{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:QVEY674JJSKUGYS7IGPOBXK74L","short_pith_number":"pith:QVEY674J","schema_version":"1.0","canonical_sha256":"85498f7f894c9543625f419ee0dd5fe2fe3107e68cf4d275919cf7a1eba2253b","source":{"kind":"arxiv","id":"1804.02086","version":4},"attestation_state":"computed","paper":{"title":"Structured Disentangled Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alican Bozkurt, Babak Esmaeili, Brooks Paige, Dana H. Brooks, Hao Wu, Jan-Willem van de Meent, Jennifer Dy, N. Siddharth, Sarthak Jain","submitted_at":"2018-04-06T00:11:26Z","abstract_excerpt":"Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches generally assume a simple diagonal Gaussian prior and as a result are not able to reliably disentangle discrete factors of variation. We propose a two-level hierarchical objective to control relative degree of statistical independence between blocks of variables and individual variables"},"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":"1804.02086","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-06T00:11:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"170a865a299d40d979b54390577f14f8ecbcefccb4159ad84271f8f5d058dd0a","abstract_canon_sha256":"90ca4687127729f61581fede846810347c7deeba626aa44a7e383f34d4e81fb3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:30.912688Z","signature_b64":"MAA19tEG+NWCG5Xp2cg/LpUZOMXjLI7vDd+f0Phe0lX6Q/ew+qOsXrWSU+OpAZlwpuXkmZrQur3QjojjXJhoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85498f7f894c9543625f419ee0dd5fe2fe3107e68cf4d275919cf7a1eba2253b","last_reissued_at":"2026-05-17T23:58:30.912041Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:30.912041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structured Disentangled Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alican Bozkurt, Babak Esmaeili, Brooks Paige, Dana H. Brooks, Hao Wu, Jan-Willem van de Meent, Jennifer Dy, N. Siddharth, Sarthak Jain","submitted_at":"2018-04-06T00:11:26Z","abstract_excerpt":"Deep latent-variable models learn representations of high-dimensional data in an unsupervised manner. A number of recent efforts have focused on learning representations that disentangle statistically independent axes of variation by introducing modifications to the standard objective function. These approaches generally assume a simple diagonal Gaussian prior and as a result are not able to reliably disentangle discrete factors of variation. We propose a two-level hierarchical objective to control relative degree of statistical independence between blocks of variables and individual variables"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02086","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":""},"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":"1804.02086","created_at":"2026-05-17T23:58:30.912144+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02086v4","created_at":"2026-05-17T23:58:30.912144+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02086","created_at":"2026-05-17T23:58:30.912144+00:00"},{"alias_kind":"pith_short_12","alias_value":"QVEY674JJSKU","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_16","alias_value":"QVEY674JJSKUGYS7","created_at":"2026-05-18T12:32:46.962924+00:00"},{"alias_kind":"pith_short_8","alias_value":"QVEY674J","created_at":"2026-05-18T12:32:46.962924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":185,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L","json":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L.json","graph_json":"https://pith.science/api/pith-number/QVEY674JJSKUGYS7IGPOBXK74L/graph.json","events_json":"https://pith.science/api/pith-number/QVEY674JJSKUGYS7IGPOBXK74L/events.json","paper":"https://pith.science/paper/QVEY674J"},"agent_actions":{"view_html":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L","download_json":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L.json","view_paper":"https://pith.science/paper/QVEY674J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02086&json=true","fetch_graph":"https://pith.science/api/pith-number/QVEY674JJSKUGYS7IGPOBXK74L/graph.json","fetch_events":"https://pith.science/api/pith-number/QVEY674JJSKUGYS7IGPOBXK74L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L/action/storage_attestation","attest_author":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L/action/author_attestation","sign_citation":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L/action/citation_signature","submit_replication":"https://pith.science/pith/QVEY674JJSKUGYS7IGPOBXK74L/action/replication_record"}},"created_at":"2026-05-17T23:58:30.912144+00:00","updated_at":"2026-05-17T23:58:30.912144+00:00"}