{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VCCAPHL24PWR356EGHNB6HOBHX","short_pith_number":"pith:VCCAPHL2","schema_version":"1.0","canonical_sha256":"a884079d7ae3ed1df7c431da1f1dc13def4d7c1d83ce411faa4d30e761b5f413","source":{"kind":"arxiv","id":"1903.12436","version":4},"attestation_state":"computed","paper":{"title":"From Variational to Deterministic Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Bernhard Sch\\\"olkopf, Mehdi S. M. Sajjadi, Michael Black, Partha Ghosh","submitted_at":"2019-03-29T10:31:55Z","abstract_excerpt":"Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this work, we propose an alternative framework for generative modeling that is simpler, easier to train, and deterministic, yet has many of the advantages of VAEs. We observe that sampling a stochastic encoder in a Gaussian VAE can be interpreted as simply injecting noise into the input of a deterministic decoder. We investigate how substituting this kind of stoch"},"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":"1903.12436","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-29T10:31:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a056545842718a397f9f651e10190e8a1d9791125e30d7d463fad3668f0b577","abstract_canon_sha256":"a78c983cf95ccec85194eca4b21405119b132e4b5aa5a892f907b16cd24c2d7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:06:30.324392Z","signature_b64":"DSRX87iJGZSOJTSKyrGNyhzv6MLaxHuoGueQleVEZMOgLxhtmj3qpVjsoZI/4ZwTESK/u6US78Sz0VNT5Ap2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a884079d7ae3ed1df7c431da1f1dc13def4d7c1d83ce411faa4d30e761b5f413","last_reissued_at":"2026-07-05T01:06:30.323825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:06:30.323825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Variational to Deterministic Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Antonio Vergari, Bernhard Sch\\\"olkopf, Mehdi S. M. Sajjadi, Michael Black, Partha Ghosh","submitted_at":"2019-03-29T10:31:55Z","abstract_excerpt":"Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this work, we propose an alternative framework for generative modeling that is simpler, easier to train, and deterministic, yet has many of the advantages of VAEs. We observe that sampling a stochastic encoder in a Gaussian VAE can be interpreted as simply injecting noise into the input of a deterministic decoder. We investigate how substituting this kind of stoch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.12436","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1903.12436/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1903.12436","created_at":"2026-07-05T01:06:30.323891+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.12436v4","created_at":"2026-07-05T01:06:30.323891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.12436","created_at":"2026-07-05T01:06:30.323891+00:00"},{"alias_kind":"pith_short_12","alias_value":"VCCAPHL24PWR","created_at":"2026-07-05T01:06:30.323891+00:00"},{"alias_kind":"pith_short_16","alias_value":"VCCAPHL24PWR356E","created_at":"2026-07-05T01:06:30.323891+00:00"},{"alias_kind":"pith_short_8","alias_value":"VCCAPHL2","created_at":"2026-07-05T01:06:30.323891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02385","citing_title":"How Optimality Structures Sparse Dictionaries: A Theory for Understanding SAE Representations","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11575","citing_title":"MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX","json":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX.json","graph_json":"https://pith.science/api/pith-number/VCCAPHL24PWR356EGHNB6HOBHX/graph.json","events_json":"https://pith.science/api/pith-number/VCCAPHL24PWR356EGHNB6HOBHX/events.json","paper":"https://pith.science/paper/VCCAPHL2"},"agent_actions":{"view_html":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX","download_json":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX.json","view_paper":"https://pith.science/paper/VCCAPHL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.12436&json=true","fetch_graph":"https://pith.science/api/pith-number/VCCAPHL24PWR356EGHNB6HOBHX/graph.json","fetch_events":"https://pith.science/api/pith-number/VCCAPHL24PWR356EGHNB6HOBHX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX/action/storage_attestation","attest_author":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX/action/author_attestation","sign_citation":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX/action/citation_signature","submit_replication":"https://pith.science/pith/VCCAPHL24PWR356EGHNB6HOBHX/action/replication_record"}},"created_at":"2026-07-05T01:06:30.323891+00:00","updated_at":"2026-07-05T01:06:30.323891+00:00"}