{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZNFW47DOUYXR73H2BGMLERLC4P","short_pith_number":"pith:ZNFW47DO","schema_version":"1.0","canonical_sha256":"cb4b6e7c6ea62f1fecfa0998b24562e3d838903f18546625ceb599ca45812ee6","source":{"kind":"arxiv","id":"1812.02833","version":3},"attestation_state":"computed","paper":{"title":"Disentangling Disentanglement in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emile Mathieu, N. Siddharth, Tom Rainforth, Yee Whye Teh","submitted_at":"2018-12-06T22:16:28Z","abstract_excerpt":"We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of the data conforming to a desired structure, represented through the prior. Decomposition permits disentanglement, i.e. explicit independence between latents, as a special case, but also allows for a much richer class of properties to be imposed on the learnt representation, such as sparsity, clustering, independent subspaces, or even i"},"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":"1812.02833","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-12-06T22:16:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d876630954c5773d4aefa5d4dfcf20c170910342dc6f7a643c94a7503c4a5f97","abstract_canon_sha256":"e51979aecb32fc69528d08fda428fd0c1f1573843e73c25f5f24406d148fb776"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.990466Z","signature_b64":"O+wTMk+MTc1xEnRgmY7gzIyIJXBIoGf7FNDPlAtwVaIs+vpGkVPWCDYFUhsSCEgfpDtBlFT2XLWMZGhkkYtJAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb4b6e7c6ea62f1fecfa0998b24562e3d838903f18546625ceb599ca45812ee6","last_reissued_at":"2026-05-17T23:43:32.989968Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.989968Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Disentanglement in Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Emile Mathieu, N. Siddharth, Tom Rainforth, Yee Whye Teh","submitted_at":"2018-12-06T22:16:28Z","abstract_excerpt":"We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of overlap, and b) the aggregate encoding of the data conforming to a desired structure, represented through the prior. Decomposition permits disentanglement, i.e. explicit independence between latents, as a special case, but also allows for a much richer class of properties to be imposed on the learnt representation, such as sparsity, clustering, independent subspaces, or even i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.02833","kind":"arxiv","version":3},"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":"1812.02833","created_at":"2026-05-17T23:43:32.990040+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.02833v3","created_at":"2026-05-17T23:43:32.990040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.02833","created_at":"2026-05-17T23:43:32.990040+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNFW47DOUYXR","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNFW47DOUYXR73H2","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNFW47DO","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.20732","citing_title":"Deep Attention Reweighting: Post-Hoc Attention-Based Feature Aggregation in CNNs for Disentangling Core and Spurious Features under Spurious Correlations","ref_index":50,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P","json":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P.json","graph_json":"https://pith.science/api/pith-number/ZNFW47DOUYXR73H2BGMLERLC4P/graph.json","events_json":"https://pith.science/api/pith-number/ZNFW47DOUYXR73H2BGMLERLC4P/events.json","paper":"https://pith.science/paper/ZNFW47DO"},"agent_actions":{"view_html":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P","download_json":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P.json","view_paper":"https://pith.science/paper/ZNFW47DO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.02833&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNFW47DOUYXR73H2BGMLERLC4P/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNFW47DOUYXR73H2BGMLERLC4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P/action/storage_attestation","attest_author":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P/action/author_attestation","sign_citation":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P/action/citation_signature","submit_replication":"https://pith.science/pith/ZNFW47DOUYXR73H2BGMLERLC4P/action/replication_record"}},"created_at":"2026-05-17T23:43:32.990040+00:00","updated_at":"2026-05-17T23:43:32.990040+00:00"}