{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OE3OFVEJKWGWER6DWVOAIYFY6B","short_pith_number":"pith:OE3OFVEJ","schema_version":"1.0","canonical_sha256":"7136e2d489558d6247c3b55c0460b8f0602017b9b66b670a7d2a0b4d63bb1704","source":{"kind":"arxiv","id":"2605.15775","version":1},"attestation_state":"computed","paper":{"title":"Continual Learning of Domain-Invariant Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pascal Janetzky, Stefan Feuerriegel, Tobias Schlagenhauf","submitted_at":"2026-05-15T09:31:10Z","abstract_excerpt":"Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious, domain-specific cues (``shortcut learning''), which limits generalization to unseen domains after deployment. In this paper, we address this limitation through continual learning of domain-invariant representation. We introduce a broad class of CL methods that sequentially learn representations capturing invariant structures across domains. Our methods are mo"},"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":"2605.15775","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T09:31:10Z","cross_cats_sorted":[],"title_canon_sha256":"3e52fc9b1dfa8489da9c206e9eefb56618666a7e1f5bc20f887b5c58da5a0c15","abstract_canon_sha256":"9b912941e520201a2b95cab943554aeaf145ea47f189f14bdf3bec9f359e2c1a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:17.638878Z","signature_b64":"LhEqjzl/66csvZHyWdTizhe7FYZJlOetQtpg7bChS2rBkwMo46nmwBI34aDwzgZTha7KDLEi6XWbLGzdId2KCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7136e2d489558d6247c3b55c0460b8f0602017b9b66b670a7d2a0b4d63bb1704","last_reissued_at":"2026-05-20T00:01:17.638053Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:17.638053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continual Learning of Domain-Invariant Representations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Pascal Janetzky, Stefan Feuerriegel, Tobias Schlagenhauf","submitted_at":"2026-05-15T09:31:10Z","abstract_excerpt":"Continual learning (CL) aims to train models sequentially over multiple domains without forgetting previously learned knowledge. However, existing CL methods optimize for in-domain performance and are therefore prone to learning spurious, domain-specific cues (``shortcut learning''), which limits generalization to unseen domains after deployment. In this paper, we address this limitation through continual learning of domain-invariant representation. We introduce a broad class of CL methods that sequentially learn representations capturing invariant structures across domains. Our methods are mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15775","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/2605.15775/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.754247Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.933086Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3a3086c12744ffb3bf048ce4ed0f6e7b0214468e884c2e2c04031ae014d6ac40"},"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":"2605.15775","created_at":"2026-05-20T00:01:17.638187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15775v1","created_at":"2026-05-20T00:01:17.638187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15775","created_at":"2026-05-20T00:01:17.638187+00:00"},{"alias_kind":"pith_short_12","alias_value":"OE3OFVEJKWGW","created_at":"2026-05-20T00:01:17.638187+00:00"},{"alias_kind":"pith_short_16","alias_value":"OE3OFVEJKWGWER6D","created_at":"2026-05-20T00:01:17.638187+00:00"},{"alias_kind":"pith_short_8","alias_value":"OE3OFVEJ","created_at":"2026-05-20T00:01:17.638187+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/OE3OFVEJKWGWER6DWVOAIYFY6B","json":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B.json","graph_json":"https://pith.science/api/pith-number/OE3OFVEJKWGWER6DWVOAIYFY6B/graph.json","events_json":"https://pith.science/api/pith-number/OE3OFVEJKWGWER6DWVOAIYFY6B/events.json","paper":"https://pith.science/paper/OE3OFVEJ"},"agent_actions":{"view_html":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B","download_json":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B.json","view_paper":"https://pith.science/paper/OE3OFVEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15775&json=true","fetch_graph":"https://pith.science/api/pith-number/OE3OFVEJKWGWER6DWVOAIYFY6B/graph.json","fetch_events":"https://pith.science/api/pith-number/OE3OFVEJKWGWER6DWVOAIYFY6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B/action/storage_attestation","attest_author":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B/action/author_attestation","sign_citation":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B/action/citation_signature","submit_replication":"https://pith.science/pith/OE3OFVEJKWGWER6DWVOAIYFY6B/action/replication_record"}},"created_at":"2026-05-20T00:01:17.638187+00:00","updated_at":"2026-05-20T00:01:17.638187+00:00"}