{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4EDQ3Z7QD6D7L5XVUB7UIOK6JK","short_pith_number":"pith:4EDQ3Z7Q","schema_version":"1.0","canonical_sha256":"e1070de7f01f87f5f6f5a07f44395e4aa48211f75836010616e159a169ad48f9","source":{"kind":"arxiv","id":"1905.10427","version":2},"attestation_state":"computed","paper":{"title":"DIVA: Domain Invariant Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Louizos, Jakub M. Tomczak, Maximilian Ilse, Max Welling","submitted_at":"2019-05-24T19:57:39Z","abstract_excerpt":"We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational Autoencoder (DIVA), a generative model that tackles this problem by learning three independent latent subspaces, one for the domain, one for the class, and one for any residual variations. We highlight that due to the generative nature of our model we can also incorporate unlabeled data from known or previously unseen domains. To the best of our knowledge this has not been don"},"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":"1905.10427","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-24T19:57:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3c7bce13db6a4485f3ca1f63f646fe52b1c94bb036f38e684318bfe5cd3c02df","abstract_canon_sha256":"e83929fa33e4a9394aa4dacd86872f86bc4eac6cde5d4b7c72465db3e6c5f580"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:01.654705Z","signature_b64":"ZxETZvwevp4A5hpLsU0CSjcK2M8J83I8ru4oVWXEiJ8MoK1gu8TMJ6vtwXIKqKriWHhRX37qqX4IZCS8EsOOBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1070de7f01f87f5f6f5a07f44395e4aa48211f75836010616e159a169ad48f9","last_reissued_at":"2026-07-05T00:10:01.654261Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:01.654261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIVA: Domain Invariant Variational Autoencoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Christos Louizos, Jakub M. Tomczak, Maximilian Ilse, Max Welling","submitted_at":"2019-05-24T19:57:39Z","abstract_excerpt":"We consider the problem of domain generalization, namely, how to learn representations given data from a set of domains that generalize to data from a previously unseen domain. We propose the Domain Invariant Variational Autoencoder (DIVA), a generative model that tackles this problem by learning three independent latent subspaces, one for the domain, one for the class, and one for any residual variations. We highlight that due to the generative nature of our model we can also incorporate unlabeled data from known or previously unseen domains. To the best of our knowledge this has not been don"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10427","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/1905.10427/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":"1905.10427","created_at":"2026-07-05T00:10:01.654336+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10427v2","created_at":"2026-07-05T00:10:01.654336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10427","created_at":"2026-07-05T00:10:01.654336+00:00"},{"alias_kind":"pith_short_12","alias_value":"4EDQ3Z7QD6D7","created_at":"2026-07-05T00:10:01.654336+00:00"},{"alias_kind":"pith_short_16","alias_value":"4EDQ3Z7QD6D7L5XV","created_at":"2026-07-05T00:10:01.654336+00:00"},{"alias_kind":"pith_short_8","alias_value":"4EDQ3Z7Q","created_at":"2026-07-05T00:10:01.654336+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":296,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK","json":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK.json","graph_json":"https://pith.science/api/pith-number/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/graph.json","events_json":"https://pith.science/api/pith-number/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/events.json","paper":"https://pith.science/paper/4EDQ3Z7Q"},"agent_actions":{"view_html":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK","download_json":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK.json","view_paper":"https://pith.science/paper/4EDQ3Z7Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10427&json=true","fetch_graph":"https://pith.science/api/pith-number/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/graph.json","fetch_events":"https://pith.science/api/pith-number/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/action/storage_attestation","attest_author":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/action/author_attestation","sign_citation":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/action/citation_signature","submit_replication":"https://pith.science/pith/4EDQ3Z7QD6D7L5XVUB7UIOK6JK/action/replication_record"}},"created_at":"2026-07-05T00:10:01.654336+00:00","updated_at":"2026-07-05T00:10:01.654336+00:00"}