{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QALSADLRIHWNYIYQI2WTRI2IGU","short_pith_number":"pith:QALSADLR","schema_version":"1.0","canonical_sha256":"8017200d7141ecdc231046ad38a3483501787f2866ea0fcff7a301be022a9c77","source":{"kind":"arxiv","id":"2308.15856","version":1},"attestation_state":"computed","paper":{"title":"Domain Generalization without Excess Empirical Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ozan Sener, Vladlen Koltun","submitted_at":"2023-08-30T08:46:46Z","abstract_excerpt":"Given data from diverse sets of distinct distributions, domain generalization aims to learn models that generalize to unseen distributions. A common approach is designing a data-driven surrogate penalty to capture generalization and minimize the empirical risk jointly with the penalty. We argue that a significant failure mode of this recipe is an excess risk due to an erroneous penalty or hardness in joint optimization. We present an approach that eliminates this problem. Instead of jointly minimizing empirical risk with the penalty, we minimize the penalty under the constraint of optimality o"},"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":"2308.15856","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-08-30T08:46:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1076cf11ac3848de7c28e6c6fb3cd9b2802ecac9243fa19c40ef6eaf8476ad58","abstract_canon_sha256":"74c757f0947b7bc8f4a54f612328c83f039601c68bff151bf47d8fe816db08cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:46:14.230403Z","signature_b64":"P9F7hD5Bxtp1NgYbm15KMoIKi9Vvv2lZ4u64iaiLVCHSELCHeNYNAoeKYfE22FC+fdVHgUsKCBN6cwlzdprVCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8017200d7141ecdc231046ad38a3483501787f2866ea0fcff7a301be022a9c77","last_reissued_at":"2026-07-05T06:46:14.229852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:46:14.229852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain Generalization without Excess Empirical Risk","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ozan Sener, Vladlen Koltun","submitted_at":"2023-08-30T08:46:46Z","abstract_excerpt":"Given data from diverse sets of distinct distributions, domain generalization aims to learn models that generalize to unseen distributions. A common approach is designing a data-driven surrogate penalty to capture generalization and minimize the empirical risk jointly with the penalty. We argue that a significant failure mode of this recipe is an excess risk due to an erroneous penalty or hardness in joint optimization. We present an approach that eliminates this problem. Instead of jointly minimizing empirical risk with the penalty, we minimize the penalty under the constraint of optimality o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.15856","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/2308.15856/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":"2308.15856","created_at":"2026-07-05T06:46:14.229921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.15856v1","created_at":"2026-07-05T06:46:14.229921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.15856","created_at":"2026-07-05T06:46:14.229921+00:00"},{"alias_kind":"pith_short_12","alias_value":"QALSADLRIHWN","created_at":"2026-07-05T06:46:14.229921+00:00"},{"alias_kind":"pith_short_16","alias_value":"QALSADLRIHWNYIYQ","created_at":"2026-07-05T06:46:14.229921+00:00"},{"alias_kind":"pith_short_8","alias_value":"QALSADLR","created_at":"2026-07-05T06:46:14.229921+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/QALSADLRIHWNYIYQI2WTRI2IGU","json":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU.json","graph_json":"https://pith.science/api/pith-number/QALSADLRIHWNYIYQI2WTRI2IGU/graph.json","events_json":"https://pith.science/api/pith-number/QALSADLRIHWNYIYQI2WTRI2IGU/events.json","paper":"https://pith.science/paper/QALSADLR"},"agent_actions":{"view_html":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU","download_json":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU.json","view_paper":"https://pith.science/paper/QALSADLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.15856&json=true","fetch_graph":"https://pith.science/api/pith-number/QALSADLRIHWNYIYQI2WTRI2IGU/graph.json","fetch_events":"https://pith.science/api/pith-number/QALSADLRIHWNYIYQI2WTRI2IGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU/action/storage_attestation","attest_author":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU/action/author_attestation","sign_citation":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU/action/citation_signature","submit_replication":"https://pith.science/pith/QALSADLRIHWNYIYQI2WTRI2IGU/action/replication_record"}},"created_at":"2026-07-05T06:46:14.229921+00:00","updated_at":"2026-07-05T06:46:14.229921+00:00"}