{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SAGL45HCVOC5WQHAO4TKU4HRL3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c87eb24eac2e2b094854c029e075aeceb8ec7c57b5714cc9b91f47f638687481","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T02:57:05Z","title_canon_sha256":"1fb93e5ce38c5074af2f99c3362460ae706d69138fb1e234a80fa99b181ed92f"},"schema_version":"1.0","source":{"id":"2210.03294","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03294","created_at":"2026-07-05T05:43:58Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03294v2","created_at":"2026-07-05T05:43:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03294","created_at":"2026-07-05T05:43:58Z"},{"alias_kind":"pith_short_12","alias_value":"SAGL45HCVOC5","created_at":"2026-07-05T05:43:58Z"},{"alias_kind":"pith_short_16","alias_value":"SAGL45HCVOC5WQHA","created_at":"2026-07-05T05:43:58Z"},{"alias_kind":"pith_short_8","alias_value":"SAGL45HC","created_at":"2026-07-05T05:43:58Z"}],"graph_snapshots":[{"event_id":"sha256:34e4af88692e56fed342dcfb5778df45598caaba2f2ab832f65cadbf64831775","target":"graph","created_at":"2026-07-05T05:43:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.03294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) is often larger than stability threshold $2/\\eta$ (where $\\eta$ is the step size). Despite this, the loss oscillates and converges in the long run, and the sharpness at the end is just slightly below $2/\\eta$. While many other well-understood nonconvex objectives such as matrix factorization or two-layer networks can also converge despite large sharpness, there is often a larger gap between sharpness of the endpoint a","authors_text":"Mo Zhou, Rong Ge, Xiang Wang, Xingyu Zhu, Zixuan Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T02:57:05Z","title":"Understanding Edge-of-Stability Training Dynamics with a Minimalist Example"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03294","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a314e654498743f881027f08c4739b0564e725461e4cad40bd075bb3a9c41e28","target":"record","created_at":"2026-07-05T05:43:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c87eb24eac2e2b094854c029e075aeceb8ec7c57b5714cc9b91f47f638687481","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T02:57:05Z","title_canon_sha256":"1fb93e5ce38c5074af2f99c3362460ae706d69138fb1e234a80fa99b181ed92f"},"schema_version":"1.0","source":{"id":"2210.03294","kind":"arxiv","version":2}},"canonical_sha256":"900cbe74e2ab85db40e07726aa70f15edd0404f44a0babc4bcd60aa729aa34be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"900cbe74e2ab85db40e07726aa70f15edd0404f44a0babc4bcd60aa729aa34be","first_computed_at":"2026-07-05T05:43:58.428703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:58.428703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5pzet+ooRUtaRh+JMCu+d+Qkt+DoZ1WKdKPoZJedLX1TWfsYprUjHc5JKiBNbt79twnmgU0smKa7bq4MfaybDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:58.429210Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03294","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a314e654498743f881027f08c4739b0564e725461e4cad40bd075bb3a9c41e28","sha256:34e4af88692e56fed342dcfb5778df45598caaba2f2ab832f65cadbf64831775"],"state_sha256":"f9d2fc66bcf85d04810024818d23e5ff224b359df99a8cb619e901fc47bf6fac"}