{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7N54CBHLGHZADONA7Z2AH5GM3T","short_pith_number":"pith:7N54CBHL","schema_version":"1.0","canonical_sha256":"fb7bc104eb31f201b9a0fe7403f4ccdcd457e158251370a57412b01eadd9a788","source":{"kind":"arxiv","id":"2605.26842","version":1},"attestation_state":"computed","paper":{"title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongtao Xu, Jiacheng Li, Jianchao Tan, Jiaqi Zhang, Xunliang Cai, Yerui Sun, Yifan Lu, Yuchen Xie","submitted_at":"2026-05-26T10:56:20Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.26842","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T10:56:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f93bf49e40aa88f37bfa3d47623b6105fc5ac7ed10115e4f238be8bc90df93d5","abstract_canon_sha256":"a4979d517012084d18680572f1a8c7ffeaf4eacfc9049d6cb4ea8244c2067a8b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:15.238917Z","signature_b64":"XsH90F1ZEHcloJwhJzkMSEJdaNJTlyKLyw24vq4Bx7aFhOhPt5+r1aC/3OEYx2mXgaClDKT/EDyZlYzh7uFFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb7bc104eb31f201b9a0fe7403f4ccdcd457e158251370a57412b01eadd9a788","last_reissued_at":"2026-05-27T01:06:15.238155Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:15.238155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hongtao Xu, Jiacheng Li, Jianchao Tan, Jiaqi Zhang, Xunliang Cai, Yerui Sun, Yifan Lu, Yuchen Xie","submitted_at":"2026-05-26T10:56:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26842","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26842/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.26842","created_at":"2026-05-27T01:06:15.238267+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26842v1","created_at":"2026-05-27T01:06:15.238267+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26842","created_at":"2026-05-27T01:06:15.238267+00:00"},{"alias_kind":"pith_short_12","alias_value":"7N54CBHLGHZA","created_at":"2026-05-27T01:06:15.238267+00:00"},{"alias_kind":"pith_short_16","alias_value":"7N54CBHLGHZADONA","created_at":"2026-05-27T01:06:15.238267+00:00"},{"alias_kind":"pith_short_8","alias_value":"7N54CBHL","created_at":"2026-05-27T01:06:15.238267+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T","json":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T.json","graph_json":"https://pith.science/api/pith-number/7N54CBHLGHZADONA7Z2AH5GM3T/graph.json","events_json":"https://pith.science/api/pith-number/7N54CBHLGHZADONA7Z2AH5GM3T/events.json","paper":"https://pith.science/paper/7N54CBHL"},"agent_actions":{"view_html":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T","download_json":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T.json","view_paper":"https://pith.science/paper/7N54CBHL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26842&json=true","fetch_graph":"https://pith.science/api/pith-number/7N54CBHLGHZADONA7Z2AH5GM3T/graph.json","fetch_events":"https://pith.science/api/pith-number/7N54CBHLGHZADONA7Z2AH5GM3T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T/action/storage_attestation","attest_author":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T/action/author_attestation","sign_citation":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T/action/citation_signature","submit_replication":"https://pith.science/pith/7N54CBHLGHZADONA7Z2AH5GM3T/action/replication_record"}},"created_at":"2026-05-27T01:06:15.238267+00:00","updated_at":"2026-05-27T01:06:15.238267+00:00"}