{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YYTQSSBXYLCI6AX7TM2JMXKDMO","short_pith_number":"pith:YYTQSSBX","schema_version":"1.0","canonical_sha256":"c627094837c2c48f02ff9b34965d4363934ccfb512a187322c3a2138a70cd723","source":{"kind":"arxiv","id":"2303.03108","version":3},"attestation_state":"computed","paper":{"title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Han Yu, Hao Zou, Peng Cui, Renzhe Xu, Xingxuan Zhang","submitted_at":"2023-03-03T16:58:53Z","abstract_excerpt":"Recently, flat minima are proven to be effective for improving generalization and sharpness-aware minimization (SAM) achieves state-of-the-art performance. Yet the current definition of flatness discussed in SAM and its follow-ups are limited to the zeroth-order flatness (i.e., the worst-case loss within a perturbation radius). We show that the zeroth-order flatness can be insufficient to discriminate minima with low generalization error from those with high generalization error both when there is a single minimum or multiple minima within the given perturbation radius. Thus we present first-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":"2303.03108","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T16:58:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3e03a2820245ce2221d0f6e63c09222a6b2e291482f33de60a13c3bbea907fec","abstract_canon_sha256":"3d5100ceddc7746e86b84ec73d2c3d065d0f7522ce4ab62147cf40687dcfc051"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:16.787496Z","signature_b64":"F8iRkOuQATyl1uggfVCbOM8FpXzCSmtmsThcolT+4i3JaTRVicTkI3ip+8FmCWE0IO+QV9+1mCJAc04NZ30UBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c627094837c2c48f02ff9b34965d4363934ccfb512a187322c3a2138a70cd723","last_reissued_at":"2026-07-05T06:28:16.787067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:16.787067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Han Yu, Hao Zou, Peng Cui, Renzhe Xu, Xingxuan Zhang","submitted_at":"2023-03-03T16:58:53Z","abstract_excerpt":"Recently, flat minima are proven to be effective for improving generalization and sharpness-aware minimization (SAM) achieves state-of-the-art performance. Yet the current definition of flatness discussed in SAM and its follow-ups are limited to the zeroth-order flatness (i.e., the worst-case loss within a perturbation radius). We show that the zeroth-order flatness can be insufficient to discriminate minima with low generalization error from those with high generalization error both when there is a single minimum or multiple minima within the given perturbation radius. Thus we present first-o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03108","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/2303.03108/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":"2303.03108","created_at":"2026-07-05T06:28:16.787125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03108v3","created_at":"2026-07-05T06:28:16.787125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03108","created_at":"2026-07-05T06:28:16.787125+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYTQSSBXYLCI","created_at":"2026-07-05T06:28:16.787125+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYTQSSBXYLCI6AX7","created_at":"2026-07-05T06:28:16.787125+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYTQSSBX","created_at":"2026-07-05T06:28:16.787125+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/YYTQSSBXYLCI6AX7TM2JMXKDMO","json":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO.json","graph_json":"https://pith.science/api/pith-number/YYTQSSBXYLCI6AX7TM2JMXKDMO/graph.json","events_json":"https://pith.science/api/pith-number/YYTQSSBXYLCI6AX7TM2JMXKDMO/events.json","paper":"https://pith.science/paper/YYTQSSBX"},"agent_actions":{"view_html":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO","download_json":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO.json","view_paper":"https://pith.science/paper/YYTQSSBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03108&json=true","fetch_graph":"https://pith.science/api/pith-number/YYTQSSBXYLCI6AX7TM2JMXKDMO/graph.json","fetch_events":"https://pith.science/api/pith-number/YYTQSSBXYLCI6AX7TM2JMXKDMO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO/action/storage_attestation","attest_author":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO/action/author_attestation","sign_citation":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO/action/citation_signature","submit_replication":"https://pith.science/pith/YYTQSSBXYLCI6AX7TM2JMXKDMO/action/replication_record"}},"created_at":"2026-07-05T06:28:16.787125+00:00","updated_at":"2026-07-05T06:28:16.787125+00:00"}