{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:VLPD4GDQQZ77PGVRX2NOFXIFNG","short_pith_number":"pith:VLPD4GDQ","schema_version":"1.0","canonical_sha256":"aade3e1870867ff79ab1be9ae2dd0569ab89e74394087aabb13ef7eaa9f5f7d6","source":{"kind":"arxiv","id":"1902.04601","version":1},"attestation_state":"computed","paper":{"title":"Contrastive Variational Autoencoder Enhances Salient Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abubakar Abid, James Zou","submitted_at":"2019-02-12T19:32:48Z","abstract_excerpt":"Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target dataset compared to some background---e.g. enriched in patients compared to the general population. Contrastive learning is a principled framework to capture such enriched variation between the target and background, but state-of-the-art contrastive methods are limited to linear models. In this paper, we introduce the contrastive variational autoencoder (cVAE), wh"},"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":"1902.04601","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-12T19:32:48Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"31d61cf5191c98b14383ad4d309f3cf440d2a9cad56a6ee748ab58b0bb99c621","abstract_canon_sha256":"755a184fddffbda90ad5eb334a393f6ff5619ff1186cd58fe2d970add192750c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:06.486524Z","signature_b64":"tYOe/Pa2iCDAuOjDyJCv2Y0yIzeS6MSOQbwLXN2kKEXwQys7U3fo01TC0/gLSlWwlmHryZ3gIyYt4qvbmpQSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aade3e1870867ff79ab1be9ae2dd0569ab89e74394087aabb13ef7eaa9f5f7d6","last_reissued_at":"2026-05-17T23:54:06.486065Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:06.486065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrastive Variational Autoencoder Enhances Salient Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abubakar Abid, James Zou","submitted_at":"2019-02-12T19:32:48Z","abstract_excerpt":"Variational autoencoders are powerful algorithms for identifying dominant latent structure in a single dataset. In many applications, however, we are interested in modeling latent structure and variation that are enriched in a target dataset compared to some background---e.g. enriched in patients compared to the general population. Contrastive learning is a principled framework to capture such enriched variation between the target and background, but state-of-the-art contrastive methods are limited to linear models. In this paper, we introduce the contrastive variational autoencoder (cVAE), wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.04601","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":"1902.04601","created_at":"2026-05-17T23:54:06.486127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.04601v1","created_at":"2026-05-17T23:54:06.486127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.04601","created_at":"2026-05-17T23:54:06.486127+00:00"},{"alias_kind":"pith_short_12","alias_value":"VLPD4GDQQZ77","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"VLPD4GDQQZ77PGVR","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"VLPD4GDQ","created_at":"2026-05-18T12:33:30.264802+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.19771","citing_title":"Frictional Q-Learning","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG","json":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG.json","graph_json":"https://pith.science/api/pith-number/VLPD4GDQQZ77PGVRX2NOFXIFNG/graph.json","events_json":"https://pith.science/api/pith-number/VLPD4GDQQZ77PGVRX2NOFXIFNG/events.json","paper":"https://pith.science/paper/VLPD4GDQ"},"agent_actions":{"view_html":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG","download_json":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG.json","view_paper":"https://pith.science/paper/VLPD4GDQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.04601&json=true","fetch_graph":"https://pith.science/api/pith-number/VLPD4GDQQZ77PGVRX2NOFXIFNG/graph.json","fetch_events":"https://pith.science/api/pith-number/VLPD4GDQQZ77PGVRX2NOFXIFNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG/action/storage_attestation","attest_author":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG/action/author_attestation","sign_citation":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG/action/citation_signature","submit_replication":"https://pith.science/pith/VLPD4GDQQZ77PGVRX2NOFXIFNG/action/replication_record"}},"created_at":"2026-05-17T23:54:06.486127+00:00","updated_at":"2026-05-17T23:54:06.486127+00:00"}