{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HH4EO636C6ATLMXILE63DTM3NT","short_pith_number":"pith:HH4EO636","schema_version":"1.0","canonical_sha256":"39f8477b7e178135b2e8593db1cd9b6cf02c1adbc97c23e41adc32a85e638efd","source":{"kind":"arxiv","id":"2106.04923","version":2},"attestation_state":"computed","paper":{"title":"Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, L\\'eo Andeol, Takafumi Kanamori, Yuichiro Wada, Yusei Kawakami","submitted_at":"2021-06-09T09:08:51Z","abstract_excerpt":"Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for example, by learning a domain-invariant representation. However, common ML losses do not give strong guarantees on how consistently the ML model performs for different domains, in particular, whether the model performs well on a domain at the expense of its performance on another domain. In this paper, we build new theoretical foundations for this problem, by c"},"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":"2106.04923","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-09T09:08:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c07be96f8041880055d21f30744b255cb1fadad1f97b2b9476fae20e01a8a772","abstract_canon_sha256":"fbae5ee5dd4ef55eb1921f11333026ba8e1bddab0bb5fb94ac94955353a6c3a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:54.833432Z","signature_b64":"CGgqe8obgy9IHSYIDHz46zna8g8V56OERV+LuECIWR41cOMn1G20kNk8uVr3HDvMbDPHy9u2NmsVnLab/WlxAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39f8477b7e178135b2e8593db1cd9b6cf02c1adbc97c23e41adc32a85e638efd","last_reissued_at":"2026-07-05T06:42:54.832937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:54.832937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gr\\'egoire Montavon, Klaus-Robert M\\\"uller, L\\'eo Andeol, Takafumi Kanamori, Yuichiro Wada, Yusei Kawakami","submitted_at":"2021-06-09T09:08:51Z","abstract_excerpt":"Domain shifts in the training data are common in practical applications of machine learning; they occur for instance when the data is coming from different sources. Ideally, a ML model should work well independently of these shifts, for example, by learning a domain-invariant representation. However, common ML losses do not give strong guarantees on how consistently the ML model performs for different domains, in particular, whether the model performs well on a domain at the expense of its performance on another domain. In this paper, we build new theoretical foundations for this problem, by c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.04923","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/2106.04923/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":"2106.04923","created_at":"2026-07-05T06:42:54.832996+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.04923v2","created_at":"2026-07-05T06:42:54.832996+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.04923","created_at":"2026-07-05T06:42:54.832996+00:00"},{"alias_kind":"pith_short_12","alias_value":"HH4EO636C6AT","created_at":"2026-07-05T06:42:54.832996+00:00"},{"alias_kind":"pith_short_16","alias_value":"HH4EO636C6ATLMXI","created_at":"2026-07-05T06:42:54.832996+00:00"},{"alias_kind":"pith_short_8","alias_value":"HH4EO636","created_at":"2026-07-05T06:42:54.832996+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT","json":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT.json","graph_json":"https://pith.science/api/pith-number/HH4EO636C6ATLMXILE63DTM3NT/graph.json","events_json":"https://pith.science/api/pith-number/HH4EO636C6ATLMXILE63DTM3NT/events.json","paper":"https://pith.science/paper/HH4EO636"},"agent_actions":{"view_html":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT","download_json":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT.json","view_paper":"https://pith.science/paper/HH4EO636","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.04923&json=true","fetch_graph":"https://pith.science/api/pith-number/HH4EO636C6ATLMXILE63DTM3NT/graph.json","fetch_events":"https://pith.science/api/pith-number/HH4EO636C6ATLMXILE63DTM3NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT/action/storage_attestation","attest_author":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT/action/author_attestation","sign_citation":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT/action/citation_signature","submit_replication":"https://pith.science/pith/HH4EO636C6ATLMXILE63DTM3NT/action/replication_record"}},"created_at":"2026-07-05T06:42:54.832996+00:00","updated_at":"2026-07-05T06:42:54.832996+00:00"}