46730a5a0f6da5acfabb0041721ab4d914a0c5779d","abstract_canon_sha256":"70e204443407deb4c61eb4beef7dc0f071d73e32c32faf78e8fe717675cf1f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:48.625295Z","signature_b64":"EIvBYKzsyWYfDvF6NDUPMcXNrO6dczw5w1vJD+Ctg+LtsFPViGNqpZ3s1nzp4WofHJCXJH/oEdJrOnBEAHK8Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0abb0d0a996d8db3f1587166081e717bcc4dcb2ec90b15a7634c438708399b10","last_reissued_at":"2026-05-18T00:51:48.624622Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:48.624622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Variational Inference with Inverse Autoregressive Flow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Diederik P. Kingma, Ilya Sutskever, Max Welling, Rafal Jozefowicz, Tim Salimans, Xi Chen","submitted_at":"2016-06-15T19:46:36Z","abstract_excerpt":"The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.04934","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":"1606.04934","created_at":"2026-05-18T00:51:48.624742+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.04934v2","created_at":"2026-05-18T00:51:48.624742+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.04934","created_at":"2026-05-18T00:51:48.624742+00:00"},{"alias_kind":"pith_short_12","alias_value":"BK5Q2CUZNWG3","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"BK5Q2CUZNWG3H4KY","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"BK5Q2CUZ","created_at":"2026-05-18T12:30:07.202191+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07769","citing_title":"Hierarchical Sequence to Sequence Voice Conversion with Limited Data","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12165","citing_title":"Machine Learning for neutron source distributions","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06348","citing_title":"Dartmouth Stellar Evolution Emulator (DSEE) 1: Generative Stellar Evolution Model Database","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP","json":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP.json","graph_json":"https://pith.science/api/pith-number/BK5Q2CUZNWG3H4KYOFTAQHTRPP/graph.json","events_json":"https://pith.science/api/pith-number/BK5Q2CUZNWG3H4KYOFTAQHTRPP/events.json","paper":"https://pith.science/paper/BK5Q2CUZ"},"agent_actions":{"view_html":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP","download_json":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP.json","view_paper":"https://pith.science/paper/BK5Q2CUZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.04934&json=true","fetch_graph":"https://pith.science/api/pith-number/BK5Q2CUZNWG3H4KYOFTAQHTRPP/graph.json","fetch_events":"https://pith.science/api/pith-number/BK5Q2CUZNWG3H4KYOFTAQHTRPP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP/action/storage_attestation","attest_author":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP/action/author_attestation","sign_citation":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP/action/citation_signature","submit_replication":"https://pith.science/pith/BK5Q2CUZNWG3H4KYOFTAQHTRPP/action/replication_record"}},"created_at":"2026-05-18T00:51:48.624742+00:00","updated_at":"2026-05-18T00:51:48.624742+00:00"}