{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DKB7QKJR744JCJL2UBOTK3F6ZB","short_pith_number":"pith:DKB7QKJR","schema_version":"1.0","canonical_sha256":"1a83f82931ff3891257aa05d356cbec84c51aa593e588684ad57f0541af6a752","source":{"kind":"arxiv","id":"2206.04172","version":3},"attestation_state":"computed","paper":{"title":"Beyond the Edge of Stability via Two-step Gradient Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joan Bruna, Lei Chen","submitted_at":"2022-06-08T21:32:50Z","abstract_excerpt":"Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where it can be seen as a `bona-fide' discretisation of an underlying gradient flow. Yet, many ML setups involving overparametrised models do not fall into this problem class, which has motivated research beyond the so-called ``Edge of Stability'' (EoS), where the step-size crosses the admissibility threshold inversely proportional to the Lipschitz constant above"},"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":"2206.04172","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-08T21:32:50Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"b2d297842a737cd33fae9b05b79f9e3f3b9c5a9216c351b2daa75f6e2b32c54f","abstract_canon_sha256":"37bf311553f28bb25e15e9714c4515df4bc30d579b8b385aead6b018d5cddf71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:34:45.059123Z","signature_b64":"KIpp4z3l06YDE08koZKN1uzGIT4hCvvjhBM0zUNGAuygCIORPYAqtld5MqNKW9YfQ1X/pyPYRpxLuGH6BgvICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a83f82931ff3891257aa05d356cbec84c51aa593e588684ad57f0541af6a752","last_reissued_at":"2026-07-05T06:34:45.058580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:34:45.058580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond the Edge of Stability via Two-step Gradient Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Joan Bruna, Lei Chen","submitted_at":"2022-06-08T21:32:50Z","abstract_excerpt":"Gradient Descent (GD) is a powerful workhorse of modern machine learning thanks to its scalability and efficiency in high-dimensional spaces. Its ability to find local minimisers is only guaranteed for losses with Lipschitz gradients, where it can be seen as a `bona-fide' discretisation of an underlying gradient flow. Yet, many ML setups involving overparametrised models do not fall into this problem class, which has motivated research beyond the so-called ``Edge of Stability'' (EoS), where the step-size crosses the admissibility threshold inversely proportional to the Lipschitz constant above"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04172","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/2206.04172/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":"2206.04172","created_at":"2026-07-05T06:34:45.058641+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04172v3","created_at":"2026-07-05T06:34:45.058641+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04172","created_at":"2026-07-05T06:34:45.058641+00:00"},{"alias_kind":"pith_short_12","alias_value":"DKB7QKJR744J","created_at":"2026-07-05T06:34:45.058641+00:00"},{"alias_kind":"pith_short_16","alias_value":"DKB7QKJR744JCJL2","created_at":"2026-07-05T06:34:45.058641+00:00"},{"alias_kind":"pith_short_8","alias_value":"DKB7QKJR","created_at":"2026-07-05T06:34:45.058641+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21016","citing_title":"SGD at the Edge of Stability: The Stochastic Sharpness Gap","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB","json":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB.json","graph_json":"https://pith.science/api/pith-number/DKB7QKJR744JCJL2UBOTK3F6ZB/graph.json","events_json":"https://pith.science/api/pith-number/DKB7QKJR744JCJL2UBOTK3F6ZB/events.json","paper":"https://pith.science/paper/DKB7QKJR"},"agent_actions":{"view_html":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB","download_json":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB.json","view_paper":"https://pith.science/paper/DKB7QKJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04172&json=true","fetch_graph":"https://pith.science/api/pith-number/DKB7QKJR744JCJL2UBOTK3F6ZB/graph.json","fetch_events":"https://pith.science/api/pith-number/DKB7QKJR744JCJL2UBOTK3F6ZB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB/action/storage_attestation","attest_author":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB/action/author_attestation","sign_citation":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB/action/citation_signature","submit_replication":"https://pith.science/pith/DKB7QKJR744JCJL2UBOTK3F6ZB/action/replication_record"}},"created_at":"2026-07-05T06:34:45.058641+00:00","updated_at":"2026-07-05T06:34:45.058641+00:00"}