{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2WXNOWLTVNIYG7RWUSOOSDDGFC","short_pith_number":"pith:2WXNOWLT","schema_version":"1.0","canonical_sha256":"d5aed75973ab51837e36a49ce90c6628a080383af02415b26a18707c5c6889a2","source":{"kind":"arxiv","id":"1903.01608","version":2},"attestation_state":"computed","paper":{"title":"Theoretical guarantees for sampling and inference in generative models with latent diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"math.PR","authors_text":"Belinda Tzen, Maxim Raginsky","submitted_at":"2019-03-05T00:38:49Z","abstract_excerpt":"We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed variable is drawn conditionally on the terminal point of the diffusion. We make the following contributions:\n  We provide a unified viewpoint on both sampling and variational inference in such generative models through the lens of stochastic control.\n  We quantify the expressiveness of diffusion-based generative models. Specifically, we show that one can efficiently sample from a wide class of terminal target distributio"},"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":"1903.01608","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.PR","submitted_at":"2019-03-05T00:38:49Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"6002084e4d7e3342dc1998e748fccc0a94316beb79b2d4393f9443e82bfa71d7","abstract_canon_sha256":"801c66d8b26a03294a3e300c03cc816f4ec6e7cd064919513af6dfbfcb1804f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.685244Z","signature_b64":"Jjx7FZzMVK3LqT1VLm2SV9GMyB7RSTauuQU9h1JObN2RnpDm+qrL+cT8PD05ka3V55nXe53raV79LZgATe7SBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5aed75973ab51837e36a49ce90c6628a080383af02415b26a18707c5c6889a2","last_reissued_at":"2026-05-17T23:44:37.684624Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.684624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical guarantees for sampling and inference in generative models with latent diffusions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"math.PR","authors_text":"Belinda Tzen, Maxim Raginsky","submitted_at":"2019-03-05T00:38:49Z","abstract_excerpt":"We introduce and study a class of probabilistic generative models, where the latent object is a finite-dimensional diffusion process on a finite time interval and the observed variable is drawn conditionally on the terminal point of the diffusion. We make the following contributions:\n  We provide a unified viewpoint on both sampling and variational inference in such generative models through the lens of stochastic control.\n  We quantify the expressiveness of diffusion-based generative models. Specifically, we show that one can efficiently sample from a wide class of terminal target distributio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.01608","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":"1903.01608","created_at":"2026-05-17T23:44:37.684725+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.01608v2","created_at":"2026-05-17T23:44:37.684725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.01608","created_at":"2026-05-17T23:44:37.684725+00:00"},{"alias_kind":"pith_short_12","alias_value":"2WXNOWLTVNIY","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2WXNOWLTVNIYG7RW","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2WXNOWLT","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.00007","citing_title":"Mean-Field Path-Integral Diffusion: From Samples to Interacting Agents","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2603.22564","citing_title":"MIOFlow 2.0: A unified framework for inferring cellular stochastic dynamics from single cell and spatial transcriptomics data","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08580","citing_title":"Adjoint Matching through the Lens of the Stochastic Maximum Principle in Optimal Control","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC","json":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC.json","graph_json":"https://pith.science/api/pith-number/2WXNOWLTVNIYG7RWUSOOSDDGFC/graph.json","events_json":"https://pith.science/api/pith-number/2WXNOWLTVNIYG7RWUSOOSDDGFC/events.json","paper":"https://pith.science/paper/2WXNOWLT"},"agent_actions":{"view_html":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC","download_json":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC.json","view_paper":"https://pith.science/paper/2WXNOWLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.01608&json=true","fetch_graph":"https://pith.science/api/pith-number/2WXNOWLTVNIYG7RWUSOOSDDGFC/graph.json","fetch_events":"https://pith.science/api/pith-number/2WXNOWLTVNIYG7RWUSOOSDDGFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC/action/storage_attestation","attest_author":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC/action/author_attestation","sign_citation":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC/action/citation_signature","submit_replication":"https://pith.science/pith/2WXNOWLTVNIYG7RWUSOOSDDGFC/action/replication_record"}},"created_at":"2026-05-17T23:44:37.684725+00:00","updated_at":"2026-05-17T23:44:37.684725+00:00"}