{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:74YS6AX7IEUCWCO5UGGKP5LICH","short_pith_number":"pith:74YS6AX7","schema_version":"1.0","canonical_sha256":"ff312f02ff41282b09dda18ca7f56811fede889a18dae4eb5cd4e89e1f0e3c5a","source":{"kind":"arxiv","id":"2505.12868","version":1},"attestation_state":"computed","paper":{"title":"Causality-Inspired Robustness for Nonlinear Models via Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Marin \\v{S}ola, Peter B\\\"uhlmann, Xinwei Shen","submitted_at":"2025-05-19T08:52:15Z","abstract_excerpt":"Distributional robustness is a central goal of prediction algorithms due to the prevalent distribution shifts in real-world data. The prediction model aims to minimize the worst-case risk among a class of distributions, a.k.a., an uncertainty set. Causality provides a modeling framework with a rigorous robustness guarantee in the above sense, where the uncertainty set is data-driven rather than pre-specified as in traditional distributional robustness optimization. However, current causality-inspired robustness methods possess finite-radius robustness guarantees only in the linear settings, wh"},"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":"2505.12868","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-19T08:52:15Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"0011f6453b2dc3b3d0dbf10c5fde2679e2840eb91060422d34ac88b442a38228","abstract_canon_sha256":"a061e5e784a9b0e16a438fd6eae77939d6414900027751551c6f4c9a5594d9e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:10.986704Z","signature_b64":"tGC3BEkhNFD+/GGitUoOB9tXq8/Q5NlzzKuJwclHOzQ97NxdZY1E7g8RoqB2aOCuIiOVrxR5QDMqjP/N/T74DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff312f02ff41282b09dda18ca7f56811fede889a18dae4eb5cd4e89e1f0e3c5a","last_reissued_at":"2026-07-05T11:05:10.986240Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:10.986240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Causality-Inspired Robustness for Nonlinear Models via Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Marin \\v{S}ola, Peter B\\\"uhlmann, Xinwei Shen","submitted_at":"2025-05-19T08:52:15Z","abstract_excerpt":"Distributional robustness is a central goal of prediction algorithms due to the prevalent distribution shifts in real-world data. The prediction model aims to minimize the worst-case risk among a class of distributions, a.k.a., an uncertainty set. Causality provides a modeling framework with a rigorous robustness guarantee in the above sense, where the uncertainty set is data-driven rather than pre-specified as in traditional distributional robustness optimization. However, current causality-inspired robustness methods possess finite-radius robustness guarantees only in the linear settings, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12868","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/2505.12868/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":"2505.12868","created_at":"2026-07-05T11:05:10.986297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12868v1","created_at":"2026-07-05T11:05:10.986297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12868","created_at":"2026-07-05T11:05:10.986297+00:00"},{"alias_kind":"pith_short_12","alias_value":"74YS6AX7IEUC","created_at":"2026-07-05T11:05:10.986297+00:00"},{"alias_kind":"pith_short_16","alias_value":"74YS6AX7IEUCWCO5","created_at":"2026-07-05T11:05:10.986297+00:00"},{"alias_kind":"pith_short_8","alias_value":"74YS6AX7","created_at":"2026-07-05T11:05:10.986297+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/74YS6AX7IEUCWCO5UGGKP5LICH","json":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH.json","graph_json":"https://pith.science/api/pith-number/74YS6AX7IEUCWCO5UGGKP5LICH/graph.json","events_json":"https://pith.science/api/pith-number/74YS6AX7IEUCWCO5UGGKP5LICH/events.json","paper":"https://pith.science/paper/74YS6AX7"},"agent_actions":{"view_html":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH","download_json":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH.json","view_paper":"https://pith.science/paper/74YS6AX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12868&json=true","fetch_graph":"https://pith.science/api/pith-number/74YS6AX7IEUCWCO5UGGKP5LICH/graph.json","fetch_events":"https://pith.science/api/pith-number/74YS6AX7IEUCWCO5UGGKP5LICH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH/action/storage_attestation","attest_author":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH/action/author_attestation","sign_citation":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH/action/citation_signature","submit_replication":"https://pith.science/pith/74YS6AX7IEUCWCO5UGGKP5LICH/action/replication_record"}},"created_at":"2026-07-05T11:05:10.986297+00:00","updated_at":"2026-07-05T11:05:10.986297+00:00"}