{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LD4B3IDLDBLUEB2BSPYYOS2GD2","short_pith_number":"pith:LD4B3IDL","schema_version":"1.0","canonical_sha256":"58f81da06b185742074193f1874b461ea5e451aaae695558b4abc66127645847","source":{"kind":"arxiv","id":"1910.01791","version":2},"attestation_state":"computed","paper":{"title":"Conditional out-of-sample generation for unpaired data using trVAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","q-bio.CB","q-bio.GN","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian J. Theis, F. Alexander Wolf, Mohammad Lotfollahi, Mohsen Naghipourfar","submitted_at":"2019-10-04T03:39:35Z","abstract_excerpt":"While generative models have shown great success in generating high-dimensional samples conditional on low-dimensional descriptors (learning e.g. stroke thickness in MNIST, hair color in CelebA, or speaker identity in Wavenet), their generation out-of-sample poses fundamental problems. The conditional variational autoencoder (CVAE) as a simple conditional generative model does not explicitly relate conditions during training and, hence, has no incentive of learning a compact joint distribution across conditions. We overcome this limitation by matching their distributions using maximum mean dis"},"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":"1910.01791","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-04T03:39:35Z","cross_cats_sorted":["eess.IV","q-bio.CB","q-bio.GN","stat.ML"],"title_canon_sha256":"b69efbbce2c70ab43bd4cde8df81168e37d4378848db44adcb16ab1c2d98a2b0","abstract_canon_sha256":"1efbcc6c941cb85734acd30f627bc6876471dedc25cb8d4c978d0db433632d83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:15:50.640606Z","signature_b64":"KEgVd+K0792qHK+zbM8vFwlQV9ef6w1lfhtS6k188cbjIpJ+0esGOd173MwvYoEORRaSYQubUskKrSf15he6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f81da06b185742074193f1874b461ea5e451aaae695558b4abc66127645847","last_reissued_at":"2026-07-05T00:15:50.640021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:15:50.640021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conditional out-of-sample generation for unpaired data using trVAE","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV","q-bio.CB","q-bio.GN","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fabian J. Theis, F. Alexander Wolf, Mohammad Lotfollahi, Mohsen Naghipourfar","submitted_at":"2019-10-04T03:39:35Z","abstract_excerpt":"While generative models have shown great success in generating high-dimensional samples conditional on low-dimensional descriptors (learning e.g. stroke thickness in MNIST, hair color in CelebA, or speaker identity in Wavenet), their generation out-of-sample poses fundamental problems. The conditional variational autoencoder (CVAE) as a simple conditional generative model does not explicitly relate conditions during training and, hence, has no incentive of learning a compact joint distribution across conditions. We overcome this limitation by matching their distributions using maximum mean dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01791","kind":"arxiv","version":2},"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/1910.01791/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":"1910.01791","created_at":"2026-07-05T00:15:50.640089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.01791v2","created_at":"2026-07-05T00:15:50.640089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01791","created_at":"2026-07-05T00:15:50.640089+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD4B3IDLDBLU","created_at":"2026-07-05T00:15:50.640089+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD4B3IDLDBLUEB2B","created_at":"2026-07-05T00:15:50.640089+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD4B3IDL","created_at":"2026-07-05T00:15:50.640089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08303","citing_title":"Evaluation of an Autonomous Surface Robot Equipped with a Transformable Mobility Mechanism for Efficient Mobility Control","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2","json":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2.json","graph_json":"https://pith.science/api/pith-number/LD4B3IDLDBLUEB2BSPYYOS2GD2/graph.json","events_json":"https://pith.science/api/pith-number/LD4B3IDLDBLUEB2BSPYYOS2GD2/events.json","paper":"https://pith.science/paper/LD4B3IDL"},"agent_actions":{"view_html":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2","download_json":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2.json","view_paper":"https://pith.science/paper/LD4B3IDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.01791&json=true","fetch_graph":"https://pith.science/api/pith-number/LD4B3IDLDBLUEB2BSPYYOS2GD2/graph.json","fetch_events":"https://pith.science/api/pith-number/LD4B3IDLDBLUEB2BSPYYOS2GD2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2/action/storage_attestation","attest_author":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2/action/author_attestation","sign_citation":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2/action/citation_signature","submit_replication":"https://pith.science/pith/LD4B3IDLDBLUEB2BSPYYOS2GD2/action/replication_record"}},"created_at":"2026-07-05T00:15:50.640089+00:00","updated_at":"2026-07-05T00:15:50.640089+00:00"}