{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7COUNJA2VF2C4ARW4ERNUR3YBU","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":"505b473b018c923106d182d0bc8c316231d52585b1a4f393f5b7029f74e9035d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-05T05:44:22Z","title_canon_sha256":"aadbdf3859aadeee1f5c5ef3c8aee283e5877cc09b2861838f91cea02d462d21"},"schema_version":"1.0","source":{"id":"2502.02900","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02900","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02900v2","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02900","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_12","alias_value":"7COUNJA2VF2C","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_16","alias_value":"7COUNJA2VF2C4ARW","created_at":"2026-07-05T11:13:19Z"},{"alias_kind":"pith_short_8","alias_value":"7COUNJA2","created_at":"2026-07-05T11:13:19Z"}],"graph_snapshots":[{"event_id":"sha256:677f7be83ff6552a7bc7eb8189a02a91a729d00fe095e2f89ebb8b94f8a057c9","target":"graph","created_at":"2026-07-05T11:13:19Z","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/2502.02900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this note, we inspect the convergence of a new optimizer for pretraining LLMs, namely the Muon optimizer. Such an optimizer is closely related to a specialized steepest descent method where the update direction is the minimizer of the quadratic approximation of the objective function under spectral norm. We provide the convergence analysis on both versions of the optimizer and discuss its implications.","authors_text":"Jiaxiang Li, Mingyi Hong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-05T05:44:22Z","title":"A Note on the Convergence of Muon"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02900","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:a207201b7c39cd9ce74b96e28eb77b6eb9062feef2f42da4d9bfee3874a2d853","target":"record","created_at":"2026-07-05T11:13:19Z","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":"505b473b018c923106d182d0bc8c316231d52585b1a4f393f5b7029f74e9035d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2025-02-05T05:44:22Z","title_canon_sha256":"aadbdf3859aadeee1f5c5ef3c8aee283e5877cc09b2861838f91cea02d462d21"},"schema_version":"1.0","source":{"id":"2502.02900","kind":"arxiv","version":2}},"canonical_sha256":"f89d46a41aa9742e0236e122da47780d2ac3905ac77facad8e45cc2445e7d461","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f89d46a41aa9742e0236e122da47780d2ac3905ac77facad8e45cc2445e7d461","first_computed_at":"2026-07-05T11:13:19.814600Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:19.814600Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"elqLSLqQPulBBQ0Vbr86G9hj89KcCmG88BvUNi/AX2FyZm49nyU4y0CkALnj6F/VGp6zmqad7I5J8BPlTjwEBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:19.815072Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02900","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a207201b7c39cd9ce74b96e28eb77b6eb9062feef2f42da4d9bfee3874a2d853","sha256:677f7be83ff6552a7bc7eb8189a02a91a729d00fe095e2f89ebb8b94f8a057c9"],"state_sha256":"9fa107dce70366ae3b29337ca41b609d213d7ad4004f19cde69e79f2819bba90"}