{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MB4KFGWPXY425BT53BDKAL54BR","short_pith_number":"pith:MB4KFGWP","schema_version":"1.0","canonical_sha256":"6078a29acfbe39ae867dd846a02fbc0c67992d1712d0e3df5c1af4a7526aa255","source":{"kind":"arxiv","id":"1807.09356","version":1},"attestation_state":"computed","paper":{"title":"Iterative Amortized Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joseph Marino, Stephan Mandt, Yisong Yue","submitted_at":"2018-07-24T21:07:25Z","abstract_excerpt":"Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computationally efficient. However, standard inference models are restricted to direct mappings from data to approximate posterior estimates. The failure of these models to reach fully optimized approximate posterior estimates results in an amortization gap. We aim toward closing this gap "},"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":"1807.09356","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-24T21:07:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a654df698801570a9a040cb109b698dbbfb325a9c2def1fa89f493a3582b8d6f","abstract_canon_sha256":"50a491d5875bdc47fdaf46232f30dff81978205b0ca7db1688015b158bfc94e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:51.563991Z","signature_b64":"RbYgYYr3iiXq63C6Pw7Iq5W2Vz5eRgi3YundGSuFPUy3sascLHafLttiMApFSuMatwppP9vk2tcukx2U/GfkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6078a29acfbe39ae867dd846a02fbc0c67992d1712d0e3df5c1af4a7526aa255","last_reissued_at":"2026-05-18T00:09:51.563367Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:51.563367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterative Amortized Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Joseph Marino, Stephan Mandt, Yisong Yue","submitted_at":"2018-07-24T21:07:25Z","abstract_excerpt":"Inference models are a key component in scaling variational inference to deep latent variable models, most notably as encoder networks in variational auto-encoders (VAEs). By replacing conventional optimization-based inference with a learned model, inference is amortized over data examples and therefore more computationally efficient. However, standard inference models are restricted to direct mappings from data to approximate posterior estimates. The failure of these models to reach fully optimized approximate posterior estimates results in an amortization gap. We aim toward closing this gap "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09356","kind":"arxiv","version":1},"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":"1807.09356","created_at":"2026-05-18T00:09:51.563475+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.09356v1","created_at":"2026-05-18T00:09:51.563475+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09356","created_at":"2026-05-18T00:09:51.563475+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB4KFGWPXY42","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB4KFGWPXY425BT5","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB4KFGWP","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":208,"is_internal_anchor":false},{"citing_arxiv_id":"2005.01643","citing_title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR","json":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR.json","graph_json":"https://pith.science/api/pith-number/MB4KFGWPXY425BT53BDKAL54BR/graph.json","events_json":"https://pith.science/api/pith-number/MB4KFGWPXY425BT53BDKAL54BR/events.json","paper":"https://pith.science/paper/MB4KFGWP"},"agent_actions":{"view_html":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR","download_json":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR.json","view_paper":"https://pith.science/paper/MB4KFGWP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.09356&json=true","fetch_graph":"https://pith.science/api/pith-number/MB4KFGWPXY425BT53BDKAL54BR/graph.json","fetch_events":"https://pith.science/api/pith-number/MB4KFGWPXY425BT53BDKAL54BR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR/action/storage_attestation","attest_author":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR/action/author_attestation","sign_citation":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR/action/citation_signature","submit_replication":"https://pith.science/pith/MB4KFGWPXY425BT53BDKAL54BR/action/replication_record"}},"created_at":"2026-05-18T00:09:51.563475+00:00","updated_at":"2026-05-18T00:09:51.563475+00:00"}