{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HKBWCHHZN5RLOCVZSZMILHTV4D","short_pith_number":"pith:HKBWCHHZ","schema_version":"1.0","canonical_sha256":"3a83611cf96f62b70ab99658859e75e0dd597ff04c341c1923e01eb69e003c23","source":{"kind":"arxiv","id":"1902.01568","version":1},"attestation_state":"computed","paper":{"title":"Relevance Factor VAE: Learning and Identifying Disentangled Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Pritish Sahu, Vladimir Pavlovic, Yuting Wang","submitted_at":"2019-02-05T06:55:36Z","abstract_excerpt":"We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality. Our model, dubbed Relevance-Factor-VAE, leverages the total correlation (TC) in the latent space to achieve the disentanglement goal, but also addresses the key issue of existing approaches which cannot distinguish between meaningful and nuisance factors of latent variation, often the source of considerable degradation in disentanglement performance. We tackle this "},"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":"1902.01568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-05T06:55:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"fa6bb24ff6a2c031df246e6f84606cb838f0b76843ff7b351cda374fb72f9bc7","abstract_canon_sha256":"1eebda4b6f271dbeb3d1084aeafcbd383c9c7435f3dd226ef035722d7d9e9262"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:47.295876Z","signature_b64":"YeuAzl1WJDcq89Q4ClKUHI1re4+VP2NE+V1FuSzkSxj2BWaX8wiH5wgYbocA+rm8+IjVSyjPBTdzTjcS0JmGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a83611cf96f62b70ab99658859e75e0dd597ff04c341c1923e01eb69e003c23","last_reissued_at":"2026-05-17T23:54:47.295250Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:47.295250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relevance Factor VAE: Learning and Identifying Disentangled Factors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Minyoung Kim, Pritish Sahu, Vladimir Pavlovic, Yuting Wang","submitted_at":"2019-02-05T06:55:36Z","abstract_excerpt":"We propose a novel VAE-based deep auto-encoder model that can learn disentangled latent representations in a fully unsupervised manner, endowed with the ability to identify all meaningful sources of variation and their cardinality. Our model, dubbed Relevance-Factor-VAE, leverages the total correlation (TC) in the latent space to achieve the disentanglement goal, but also addresses the key issue of existing approaches which cannot distinguish between meaningful and nuisance factors of latent variation, often the source of considerable degradation in disentanglement performance. We tackle this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.01568","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":""},"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":"1902.01568","created_at":"2026-05-17T23:54:47.295354+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.01568v1","created_at":"2026-05-17T23:54:47.295354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.01568","created_at":"2026-05-17T23:54:47.295354+00:00"},{"alias_kind":"pith_short_12","alias_value":"HKBWCHHZN5RL","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"HKBWCHHZN5RLOCVZ","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"HKBWCHHZ","created_at":"2026-05-18T12:33:18.533446+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":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D","json":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D.json","graph_json":"https://pith.science/api/pith-number/HKBWCHHZN5RLOCVZSZMILHTV4D/graph.json","events_json":"https://pith.science/api/pith-number/HKBWCHHZN5RLOCVZSZMILHTV4D/events.json","paper":"https://pith.science/paper/HKBWCHHZ"},"agent_actions":{"view_html":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D","download_json":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D.json","view_paper":"https://pith.science/paper/HKBWCHHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.01568&json=true","fetch_graph":"https://pith.science/api/pith-number/HKBWCHHZN5RLOCVZSZMILHTV4D/graph.json","fetch_events":"https://pith.science/api/pith-number/HKBWCHHZN5RLOCVZSZMILHTV4D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D/action/storage_attestation","attest_author":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D/action/author_attestation","sign_citation":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D/action/citation_signature","submit_replication":"https://pith.science/pith/HKBWCHHZN5RLOCVZSZMILHTV4D/action/replication_record"}},"created_at":"2026-05-17T23:54:47.295354+00:00","updated_at":"2026-05-17T23:54:47.295354+00:00"}