{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:7G2ZBMYT3LGLL3NPOOHK74NHOS","short_pith_number":"pith:7G2ZBMYT","schema_version":"1.0","canonical_sha256":"f9b590b313daccb5edaf738eaff1a77491859355233def671b505e3d4e7e30cb","source":{"kind":"arxiv","id":"1603.06277","version":5},"attestation_state":"computed","paper":{"title":"Composing graphical models with neural networks for structured representations and fast inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Alexander B. Wiltschko, David Duvenaud, Matthew J. Johnson, Ryan P. Adams, Sandeep R. Datta","submitted_at":"2016-03-20T22:01:02Z","abstract_excerpt":"We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference, we extend variational autoencoders to use graphical model approximating distributions with recognition networks that output conjugate potentials. All components of these models are learned simultaneously with a single objective, giving a scalable algorithm that leverages stochastic variational inference, natura"},"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":"1603.06277","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-03-20T22:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"e9996634d25fafb3469e3c4122c4077fa534b719d614f2381e95d59e1d94a6d0","abstract_canon_sha256":"0c9950204832136eaa66fe08104f4aef65b3374d4b4203f6f5c293dcb7c1d850"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:46.822526Z","signature_b64":"1nb/8M3G3FldAPRJyHjv9iIiwYvS0aNjk6OHNYMyr0Iob0tenbHgvQdSNEE/brEf7rMVmfCE2XTnT7+cY8d1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9b590b313daccb5edaf738eaff1a77491859355233def671b505e3d4e7e30cb","last_reissued_at":"2026-05-18T00:40:46.821804Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:46.821804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Composing graphical models with neural networks for structured representations and fast inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Alexander B. Wiltschko, David Duvenaud, Matthew J. Johnson, Ryan P. Adams, Sandeep R. Datta","submitted_at":"2016-03-20T22:01:02Z","abstract_excerpt":"We propose a general modeling and inference framework that composes probabilistic graphical models with deep learning methods and combines their respective strengths. Our model family augments graphical structure in latent variables with neural network observation models. For inference, we extend variational autoencoders to use graphical model approximating distributions with recognition networks that output conjugate potentials. All components of these models are learned simultaneously with a single objective, giving a scalable algorithm that leverages stochastic variational inference, natura"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.06277","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":"1603.06277","created_at":"2026-05-18T00:40:46.821917+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.06277v5","created_at":"2026-05-18T00:40:46.821917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.06277","created_at":"2026-05-18T00:40:46.821917+00:00"},{"alias_kind":"pith_short_12","alias_value":"7G2ZBMYT3LGL","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"7G2ZBMYT3LGLL3NP","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"7G2ZBMYT","created_at":"2026-05-18T12:30:04.600751+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/7G2ZBMYT3LGLL3NPOOHK74NHOS","json":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS.json","graph_json":"https://pith.science/api/pith-number/7G2ZBMYT3LGLL3NPOOHK74NHOS/graph.json","events_json":"https://pith.science/api/pith-number/7G2ZBMYT3LGLL3NPOOHK74NHOS/events.json","paper":"https://pith.science/paper/7G2ZBMYT"},"agent_actions":{"view_html":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS","download_json":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS.json","view_paper":"https://pith.science/paper/7G2ZBMYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.06277&json=true","fetch_graph":"https://pith.science/api/pith-number/7G2ZBMYT3LGLL3NPOOHK74NHOS/graph.json","fetch_events":"https://pith.science/api/pith-number/7G2ZBMYT3LGLL3NPOOHK74NHOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS/action/storage_attestation","attest_author":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS/action/author_attestation","sign_citation":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS/action/citation_signature","submit_replication":"https://pith.science/pith/7G2ZBMYT3LGLL3NPOOHK74NHOS/action/replication_record"}},"created_at":"2026-05-18T00:40:46.821917+00:00","updated_at":"2026-05-18T00:40:46.821917+00:00"}