{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:4XHACSXG7Z3XIIPBQZV3NSFROD","short_pith_number":"pith:4XHACSXG","schema_version":"1.0","canonical_sha256":"e5ce014ae6fe777421e1866bb6c8b170c217d1d2991d3b1d4ce0c27a84933f89","source":{"kind":"arxiv","id":"1507.05333","version":4},"attestation_state":"computed","paper":{"title":"Invariant Models for Causal Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jonas Peters, Mateo Rojas-Carulla, Richard Turner","submitted_at":"2015-07-19T20:36:10Z","abstract_excerpt":"Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true for a subset of predictor variables: the conditional distribution of the target variable given this subset of predictors is invariant over all tasks. We show how this assumption can be motivated from ideas in the field of causality. We focus on the problem of Domain Generalization, in which no examples from the test task are observed. We prove that in an ad"},"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":"1507.05333","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-07-19T20:36:10Z","cross_cats_sorted":[],"title_canon_sha256":"5d700b9059980b393f3e392a13e795b88258b5041b815a1acf74f949dd47a000","abstract_canon_sha256":"9397c950730ec796ba7cb39397396e06a4f24f2676855c1bc09187571c432f0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:08.139388Z","signature_b64":"0wGLuzr63lqY/VCuYn+5DPHETess3Vq6zy1cR0q0PeYRu0IpBdHAR53Y/FZ2M+ZBbBLkZOQ/HpjJrzIzgsfRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5ce014ae6fe777421e1866bb6c8b170c217d1d2991d3b1d4ce0c27a84933f89","last_reissued_at":"2026-05-18T00:05:08.138783Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:08.138783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Invariant Models for Causal Transfer Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Bernhard Sch\\\"olkopf, Jonas Peters, Mateo Rojas-Carulla, Richard Turner","submitted_at":"2015-07-19T20:36:10Z","abstract_excerpt":"Methods of transfer learning try to combine knowledge from several related tasks (or domains) to improve performance on a test task. Inspired by causal methodology, we relax the usual covariate shift assumption and assume that it holds true for a subset of predictor variables: the conditional distribution of the target variable given this subset of predictors is invariant over all tasks. We show how this assumption can be motivated from ideas in the field of causality. We focus on the problem of Domain Generalization, in which no examples from the test task are observed. We prove that in an ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.05333","kind":"arxiv","version":4},"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":"1507.05333","created_at":"2026-05-18T00:05:08.138875+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.05333v4","created_at":"2026-05-18T00:05:08.138875+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.05333","created_at":"2026-05-18T00:05:08.138875+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XHACSXG7Z3X","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XHACSXG7Z3XIIPB","created_at":"2026-05-18T12:29:05.191682+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XHACSXG","created_at":"2026-05-18T12:29:05.191682+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/4XHACSXG7Z3XIIPBQZV3NSFROD","json":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD.json","graph_json":"https://pith.science/api/pith-number/4XHACSXG7Z3XIIPBQZV3NSFROD/graph.json","events_json":"https://pith.science/api/pith-number/4XHACSXG7Z3XIIPBQZV3NSFROD/events.json","paper":"https://pith.science/paper/4XHACSXG"},"agent_actions":{"view_html":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD","download_json":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD.json","view_paper":"https://pith.science/paper/4XHACSXG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.05333&json=true","fetch_graph":"https://pith.science/api/pith-number/4XHACSXG7Z3XIIPBQZV3NSFROD/graph.json","fetch_events":"https://pith.science/api/pith-number/4XHACSXG7Z3XIIPBQZV3NSFROD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD/action/storage_attestation","attest_author":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD/action/author_attestation","sign_citation":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD/action/citation_signature","submit_replication":"https://pith.science/pith/4XHACSXG7Z3XIIPBQZV3NSFROD/action/replication_record"}},"created_at":"2026-05-18T00:05:08.138875+00:00","updated_at":"2026-05-18T00:05:08.138875+00:00"}