{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ODFUJIFPOQKPHL54LIPC55YGJN","short_pith_number":"pith:ODFUJIFP","schema_version":"1.0","canonical_sha256":"70cb44a0af7414f3afbc5a1e2ef7064b44bc19e41b7008a7064be18389ffe19a","source":{"kind":"arxiv","id":"1509.00519","version":4},"attestation_state":"computed","paper":{"title":"Importance Weighted Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Roger Grosse, Ruslan Salakhutdinov, Yuri Burda","submitted_at":"2015-09-01T22:33:13Z","abstract_excerpt":"The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present"},"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":"1509.00519","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-09-01T22:33:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2879edc872de08f095b61e5799f6eab244ef9f453e5ca959357139b604db7602","abstract_canon_sha256":"2646e3a022c962fff640d15ac0c5b2051e073ba2eff4de2c5f3933fd90475071"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:03.273103Z","signature_b64":"+SDCB08LRjUrRnTMz02WuFbffSWwBkSyhNPHaOdSYvnbVBxaEfthio5UBKvlSjMUyGFH5vOpo4kOWzhtS0YlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70cb44a0af7414f3afbc5a1e2ef7064b44bc19e41b7008a7064be18389ffe19a","last_reissued_at":"2026-05-18T01:00:03.272381Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:03.272381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Importance Weighted Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Roger Grosse, Ruslan Salakhutdinov, Yuri Burda","submitted_at":"2015-09-01T22:33:13Z","abstract_excerpt":"The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference. It typically makes strong assumptions about posterior inference, for instance that the posterior distribution is approximately factorial, and that its parameters can be approximated with nonlinear regression from the observations. As we show empirically, the VAE objective can lead to overly simplified representations which fail to use the network's entire modeling capacity. We present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1509.00519","kind":"arxiv","version":4},"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":"1509.00519","created_at":"2026-05-18T01:00:03.272498+00:00"},{"alias_kind":"arxiv_version","alias_value":"1509.00519v4","created_at":"2026-05-18T01:00:03.272498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1509.00519","created_at":"2026-05-18T01:00:03.272498+00:00"},{"alias_kind":"pith_short_12","alias_value":"ODFUJIFPOQKP","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_16","alias_value":"ODFUJIFPOQKPHL54","created_at":"2026-05-18T12:29:34.919912+00:00"},{"alias_kind":"pith_short_8","alias_value":"ODFUJIFP","created_at":"2026-05-18T12:29:34.919912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2406.09250","citing_title":"MirrorCheck: Efficient Adversarial Defense for Vision-Language Models","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08167","citing_title":"Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21108","citing_title":"Efficient Learning of Deep State Space Models via Importance Smoothing","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18530","citing_title":"Continuous Diffusion Scales Competitively with Discrete Diffusion for Language","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06695","citing_title":"Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"1605.08803","citing_title":"Density estimation using Real NVP","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03413","citing_title":"Learning to Theorize the World from Observation","ref_index":205,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06315","citing_title":"End-to-End Identifiable and Consistent Recurrent Switching Dynamical Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01862","citing_title":"QHyer: Q-conditioned Hybrid Attention-mamba Transformer for Offline Goal-conditioned RL","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN","json":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN.json","graph_json":"https://pith.science/api/pith-number/ODFUJIFPOQKPHL54LIPC55YGJN/graph.json","events_json":"https://pith.science/api/pith-number/ODFUJIFPOQKPHL54LIPC55YGJN/events.json","paper":"https://pith.science/paper/ODFUJIFP"},"agent_actions":{"view_html":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN","download_json":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN.json","view_paper":"https://pith.science/paper/ODFUJIFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1509.00519&json=true","fetch_graph":"https://pith.science/api/pith-number/ODFUJIFPOQKPHL54LIPC55YGJN/graph.json","fetch_events":"https://pith.science/api/pith-number/ODFUJIFPOQKPHL54LIPC55YGJN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN/action/storage_attestation","attest_author":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN/action/author_attestation","sign_citation":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN/action/citation_signature","submit_replication":"https://pith.science/pith/ODFUJIFPOQKPHL54LIPC55YGJN/action/replication_record"}},"created_at":"2026-05-18T01:00:03.272498+00:00","updated_at":"2026-05-18T01:00:03.272498+00:00"}