{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:EPWIIK2WIPX6NFEFGNJWI7DD7B","short_pith_number":"pith:EPWIIK2W","schema_version":"1.0","canonical_sha256":"23ec842b5643efe694853353647c63f86c34cb062f5cde8a7798211e29259772","source":{"kind":"arxiv","id":"2501.09163","version":1},"attestation_state":"computed","paper":{"title":"Towards Understanding Extrapolation: a Causal Lens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Guangyi Chen, Haoxuan Li, Kun Zhang, Lingjing Kong, Petar Stojanov","submitted_at":"2025-01-15T21:29:29Z","abstract_excerpt":"Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often involve only a handful of target samples, potentially lying outside the training support, which requires the capability of extrapolation. In this work, we aim to provide a theoretical understanding of when extrapolation is possible and offer principled methods to achieve it without requiring an on-support target distribution. To this end, we formulate the extrapolation problem with a latent-variable model that embodies "},"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":"2501.09163","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-15T21:29:29Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e33a2ecdb2e936646cfeae61b28892bc49d10e70eb8ed9c049638e41d7e66879","abstract_canon_sha256":"21b462ba1050907a022d2897a2336ccf567cffad48f414b6781712cd4894e714"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:42.847832Z","signature_b64":"GwBMgAP4uWksQkMGNwlfGTomEUjY35HUAgehmSqpLgusf4RktWThoXXv9Wgo+Rx8SL0fCZr0OAvrNSSOUhCkAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ec842b5643efe694853353647c63f86c34cb062f5cde8a7798211e29259772","last_reissued_at":"2026-07-05T10:01:42.847327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:42.847327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Extrapolation: a Causal Lens","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric P. Xing, Guangyi Chen, Haoxuan Li, Kun Zhang, Lingjing Kong, Petar Stojanov","submitted_at":"2025-01-15T21:29:29Z","abstract_excerpt":"Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often involve only a handful of target samples, potentially lying outside the training support, which requires the capability of extrapolation. In this work, we aim to provide a theoretical understanding of when extrapolation is possible and offer principled methods to achieve it without requiring an on-support target distribution. To this end, we formulate the extrapolation problem with a latent-variable model that embodies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09163","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/2501.09163/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":"2501.09163","created_at":"2026-07-05T10:01:42.847389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09163v1","created_at":"2026-07-05T10:01:42.847389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09163","created_at":"2026-07-05T10:01:42.847389+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPWIIK2WIPX6","created_at":"2026-07-05T10:01:42.847389+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPWIIK2WIPX6NFEF","created_at":"2026-07-05T10:01:42.847389+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPWIIK2W","created_at":"2026-07-05T10:01:42.847389+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/EPWIIK2WIPX6NFEFGNJWI7DD7B","json":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B.json","graph_json":"https://pith.science/api/pith-number/EPWIIK2WIPX6NFEFGNJWI7DD7B/graph.json","events_json":"https://pith.science/api/pith-number/EPWIIK2WIPX6NFEFGNJWI7DD7B/events.json","paper":"https://pith.science/paper/EPWIIK2W"},"agent_actions":{"view_html":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B","download_json":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B.json","view_paper":"https://pith.science/paper/EPWIIK2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09163&json=true","fetch_graph":"https://pith.science/api/pith-number/EPWIIK2WIPX6NFEFGNJWI7DD7B/graph.json","fetch_events":"https://pith.science/api/pith-number/EPWIIK2WIPX6NFEFGNJWI7DD7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B/action/storage_attestation","attest_author":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B/action/author_attestation","sign_citation":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B/action/citation_signature","submit_replication":"https://pith.science/pith/EPWIIK2WIPX6NFEFGNJWI7DD7B/action/replication_record"}},"created_at":"2026-07-05T10:01:42.847389+00:00","updated_at":"2026-07-05T10:01:42.847389+00:00"}