{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CDHH7FR7ZL54FGV3IQWEILITEU","short_pith_number":"pith:CDHH7FR7","schema_version":"1.0","canonical_sha256":"10ce7f963fcafbc29abb442c442d13252b1659037a79320a68e869d0ffe476f2","source":{"kind":"arxiv","id":"1911.06443","version":1},"attestation_state":"computed","paper":{"title":"Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden","submitted_at":"2019-11-15T01:46:16Z","abstract_excerpt":"Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However, there is some debate about how to encourage disentanglement with VAEs and evidence indicates that existing implementations of VAEs do not achieve disentanglement consistently. The evaluation of how well a VAE's latent space has been disentangled is often evaluated against our subjective expectations of which attributes should be disentangled for a given probl"},"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":"1911.06443","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-11-15T01:46:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"29c8961b45298ded925bb2cb677a743e8995e6ed5efab782bebec8e1695cddcd","abstract_canon_sha256":"f39faaeceb40281ea9e5afe3b8dc4e46e0b5d8737bdfe8125e61c26eae6046f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:19:23.541335Z","signature_b64":"XG8CO9sd83Sq1QNrUC1YzXbsw7myr4UOyJGLUcPqmkqaax9Lh1jfQm9zr2HWTpfXA1xPIO/OcMNTEpXUTdJLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10ce7f963fcafbc29abb442c442d13252b1659037a79320a68e869d0ffe476f2","last_reissued_at":"2026-07-05T00:19:23.540895Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:19:23.540895Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gated Variational AutoEncoders: Incorporating Weak Supervision to Encourage Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Matthew J. Vowels, Necati Cihan Camgoz, Richard Bowden","submitted_at":"2019-11-15T01:46:16Z","abstract_excerpt":"Variational AutoEncoders (VAEs) provide a means to generate representational latent embeddings. Previous research has highlighted the benefits of achieving representations that are disentangled, particularly for downstream tasks. However, there is some debate about how to encourage disentanglement with VAEs and evidence indicates that existing implementations of VAEs do not achieve disentanglement consistently. The evaluation of how well a VAE's latent space has been disentangled is often evaluated against our subjective expectations of which attributes should be disentangled for a given probl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06443","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.06443/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":"1911.06443","created_at":"2026-07-05T00:19:23.540971+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06443v1","created_at":"2026-07-05T00:19:23.540971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06443","created_at":"2026-07-05T00:19:23.540971+00:00"},{"alias_kind":"pith_short_12","alias_value":"CDHH7FR7ZL54","created_at":"2026-07-05T00:19:23.540971+00:00"},{"alias_kind":"pith_short_16","alias_value":"CDHH7FR7ZL54FGV3","created_at":"2026-07-05T00:19:23.540971+00:00"},{"alias_kind":"pith_short_8","alias_value":"CDHH7FR7","created_at":"2026-07-05T00:19:23.540971+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.04737","citing_title":"Imitation Learning Based on Disentangled Representation Learning of Behavioral Characteristics","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU","json":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU.json","graph_json":"https://pith.science/api/pith-number/CDHH7FR7ZL54FGV3IQWEILITEU/graph.json","events_json":"https://pith.science/api/pith-number/CDHH7FR7ZL54FGV3IQWEILITEU/events.json","paper":"https://pith.science/paper/CDHH7FR7"},"agent_actions":{"view_html":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU","download_json":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU.json","view_paper":"https://pith.science/paper/CDHH7FR7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06443&json=true","fetch_graph":"https://pith.science/api/pith-number/CDHH7FR7ZL54FGV3IQWEILITEU/graph.json","fetch_events":"https://pith.science/api/pith-number/CDHH7FR7ZL54FGV3IQWEILITEU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU/action/storage_attestation","attest_author":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU/action/author_attestation","sign_citation":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU/action/citation_signature","submit_replication":"https://pith.science/pith/CDHH7FR7ZL54FGV3IQWEILITEU/action/replication_record"}},"created_at":"2026-07-05T00:19:23.540971+00:00","updated_at":"2026-07-05T00:19:23.540971+00:00"}