{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:RLDMPK6IJOENNFSONSJCDXLXMM","short_pith_number":"pith:RLDMPK6I","schema_version":"1.0","canonical_sha256":"8ac6c7abc84b88d6964e6c9221dd7763192c52cd2bfddc21061f5f1f828d7d12","source":{"kind":"arxiv","id":"1611.02731","version":2},"attestation_state":"computed","paper":{"title":"Variational Lossy Autoencoder","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, John Schulman, Pieter Abbeel, Prafulla Dhariwal, Tim Salimans, Xi Chen, Yan Duan","submitted_at":"2016-11-08T21:43:34Z","abstract_excerpt":"Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper, we present a simple but principled method to learn such global representations by combining Variational Autoencoder (VAE) with neural autoregressive models such as RNN, MADE and PixelRNN/CNN. Our proposed VAE model allows us to have control over what the global latent code can "},"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":"1611.02731","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-11-08T21:43:34Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"626ed26729e478bc4fe4b0fa23daa6abc0783fbe1aec7ddf707ba3fabf2988fe","abstract_canon_sha256":"fdc43924cb2bbdfbaafdf739e5b9f5778c3312434602661ad3140ac1f512e458"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:31.804938Z","signature_b64":"CCtbQwGZh3A0CbVcR7TY8iyZqnubL4TDKhgoPciHFfSd4jvFd/wAzVJhbMt+ZxiA17e3iA418BeGUxeHC2fBAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ac6c7abc84b88d6964e6c9221dd7763192c52cd2bfddc21061f5f1f828d7d12","last_reissued_at":"2026-05-18T00:49:31.804232Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:31.804232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Lossy Autoencoder","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, John Schulman, Pieter Abbeel, Prafulla Dhariwal, Tim Salimans, Xi Chen, Yan Duan","submitted_at":"2016-11-08T21:43:34Z","abstract_excerpt":"Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper, we present a simple but principled method to learn such global representations by combining Variational Autoencoder (VAE) with neural autoregressive models such as RNN, MADE and PixelRNN/CNN. Our proposed VAE model allows us to have control over what the global latent code can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02731","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":"1611.02731","created_at":"2026-05-18T00:49:31.804339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02731v2","created_at":"2026-05-18T00:49:31.804339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02731","created_at":"2026-05-18T00:49:31.804339+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLDMPK6IJOEN","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLDMPK6IJOENNFSO","created_at":"2026-05-18T12:30:41.710351+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLDMPK6I","created_at":"2026-05-18T12:30:41.710351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.22493","citing_title":"Understanding Multimodal Failure in Action-Chunking Behavioral Cloning","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20534","citing_title":"Axiomatizing Neural Networks via Pursuit of Subspaces","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07513","citing_title":"Tessellations of Semi-Discrete Flow Matching","ref_index":140,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM","json":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM.json","graph_json":"https://pith.science/api/pith-number/RLDMPK6IJOENNFSONSJCDXLXMM/graph.json","events_json":"https://pith.science/api/pith-number/RLDMPK6IJOENNFSONSJCDXLXMM/events.json","paper":"https://pith.science/paper/RLDMPK6I"},"agent_actions":{"view_html":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM","download_json":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM.json","view_paper":"https://pith.science/paper/RLDMPK6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02731&json=true","fetch_graph":"https://pith.science/api/pith-number/RLDMPK6IJOENNFSONSJCDXLXMM/graph.json","fetch_events":"https://pith.science/api/pith-number/RLDMPK6IJOENNFSONSJCDXLXMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM/action/storage_attestation","attest_author":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM/action/author_attestation","sign_citation":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM/action/citation_signature","submit_replication":"https://pith.science/pith/RLDMPK6IJOENNFSONSJCDXLXMM/action/replication_record"}},"created_at":"2026-05-18T00:49:31.804339+00:00","updated_at":"2026-05-18T00:49:31.804339+00:00"}