{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FCYYEBG3KLEQTHK2IRTJNJLX3A","short_pith_number":"pith:FCYYEBG3","schema_version":"1.0","canonical_sha256":"28b18204db52c9099d5a446696a577d823d32f6e080cf4baa12eb0d948db286b","source":{"kind":"arxiv","id":"2309.13303","version":1},"attestation_state":"computed","paper":{"title":"C$^2$VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Longbing Cao, Zhangkai Wu","submitted_at":"2023-09-23T08:33:48Z","abstract_excerpt":"We present a self-supervised variational autoencoder (VAE) to jointly learn disentangled and dependent hidden factors and then enhance disentangled representation learning by a self-supervised classifier to eliminate coupled representations in a contrastive manner. To this end, a Contrastive Copula VAE (C$^2$VAE) is introduced without relying on prior knowledge about data in the probabilistic principle and involving strong modeling assumptions on the posterior in the neural architecture. C$^2$VAE simultaneously factorizes the posterior (evidence lower bound, ELBO) with total correlation (TC)-d"},"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":"2309.13303","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-23T08:33:48Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"36d6912bd1310b67ce347cc4b597d82bdfd4644c7b945eaac30666658dbf848a","abstract_canon_sha256":"688db0b3df43f6366920a45e317cf2f59178c3cd7b21e3d25e92dd231c29034f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:53:49.969569Z","signature_b64":"b9WC+S/WBc8yS1NKBfPGXPT71FBu50F3PccJND5WhJV7EgNLAlCV9lAHHvPzBpToNmMKb2noLD1YXXhmdEjPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b18204db52c9099d5a446696a577d823d32f6e080cf4baa12eb0d948db286b","last_reissued_at":"2026-07-05T06:53:49.969081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:53:49.969081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"C$^2$VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Longbing Cao, Zhangkai Wu","submitted_at":"2023-09-23T08:33:48Z","abstract_excerpt":"We present a self-supervised variational autoencoder (VAE) to jointly learn disentangled and dependent hidden factors and then enhance disentangled representation learning by a self-supervised classifier to eliminate coupled representations in a contrastive manner. To this end, a Contrastive Copula VAE (C$^2$VAE) is introduced without relying on prior knowledge about data in the probabilistic principle and involving strong modeling assumptions on the posterior in the neural architecture. C$^2$VAE simultaneously factorizes the posterior (evidence lower bound, ELBO) with total correlation (TC)-d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13303","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/2309.13303/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":"2309.13303","created_at":"2026-07-05T06:53:49.969152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13303v1","created_at":"2026-07-05T06:53:49.969152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13303","created_at":"2026-07-05T06:53:49.969152+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCYYEBG3KLEQ","created_at":"2026-07-05T06:53:49.969152+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCYYEBG3KLEQTHK2","created_at":"2026-07-05T06:53:49.969152+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCYYEBG3","created_at":"2026-07-05T06:53:49.969152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.08364","citing_title":"A Survey on Pre-Trained Diffusion Model Distillations","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A","json":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A.json","graph_json":"https://pith.science/api/pith-number/FCYYEBG3KLEQTHK2IRTJNJLX3A/graph.json","events_json":"https://pith.science/api/pith-number/FCYYEBG3KLEQTHK2IRTJNJLX3A/events.json","paper":"https://pith.science/paper/FCYYEBG3"},"agent_actions":{"view_html":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A","download_json":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A.json","view_paper":"https://pith.science/paper/FCYYEBG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13303&json=true","fetch_graph":"https://pith.science/api/pith-number/FCYYEBG3KLEQTHK2IRTJNJLX3A/graph.json","fetch_events":"https://pith.science/api/pith-number/FCYYEBG3KLEQTHK2IRTJNJLX3A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A/action/storage_attestation","attest_author":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A/action/author_attestation","sign_citation":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A/action/citation_signature","submit_replication":"https://pith.science/pith/FCYYEBG3KLEQTHK2IRTJNJLX3A/action/replication_record"}},"created_at":"2026-07-05T06:53:49.969152+00:00","updated_at":"2026-07-05T06:53:49.969152+00:00"}