{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7N54CBHLGHZADONA7Z2AH5GM3T","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":"a4979d517012084d18680572f1a8c7ffeaf4eacfc9049d6cb4ea8244c2067a8b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:20Z","title_canon_sha256":"f93bf49e40aa88f37bfa3d47623b6105fc5ac7ed10115e4f238be8bc90df93d5"},"schema_version":"1.0","source":{"id":"2605.26842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26842","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26842v1","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26842","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_12","alias_value":"7N54CBHLGHZA","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_16","alias_value":"7N54CBHLGHZADONA","created_at":"2026-05-27T01:06:15Z"},{"alias_kind":"pith_short_8","alias_value":"7N54CBHL","created_at":"2026-05-27T01:06:15Z"}],"graph_snapshots":[{"event_id":"sha256:a9b4e47e0f4b3747ed505f5a19023cbb926abbfcb7c0b7c11bdf049dc656d719","target":"graph","created_at":"2026-05-27T01:06:15Z","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/2605.26842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Muon optimizer has recently offered a promising alternative to AdamW for large language model training, leveraging matrix orthogonalization to produce geometry-aware updates. However, like all first-order methods, Muon can become trapped in sharp local minima. In this work, we present MONA, an optimizer that bridges Muon's orthogonalization framework with curvature-aware acceleration. MONA adds an acceleration term directly into Muon's gradient processing pipeline. This term is calculated from the exponential moving average of gradient differences. We provide a detailed convergence analysi","authors_text":"Hongtao Xu, Jiacheng Li, Jianchao Tan, Jiaqi Zhang, Xunliang Cai, Yerui Sun, Yifan Lu, Yuchen Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:20Z","title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26842","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":"sha256:64a7f0d51108e09b28323bd4197e3831fa8f805be3291e8c20f7aea318cb1846","target":"record","created_at":"2026-05-27T01:06:15Z","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":"a4979d517012084d18680572f1a8c7ffeaf4eacfc9049d6cb4ea8244c2067a8b","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:20Z","title_canon_sha256":"f93bf49e40aa88f37bfa3d47623b6105fc5ac7ed10115e4f238be8bc90df93d5"},"schema_version":"1.0","source":{"id":"2605.26842","kind":"arxiv","version":1}},"canonical_sha256":"fb7bc104eb31f201b9a0fe7403f4ccdcd457e158251370a57412b01eadd9a788","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb7bc104eb31f201b9a0fe7403f4ccdcd457e158251370a57412b01eadd9a788","first_computed_at":"2026-05-27T01:06:15.238155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:06:15.238155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XsH90F1ZEHcloJwhJzkMSEJdaNJTlyKLyw24vq4Bx7aFhOhPt5+r1aC/3OEYx2mXgaClDKT/EDyZlYzh7uFFAg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:06:15.238917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64a7f0d51108e09b28323bd4197e3831fa8f805be3291e8c20f7aea318cb1846","sha256:a9b4e47e0f4b3747ed505f5a19023cbb926abbfcb7c0b7c11bdf049dc656d719"],"state_sha256":"1cc4a40954d62b8f74519f7b779e12290cf4af045b1e103ce40ddd6ed074ed93"}