{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WKAZBTULDTLQHEMQWVHEYPVX6X","short_pith_number":"pith:WKAZBTUL","schema_version":"1.0","canonical_sha256":"b28190ce8b1cd7039190b54e4c3eb7f5ef3acb56bce8f0c1d63c30032695fd98","source":{"kind":"arxiv","id":"1905.09432","version":1},"attestation_state":"computed","paper":{"title":"Learning Discrete and Continuous Factors of Data via Alternating Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyun Oh Song, Yeonwoo Jeong","submitted_at":"2019-05-23T02:06:50Z","abstract_excerpt":"We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the information flow in the $\\beta$-vae framework. Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure.\n  This leads to an interestin"},"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":"1905.09432","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-23T02:06:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"42c193c5884e0826898054cd73f7f838bf0ae5f4cd74621056f1c18425ce2092","abstract_canon_sha256":"5e2f3f6c50894362085bb84c6191f5360dec20793df5b80f8c4a40b0623f2ffc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:17.046009Z","signature_b64":"LyVqz8pJh323Y943ZMMtAXMkhoqadkJrYj9GZ5TKdAB2NpVtLTyggca1yjEEgxdEDDONnpxesBw5CMD1NKFQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b28190ce8b1cd7039190b54e4c3eb7f5ef3acb56bce8f0c1d63c30032695fd98","last_reissued_at":"2026-05-17T23:45:17.045301Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:17.045301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Discrete and Continuous Factors of Data via Alternating Disentanglement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyun Oh Song, Yeonwoo Jeong","submitted_at":"2019-05-23T02:06:50Z","abstract_excerpt":"We address the problem of unsupervised disentanglement of discrete and continuous explanatory factors of data. We first show a simple procedure for minimizing the total correlation of the continuous latent variables without having to use a discriminator network or perform importance sampling, via cascading the information flow in the $\\beta$-vae framework. Furthermore, we propose a method which avoids offloading the entire burden of jointly modeling the continuous and discrete factors to the variational encoder by employing a separate discrete inference procedure.\n  This leads to an interestin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09432","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":"1905.09432","created_at":"2026-05-17T23:45:17.045432+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09432v1","created_at":"2026-05-17T23:45:17.045432+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09432","created_at":"2026-05-17T23:45:17.045432+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKAZBTULDTLQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKAZBTULDTLQHEMQ","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKAZBTUL","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X","json":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X.json","graph_json":"https://pith.science/api/pith-number/WKAZBTULDTLQHEMQWVHEYPVX6X/graph.json","events_json":"https://pith.science/api/pith-number/WKAZBTULDTLQHEMQWVHEYPVX6X/events.json","paper":"https://pith.science/paper/WKAZBTUL"},"agent_actions":{"view_html":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X","download_json":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X.json","view_paper":"https://pith.science/paper/WKAZBTUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09432&json=true","fetch_graph":"https://pith.science/api/pith-number/WKAZBTULDTLQHEMQWVHEYPVX6X/graph.json","fetch_events":"https://pith.science/api/pith-number/WKAZBTULDTLQHEMQWVHEYPVX6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X/action/storage_attestation","attest_author":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X/action/author_attestation","sign_citation":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X/action/citation_signature","submit_replication":"https://pith.science/pith/WKAZBTULDTLQHEMQWVHEYPVX6X/action/replication_record"}},"created_at":"2026-05-17T23:45:17.045432+00:00","updated_at":"2026-05-17T23:45:17.045432+00:00"}