{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Q774Y7OPKRK6HOW5WHZ2F3HKXG","short_pith_number":"pith:Q774Y7OP","schema_version":"1.0","canonical_sha256":"87ffcc7dcf5455e3baddb1f3a2eceab9a1095a0b5d095593de44767496e9d8fd","source":{"kind":"arxiv","id":"2606.12680","version":1},"attestation_state":"computed","paper":{"title":"How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Elias Bareinboim, Fanny Yang, Julia Kostin, Kasra Jalaldoust, Samory Kpotufe","submitted_at":"2026-06-10T21:07:49Z","abstract_excerpt":"Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-based domain generalization has shown how shared causal structure between domains can induce invariant predictors, e.g., models on a subset of features which have stable risk across structured domain shifts. However, the extent to which such population-level causal invariances can lead to gains in finite-sample settings remains underexplored. In particular, in practice we often have access to a few labeled target samples"},"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":"2606.12680","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T21:07:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"71c75e58de765485de0a4747df8a93960f2bd7ba39a96b9911a88871a4f5b18f","abstract_canon_sha256":"db5d8287597646441e9374816d774aee9e4e407bc5e560b20e16803d34fe6576"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:08:44.267339Z","signature_b64":"qDdijv9DRVzjM+xbs6su1Xn+RQoYAaCWkiLUKTnsnbalSIpUa6YwxeowhiBGhbWtPzlZHtueOlBAgAEWBKbrDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87ffcc7dcf5455e3baddb1f3a2eceab9a1095a0b5d095593de44767496e9d8fd","last_reissued_at":"2026-06-12T01:08:44.266566Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:08:44.266566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Elias Bareinboim, Fanny Yang, Julia Kostin, Kasra Jalaldoust, Samory Kpotufe","submitted_at":"2026-06-10T21:07:49Z","abstract_excerpt":"Machine learning models often degrade when they are deployed on a target distribution that differs from the source distributions they were trained on. Recent work in causality-based domain generalization has shown how shared causal structure between domains can induce invariant predictors, e.g., models on a subset of features which have stable risk across structured domain shifts. However, the extent to which such population-level causal invariances can lead to gains in finite-sample settings remains underexplored. In particular, in practice we often have access to a few labeled target samples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12680","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/2606.12680/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":"2606.12680","created_at":"2026-06-12T01:08:44.266689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.12680v1","created_at":"2026-06-12T01:08:44.266689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12680","created_at":"2026-06-12T01:08:44.266689+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q774Y7OPKRK6","created_at":"2026-06-12T01:08:44.266689+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q774Y7OPKRK6HOW5","created_at":"2026-06-12T01:08:44.266689+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q774Y7OP","created_at":"2026-06-12T01:08:44.266689+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/Q774Y7OPKRK6HOW5WHZ2F3HKXG","json":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG.json","graph_json":"https://pith.science/api/pith-number/Q774Y7OPKRK6HOW5WHZ2F3HKXG/graph.json","events_json":"https://pith.science/api/pith-number/Q774Y7OPKRK6HOW5WHZ2F3HKXG/events.json","paper":"https://pith.science/paper/Q774Y7OP"},"agent_actions":{"view_html":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG","download_json":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG.json","view_paper":"https://pith.science/paper/Q774Y7OP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.12680&json=true","fetch_graph":"https://pith.science/api/pith-number/Q774Y7OPKRK6HOW5WHZ2F3HKXG/graph.json","fetch_events":"https://pith.science/api/pith-number/Q774Y7OPKRK6HOW5WHZ2F3HKXG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG/action/storage_attestation","attest_author":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG/action/author_attestation","sign_citation":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG/action/citation_signature","submit_replication":"https://pith.science/pith/Q774Y7OPKRK6HOW5WHZ2F3HKXG/action/replication_record"}},"created_at":"2026-06-12T01:08:44.266689+00:00","updated_at":"2026-06-12T01:08:44.266689+00:00"}