{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GRYWMCYKKI7NPI7URTJXOCATST","short_pith_number":"pith:GRYWMCYK","schema_version":"1.0","canonical_sha256":"3471660b0a523ed7a3f48cd377081394da03a465e0f5d8d0eb167073d43dfa25","source":{"kind":"arxiv","id":"2211.11719","version":2},"attestation_state":"computed","paper":{"title":"First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Tengyu Ma","submitted_at":"2022-11-21T18:41:19Z","abstract_excerpt":"Real-world machine learning applications often involve deploying neural networks to domains that are not seen in the training time. Hence, we need to understand the extrapolation of nonlinear models -- under what conditions on the distributions and function class, models can be guaranteed to extrapolate to new test distributions. The question is very challenging because even two-layer neural networks cannot be guaranteed to extrapolate outside the support of the training distribution without further assumptions on the domain shift. This paper makes some initial steps toward analyzing the extra"},"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":"2211.11719","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-21T18:41:19Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d43984669749674651f9eca70c31e4c66c7dce8a82943312abf33dd223edc1e4","abstract_canon_sha256":"c65dafa92af1e8c1d65b6dc83778db0621ae784aac2d979b55c1c22d4a5f8f2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:28.652714Z","signature_b64":"cYWJiPqa41Z3odqaGwfMD+FaJjiz17GJDY1dG0KEra7gPH0RvoiBC8MdfbaPnhMP74bkRibUa9M74yziDEe9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3471660b0a523ed7a3f48cd377081394da03a465e0f5d8d0eb167073d43dfa25","last_reissued_at":"2026-07-05T05:21:28.652267Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:28.652267Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kefan Dong, Tengyu Ma","submitted_at":"2022-11-21T18:41:19Z","abstract_excerpt":"Real-world machine learning applications often involve deploying neural networks to domains that are not seen in the training time. Hence, we need to understand the extrapolation of nonlinear models -- under what conditions on the distributions and function class, models can be guaranteed to extrapolate to new test distributions. The question is very challenging because even two-layer neural networks cannot be guaranteed to extrapolate outside the support of the training distribution without further assumptions on the domain shift. This paper makes some initial steps toward analyzing the extra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.11719","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/2211.11719/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":"2211.11719","created_at":"2026-07-05T05:21:28.652323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.11719v2","created_at":"2026-07-05T05:21:28.652323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.11719","created_at":"2026-07-05T05:21:28.652323+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRYWMCYKKI7N","created_at":"2026-07-05T05:21:28.652323+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRYWMCYKKI7NPI7U","created_at":"2026-07-05T05:21:28.652323+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRYWMCYK","created_at":"2026-07-05T05:21:28.652323+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/GRYWMCYKKI7NPI7URTJXOCATST","json":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST.json","graph_json":"https://pith.science/api/pith-number/GRYWMCYKKI7NPI7URTJXOCATST/graph.json","events_json":"https://pith.science/api/pith-number/GRYWMCYKKI7NPI7URTJXOCATST/events.json","paper":"https://pith.science/paper/GRYWMCYK"},"agent_actions":{"view_html":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST","download_json":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST.json","view_paper":"https://pith.science/paper/GRYWMCYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.11719&json=true","fetch_graph":"https://pith.science/api/pith-number/GRYWMCYKKI7NPI7URTJXOCATST/graph.json","fetch_events":"https://pith.science/api/pith-number/GRYWMCYKKI7NPI7URTJXOCATST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST/action/storage_attestation","attest_author":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST/action/author_attestation","sign_citation":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST/action/citation_signature","submit_replication":"https://pith.science/pith/GRYWMCYKKI7NPI7URTJXOCATST/action/replication_record"}},"created_at":"2026-07-05T05:21:28.652323+00:00","updated_at":"2026-07-05T05:21:28.652323+00:00"}