{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NT3RFCAWY52KA4YATKBU5CRS6I","short_pith_number":"pith:NT3RFCAW","schema_version":"1.0","canonical_sha256":"6cf7128816c774a073009a834e8a32f235f415c77ea62b7ef9c5347721e4422d","source":{"kind":"arxiv","id":"2302.11836","version":3},"attestation_state":"computed","paper":{"title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kayhan Behdin, Rahul Mazumder","submitted_at":"2023-02-23T07:52:31Z","abstract_excerpt":"Sharpness-Aware Minimization (SAM) is a recent optimization framework aiming to improve the deep neural network generalization, through obtaining flatter (i.e. less sharp) solutions. As SAM has been numerically successful, recent papers have studied the theoretical aspects of the framework and have shown SAM solutions are indeed flat. However, there has been limited theoretical exploration regarding statistical properties of SAM. In this work, we directly study the statistical performance of SAM, and present a new theoretical explanation of why SAM generalizes well. To this end, we study two s"},"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":"2302.11836","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-02-23T07:52:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4fc1900ef030ca68c0ac3b1522a57237ae67edd79237448289793f43d06a9eb8","abstract_canon_sha256":"aed0a4e028a6ee3d3ac8d6a66cd05ce9a545160826dea868aca7371bf98cb4cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:45.276343Z","signature_b64":"vMnGeJmr+0EV81bU5n5ARZyTFmtoPZfoNZ34yapAjRC83JZxSy3wMZxJorrlT7m8J3s0TqMGngKH455W/lRrDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6cf7128816c774a073009a834e8a32f235f415c77ea62b7ef9c5347721e4422d","last_reissued_at":"2026-07-05T06:11:45.275801Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:45.275801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Statistical Properties of Sharpness-Aware Minimization: Provable Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kayhan Behdin, Rahul Mazumder","submitted_at":"2023-02-23T07:52:31Z","abstract_excerpt":"Sharpness-Aware Minimization (SAM) is a recent optimization framework aiming to improve the deep neural network generalization, through obtaining flatter (i.e. less sharp) solutions. As SAM has been numerically successful, recent papers have studied the theoretical aspects of the framework and have shown SAM solutions are indeed flat. However, there has been limited theoretical exploration regarding statistical properties of SAM. In this work, we directly study the statistical performance of SAM, and present a new theoretical explanation of why SAM generalizes well. To this end, we study two s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.11836","kind":"arxiv","version":3},"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/2302.11836/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":"2302.11836","created_at":"2026-07-05T06:11:45.275864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.11836v3","created_at":"2026-07-05T06:11:45.275864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.11836","created_at":"2026-07-05T06:11:45.275864+00:00"},{"alias_kind":"pith_short_12","alias_value":"NT3RFCAWY52K","created_at":"2026-07-05T06:11:45.275864+00:00"},{"alias_kind":"pith_short_16","alias_value":"NT3RFCAWY52KA4YA","created_at":"2026-07-05T06:11:45.275864+00:00"},{"alias_kind":"pith_short_8","alias_value":"NT3RFCAW","created_at":"2026-07-05T06:11:45.275864+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/NT3RFCAWY52KA4YATKBU5CRS6I","json":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I.json","graph_json":"https://pith.science/api/pith-number/NT3RFCAWY52KA4YATKBU5CRS6I/graph.json","events_json":"https://pith.science/api/pith-number/NT3RFCAWY52KA4YATKBU5CRS6I/events.json","paper":"https://pith.science/paper/NT3RFCAW"},"agent_actions":{"view_html":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I","download_json":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I.json","view_paper":"https://pith.science/paper/NT3RFCAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.11836&json=true","fetch_graph":"https://pith.science/api/pith-number/NT3RFCAWY52KA4YATKBU5CRS6I/graph.json","fetch_events":"https://pith.science/api/pith-number/NT3RFCAWY52KA4YATKBU5CRS6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I/action/storage_attestation","attest_author":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I/action/author_attestation","sign_citation":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I/action/citation_signature","submit_replication":"https://pith.science/pith/NT3RFCAWY52KA4YATKBU5CRS6I/action/replication_record"}},"created_at":"2026-07-05T06:11:45.275864+00:00","updated_at":"2026-07-05T06:11:45.275864+00:00"}