{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:E4ZNFZQVBTGUSKYVPKMCGEFICT","short_pith_number":"pith:E4ZNFZQV","schema_version":"1.0","canonical_sha256":"2732d2e6150ccd492b157a982310a814f86b85ce16deb24ad06ccf0b533dcfd8","source":{"kind":"arxiv","id":"2605.16622","version":1},"attestation_state":"computed","paper":{"title":"Does Weight Decay Enhance Training Stability?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Kolic, Marius Saether, Pierfrancesco Beneventano, Tomaso Poggio","submitted_at":"2026-05-15T20:43:26Z","abstract_excerpt":"In modern deep learning, weight decay is often credited with \"stabilizing\" training dynamics, diverging from its classical role as a static regularization penalty. We investigate a fundamental question: *does weight decay stabilize training dynamics, and if so, through which mechanism?* Indeed, training stability is understood through different but related notions in the literature. We consider how weight decay affects the parameter-space dynamics and loss sharpness by analyzing its effects at the \\emph{Edge of Stability} (EoS). We show that weight decay robustly slows *progressive sharpening}"},"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":"2605.16622","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T20:43:26Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"8021afc3eb1e29944d0322684a62cc12263ae0bd48e793296e7563c5ea1b0436","abstract_canon_sha256":"d3ed7a2f572e7d00279ab8308fd4414d2d825930c753b08d62054c8f338f42e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:32.969672Z","signature_b64":"c4c3FyKacO96XLA5cT7/Kbdv1V5jjsayC5QAzlkMSXBQyyzQh4zFxh7Zr7ABdd3vEGDG2WM7WIJOZsCcM6sUAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2732d2e6150ccd492b157a982310a814f86b85ce16deb24ad06ccf0b533dcfd8","last_reissued_at":"2026-05-20T00:02:32.968810Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:32.968810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does Weight Decay Enhance Training Stability?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Kolic, Marius Saether, Pierfrancesco Beneventano, Tomaso Poggio","submitted_at":"2026-05-15T20:43:26Z","abstract_excerpt":"In modern deep learning, weight decay is often credited with \"stabilizing\" training dynamics, diverging from its classical role as a static regularization penalty. We investigate a fundamental question: *does weight decay stabilize training dynamics, and if so, through which mechanism?* Indeed, training stability is understood through different but related notions in the literature. We consider how weight decay affects the parameter-space dynamics and loss sharpness by analyzing its effects at the \\emph{Edge of Stability} (EoS). We show that weight decay robustly slows *progressive sharpening}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16622","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/2605.16622/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:21:56.766259Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.587110Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"67b2fd61e7f6e426725766ec034fdd1c6532aae3ac9078e86c564de739e55bc0"},"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":"2605.16622","created_at":"2026-05-20T00:02:32.968926+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16622v1","created_at":"2026-05-20T00:02:32.968926+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16622","created_at":"2026-05-20T00:02:32.968926+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4ZNFZQVBTGU","created_at":"2026-05-20T00:02:32.968926+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4ZNFZQVBTGUSKYV","created_at":"2026-05-20T00:02:32.968926+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4ZNFZQV","created_at":"2026-05-20T00:02:32.968926+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/E4ZNFZQVBTGUSKYVPKMCGEFICT","json":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT.json","graph_json":"https://pith.science/api/pith-number/E4ZNFZQVBTGUSKYVPKMCGEFICT/graph.json","events_json":"https://pith.science/api/pith-number/E4ZNFZQVBTGUSKYVPKMCGEFICT/events.json","paper":"https://pith.science/paper/E4ZNFZQV"},"agent_actions":{"view_html":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT","download_json":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT.json","view_paper":"https://pith.science/paper/E4ZNFZQV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16622&json=true","fetch_graph":"https://pith.science/api/pith-number/E4ZNFZQVBTGUSKYVPKMCGEFICT/graph.json","fetch_events":"https://pith.science/api/pith-number/E4ZNFZQVBTGUSKYVPKMCGEFICT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT/action/storage_attestation","attest_author":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT/action/author_attestation","sign_citation":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT/action/citation_signature","submit_replication":"https://pith.science/pith/E4ZNFZQVBTGUSKYVPKMCGEFICT/action/replication_record"}},"created_at":"2026-05-20T00:02:32.968926+00:00","updated_at":"2026-05-20T00:02:32.968926+00:00"}