{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6KV3STARSKM2X2SLZFDLVAVBFA","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":"302c147a54872ff42186bba3d3947721f26135a3ed09ae5c80e17bb901a94d04","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T03:42:22Z","title_canon_sha256":"019abf23ef097615c832d773cb54563e213029b0d97d202ad9c6199f2174ead5"},"schema_version":"1.0","source":{"id":"2509.02981","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02981","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02981v2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02981","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_12","alias_value":"6KV3STARSKM2","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_16","alias_value":"6KV3STARSKM2X2SL","created_at":"2026-07-05T12:06:20Z"},{"alias_kind":"pith_short_8","alias_value":"6KV3STAR","created_at":"2026-07-05T12:06:20Z"}],"graph_snapshots":[{"event_id":"sha256:317d8de8b0ca54e8fc73ba1af4aa1461a6275bc716b93acd3b5f66625373b930","target":"graph","created_at":"2026-07-05T12:06:20Z","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/2509.02981/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently proposed Muon optimizer updates weight matrices via orthogonalized momentum and has demonstrated strong empirical success in large language model training. However, it remains unclear how to determine the learning rates for such orthogonalized updates. AdaGrad, by contrast, is a widely used adaptive method that scales stochastic gradients by accumulated past gradients. We propose a new algorithm, AdaGO, which combines a norm-based AdaGrad-type stepsize with an orthogonalized update direction, bringing together the benefits of both approaches. Unlike other adaptive variants of Muon","authors_text":"Hayden Schaeffer, Minxin Zhang, Yuxuan Liu","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T03:42:22Z","title":"AdaGrad Meets Muon: Adaptive Stepsizes for Orthogonal Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02981","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:a1dcb0622c3db7db406b25a0f0765e8c043441a57bfabfe29a903a128906cda1","target":"record","created_at":"2026-07-05T12:06:20Z","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":"302c147a54872ff42186bba3d3947721f26135a3ed09ae5c80e17bb901a94d04","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-03T03:42:22Z","title_canon_sha256":"019abf23ef097615c832d773cb54563e213029b0d97d202ad9c6199f2174ead5"},"schema_version":"1.0","source":{"id":"2509.02981","kind":"arxiv","version":2}},"canonical_sha256":"f2abb94c119299abea4bc946ba82a12808c85e8f985ae0e49fe59c815b3f6d14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2abb94c119299abea4bc946ba82a12808c85e8f985ae0e49fe59c815b3f6d14","first_computed_at":"2026-07-05T12:06:20.026263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:20.026263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+Qf9ILr9IJeR2YdzvH0SYFV6OHc8lgqiNx+gxsG4T7P1ddPs+bJSr8u+PqayNVIpcUYri+uEGWaglwQyhvJhCg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:20.026793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02981","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1dcb0622c3db7db406b25a0f0765e8c043441a57bfabfe29a903a128906cda1","sha256:317d8de8b0ca54e8fc73ba1af4aa1461a6275bc716b93acd3b5f66625373b930"],"state_sha256":"0dad8c35c97770dfdc996beff10c48b0b68cc3d54b7e9fad264261d1ae251a3d"}