{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:25CZO2UUPVZI2K5EQAQXUQCOZC","short_pith_number":"pith:25CZO2UU","schema_version":"1.0","canonical_sha256":"d745976a947d728d2ba480217a404ec8b0d3fe7225e4434821544b5dc0d9a55b","source":{"kind":"arxiv","id":"2412.05169","version":1},"attestation_state":"computed","paper":{"title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Samuel Schapiro","submitted_at":"2024-12-06T16:41:44Z","abstract_excerpt":"Recently, sharpness-aware minimization (SAM) has emerged as a promising method to improve generalization by minimizing sharpness, which is known to correlate well with generalization ability. Since the original proposal of SAM, many variants of SAM have been proposed to improve its accuracy and efficiency, but comparisons have mainly been restricted to the i.i.d. setting. In this paper we study SAM for out-of-distribution (OOD) generalization. First, we perform a comprehensive comparison of eight SAM variants on zero-shot OOD generalization, finding that the original SAM outperforms the Adam b"},"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":"2412.05169","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T16:41:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6a9b5db0dee43edc5ae30af1939699f25973e4dd1290805f1d5ac4b06546ad4b","abstract_canon_sha256":"b8aced532994dc5bd357b6269435c56604b46c163b3f96d3854a95ed63969028"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:29.721660Z","signature_b64":"u8m7oNdFYblm7+xmuHkEHZ/Z4QAoRjPeX6gIFhL8FhBepLsIDj9hM7yqnsJJyTIuiN6bGz/un1Z7+bdYV7h6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d745976a947d728d2ba480217a404ec8b0d3fe7225e4434821544b5dc0d9a55b","last_reissued_at":"2026-07-05T09:45:29.721222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:29.721222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding the Role of Sharpness-Aware Minimization Algorithms for Out-of-Distribution Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Han Zhao, Samuel Schapiro","submitted_at":"2024-12-06T16:41:44Z","abstract_excerpt":"Recently, sharpness-aware minimization (SAM) has emerged as a promising method to improve generalization by minimizing sharpness, which is known to correlate well with generalization ability. Since the original proposal of SAM, many variants of SAM have been proposed to improve its accuracy and efficiency, but comparisons have mainly been restricted to the i.i.d. setting. In this paper we study SAM for out-of-distribution (OOD) generalization. First, we perform a comprehensive comparison of eight SAM variants on zero-shot OOD generalization, finding that the original SAM outperforms the Adam b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05169","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/2412.05169/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":"2412.05169","created_at":"2026-07-05T09:45:29.721280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05169v1","created_at":"2026-07-05T09:45:29.721280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05169","created_at":"2026-07-05T09:45:29.721280+00:00"},{"alias_kind":"pith_short_12","alias_value":"25CZO2UUPVZI","created_at":"2026-07-05T09:45:29.721280+00:00"},{"alias_kind":"pith_short_16","alias_value":"25CZO2UUPVZI2K5E","created_at":"2026-07-05T09:45:29.721280+00:00"},{"alias_kind":"pith_short_8","alias_value":"25CZO2UU","created_at":"2026-07-05T09:45:29.721280+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06418","citing_title":"Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss","ref_index":188,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08192","citing_title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC","json":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC.json","graph_json":"https://pith.science/api/pith-number/25CZO2UUPVZI2K5EQAQXUQCOZC/graph.json","events_json":"https://pith.science/api/pith-number/25CZO2UUPVZI2K5EQAQXUQCOZC/events.json","paper":"https://pith.science/paper/25CZO2UU"},"agent_actions":{"view_html":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC","download_json":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC.json","view_paper":"https://pith.science/paper/25CZO2UU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05169&json=true","fetch_graph":"https://pith.science/api/pith-number/25CZO2UUPVZI2K5EQAQXUQCOZC/graph.json","fetch_events":"https://pith.science/api/pith-number/25CZO2UUPVZI2K5EQAQXUQCOZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC/action/storage_attestation","attest_author":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC/action/author_attestation","sign_citation":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC/action/citation_signature","submit_replication":"https://pith.science/pith/25CZO2UUPVZI2K5EQAQXUQCOZC/action/replication_record"}},"created_at":"2026-07-05T09:45:29.721280+00:00","updated_at":"2026-07-05T09:45:29.721280+00:00"}