{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3DIZEA4UCJPD2NGUME37BUOWUM","short_pith_number":"pith:3DIZEA4U","schema_version":"1.0","canonical_sha256":"d8d1920394125e3d34d46137f0d1d6a30c285f6c9a98d358099b03dc77bafda6","source":{"kind":"arxiv","id":"2507.13287","version":1},"attestation_state":"computed","paper":{"title":"Optimal Empirical Risk Minimization under Temporal Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Dominik Rothenh\\\"ausler, Emily Fox, Ramesh Johari, Yujin Jeong","submitted_at":"2025-07-17T16:53:31Z","abstract_excerpt":"Temporal distribution shifts pose a key challenge for machine learning models trained and deployed in dynamically evolving environments. This paper introduces RIDER (RIsk minimization under Dynamically Evolving Regimes) which derives optimally-weighted empirical risk minimization procedures under temporal distribution shifts. Our approach is theoretically grounded in the random distribution shift model, where random shifts arise as a superposition of numerous unpredictable changes in the data-generating process. We show that common weighting schemes, such as pooling all data, exponentially wei"},"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":"2507.13287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2025-07-17T16:53:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1e041afab66cb208535a7bfda9b659a7b6b8c0b65f4eda31e3d29f7e46d2e0b9","abstract_canon_sha256":"d76e197b4adb9e14945e6dfd3863f1b1b478505f43f4666f6bec37e914a4a9f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:58.539857Z","signature_b64":"QNZTYWSxH+/vkKc8s4eo8RJZk3vA4TMDa//fQs5wuLkjFSYOWbn+E3rU+cAQOx2lDD3H/jOeR8I9ApPsV/dGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8d1920394125e3d34d46137f0d1d6a30c285f6c9a98d358099b03dc77bafda6","last_reissued_at":"2026-07-05T11:38:58.539404Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:58.539404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Empirical Risk Minimization under Temporal Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Dominik Rothenh\\\"ausler, Emily Fox, Ramesh Johari, Yujin Jeong","submitted_at":"2025-07-17T16:53:31Z","abstract_excerpt":"Temporal distribution shifts pose a key challenge for machine learning models trained and deployed in dynamically evolving environments. This paper introduces RIDER (RIsk minimization under Dynamically Evolving Regimes) which derives optimally-weighted empirical risk minimization procedures under temporal distribution shifts. Our approach is theoretically grounded in the random distribution shift model, where random shifts arise as a superposition of numerous unpredictable changes in the data-generating process. We show that common weighting schemes, such as pooling all data, exponentially wei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13287","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/2507.13287/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":"2507.13287","created_at":"2026-07-05T11:38:58.539453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13287v1","created_at":"2026-07-05T11:38:58.539453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13287","created_at":"2026-07-05T11:38:58.539453+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DIZEA4UCJPD","created_at":"2026-07-05T11:38:58.539453+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DIZEA4UCJPD2NGU","created_at":"2026-07-05T11:38:58.539453+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DIZEA4U","created_at":"2026-07-05T11:38:58.539453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.05742","citing_title":"Fast Rates for Nonstationary Weighted Risk Minimization","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM","json":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM.json","graph_json":"https://pith.science/api/pith-number/3DIZEA4UCJPD2NGUME37BUOWUM/graph.json","events_json":"https://pith.science/api/pith-number/3DIZEA4UCJPD2NGUME37BUOWUM/events.json","paper":"https://pith.science/paper/3DIZEA4U"},"agent_actions":{"view_html":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM","download_json":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM.json","view_paper":"https://pith.science/paper/3DIZEA4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13287&json=true","fetch_graph":"https://pith.science/api/pith-number/3DIZEA4UCJPD2NGUME37BUOWUM/graph.json","fetch_events":"https://pith.science/api/pith-number/3DIZEA4UCJPD2NGUME37BUOWUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM/action/storage_attestation","attest_author":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM/action/author_attestation","sign_citation":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM/action/citation_signature","submit_replication":"https://pith.science/pith/3DIZEA4UCJPD2NGUME37BUOWUM/action/replication_record"}},"created_at":"2026-07-05T11:38:58.539453+00:00","updated_at":"2026-07-05T11:38:58.539453+00:00"}