{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IO76NDOSRQS3E3TRMQGX2XPGZL","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":"02b325e3bc75c6c456e9e1a3bfcbb3d1a959685661c23e24c6d9f1d4089c003a","cross_cats_sorted":["cond-mat.dis-nn","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T22:49:41Z","title_canon_sha256":"2d066c3a186e7f8cb91216352e294910af87775c3f1f5be04f7eb00822e6d28e"},"schema_version":"1.0","source":{"id":"2006.06098","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06098","created_at":"2026-07-05T04:08:23Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06098v2","created_at":"2026-07-05T04:08:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06098","created_at":"2026-07-05T04:08:23Z"},{"alias_kind":"pith_short_12","alias_value":"IO76NDOSRQS3","created_at":"2026-07-05T04:08:23Z"},{"alias_kind":"pith_short_16","alias_value":"IO76NDOSRQS3E3TR","created_at":"2026-07-05T04:08:23Z"},{"alias_kind":"pith_short_8","alias_value":"IO76NDOS","created_at":"2026-07-05T04:08:23Z"}],"graph_snapshots":[{"event_id":"sha256:0906d974e7f079088b4c5d10576205ecd00c31fb04f67bb16d0f6a6079b9a27f","target":"graph","created_at":"2026-07-05T04:08:23Z","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/2006.06098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We analyze in a closed form the learning dynamics of stochastic gradient descent (SGD) for a single-layer neural network classifying a high-dimensional Gaussian mixture where each cluster is assigned one of two labels. This problem provides a prototype of a non-convex loss landscape with interpolating regimes and a large generalization gap. We define a particular stochastic process for which SGD can be extended to a continuous-time limit that we call stochastic gradient flow. In the full-batch limit, we recover the standard gradient flow. We apply dynamical mean-field theory from statistical p","authors_text":"Florent Krzakala, Francesca Mignacco, Lenka Zdeborov\\'a, Pierfrancesco Urbani","cross_cats":["cond-mat.dis-nn","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T22:49:41Z","title":"Dynamical mean-field theory for stochastic gradient descent in Gaussian mixture classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06098","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":"sha256:3746b4370bd88cb03c18b97cfe503f54a5406b78161f7fcaa0c14dbfbfc80975","target":"record","created_at":"2026-07-05T04:08:23Z","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":"02b325e3bc75c6c456e9e1a3bfcbb3d1a959685661c23e24c6d9f1d4089c003a","cross_cats_sorted":["cond-mat.dis-nn","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-10T22:49:41Z","title_canon_sha256":"2d066c3a186e7f8cb91216352e294910af87775c3f1f5be04f7eb00822e6d28e"},"schema_version":"1.0","source":{"id":"2006.06098","kind":"arxiv","version":2}},"canonical_sha256":"43bfe68dd28c25b26e71640d7d5de6cacde469fbfa41058d3bac7fc989f73c1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43bfe68dd28c25b26e71640d7d5de6cacde469fbfa41058d3bac7fc989f73c1a","first_computed_at":"2026-07-05T04:08:23.239451Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:23.239451Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OkT1tWjNyMlGmgibqVKHOmyFnO17zG1z3+jdb8YpDIykZaByzDbNJdC8/RfySc7Y9mPT8wd1ll0j4baTE5/dAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:23.239925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06098","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3746b4370bd88cb03c18b97cfe503f54a5406b78161f7fcaa0c14dbfbfc80975","sha256:0906d974e7f079088b4c5d10576205ecd00c31fb04f67bb16d0f6a6079b9a27f"],"state_sha256":"643b0ba0874c7f5590e200d373c769c351951a11f17d53e8bfcce00ab5b4a83a"}