{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:NG4GK6DRXK66GW5ZCFDQBZHQVL","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":"c1c7ff66b1d8a27606f3dfb1a7ad217b7ac691f4ce71dad95ed7d56441dede55","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-16T22:26:59Z","title_canon_sha256":"93aa799febde20690066354a2c0a4ec758b3eea0f6bdf57753bc2b54149b6738"},"schema_version":"1.0","source":{"id":"2605.17177","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17177","created_at":"2026-05-20T00:03:43Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17177v1","created_at":"2026-05-20T00:03:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17177","created_at":"2026-05-20T00:03:43Z"},{"alias_kind":"pith_short_12","alias_value":"NG4GK6DRXK66","created_at":"2026-05-20T00:03:43Z"},{"alias_kind":"pith_short_16","alias_value":"NG4GK6DRXK66GW5Z","created_at":"2026-05-20T00:03:43Z"},{"alias_kind":"pith_short_8","alias_value":"NG4GK6DR","created_at":"2026-05-20T00:03:43Z"}],"graph_snapshots":[{"event_id":"sha256:72b6e4dbd1cf6854b55b75aef83fa62690255ee8df58dd28568ba6f90d5e872a","target":"graph","created_at":"2026-05-20T00:03:43Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.749452Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T22:01:57.971548Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17177/integrity.json","findings":[],"snapshot_sha256":"35ac3527e6de1df4496d0d61bd9816c3d1afe0adbfc2e5f4d922384813eade77","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the behavior of stochastic gradient methods is a central problem in modern machine learning. Recent work has highlighted diagonal linear networks as a simplified yet expressive setting for analyzing the optimization and generalization properties of neural models. In this work, we show that in the high-dimensional regime, stochastic gradient descent on diagonal linear networks is well-approximated by continuous dynamics governed by a stochastic differential equation (SDE), which explicitly decouples the drift from the gradient noise. We further derive a deterministic partial diffe","authors_text":"Bego\\~na Garc\\'ia Malaxechebarr\\'ia, Courtney Paquette, Dmitriy Drusvyatskiy, Maryam Fazel","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-16T22:26:59Z","title":"High-dimensional Limit of SGD for Diagonal Linear Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17177","kind":"arxiv","version":1},"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:f42e949168777c442dc973e87cd121b11f7a82537e47610f4aa26ac4cb5aa37e","target":"record","created_at":"2026-05-20T00:03:43Z","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":"c1c7ff66b1d8a27606f3dfb1a7ad217b7ac691f4ce71dad95ed7d56441dede55","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-05-16T22:26:59Z","title_canon_sha256":"93aa799febde20690066354a2c0a4ec758b3eea0f6bdf57753bc2b54149b6738"},"schema_version":"1.0","source":{"id":"2605.17177","kind":"arxiv","version":1}},"canonical_sha256":"69b8657871babde35bb9114700e4f0aae198fac140dd54e3d3c7bbb0298cd9d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"69b8657871babde35bb9114700e4f0aae198fac140dd54e3d3c7bbb0298cd9d5","first_computed_at":"2026-05-20T00:03:43.550125Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:03:43.550125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2iGt4D4LKu4ddPeUhE2rvzjJMNbc9UQapJQs0WrMuolY7Vu9Kg/p/E7jeMHVqo46YbQv1gsr48HcptH++2V2Bg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:03:43.551028Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17177","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f42e949168777c442dc973e87cd121b11f7a82537e47610f4aa26ac4cb5aa37e","sha256:72b6e4dbd1cf6854b55b75aef83fa62690255ee8df58dd28568ba6f90d5e872a"],"state_sha256":"425ebee47f1fe7aa85b859b0b236c6680333a92192a446a9dea0d202a89e6e30"}