{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AT4VBOJYJ7PLOPN7ANRDSPO55J","short_pith_number":"pith:AT4VBOJY","schema_version":"1.0","canonical_sha256":"04f950b9384fdeb73dbf0362393dddea42f418278470f6cae5695a4f5b8db4b0","source":{"kind":"arxiv","id":"2605.23871","version":1},"attestation_state":"computed","paper":{"title":"Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Aratrika Mustafi, Bharath K. Sriperumbudur, Soumya Mukherjee","submitted_at":"2026-05-22T17:28:53Z","abstract_excerpt":"We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized Muon optimizer. The key observation is that the regularized orthogonalization map is the gradient of a smooth Fenchel-dual smoothing of the nuclear norm. This identifies the (regularized) Muon update as a mirror/prox step in the update variable, with momentum acting as the dual coordinate. We use this structure to lift Muon from a single matrix parameter to finite-particle probability objectives of the form $J(\\rho)=R"},"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":"2605.23871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-22T17:28:53Z","cross_cats_sorted":["cs.LG","math.ST","stat.TH"],"title_canon_sha256":"a2a527bc0ca97ffe94709753e7d0645053d142dbffe98aaee2d4672483d7e869","abstract_canon_sha256":"95be6c0e279434cb8b618e8e73241792cb2aec36b1b2f55b718a02c5c175afef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:36.974925Z","signature_b64":"ZNKo3Y+5ZqfCSwuSmYh0Al76Qm59EtiMbUlSPnXyOdpZx76aTOtdvYvjv5pEuvg/u2dSMZvTTI/OvqKIq91qDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04f950b9384fdeb73dbf0362393dddea42f418278470f6cae5695a4f5b8db4b0","last_reissued_at":"2026-05-25T02:02:36.974156Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:36.974156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Aratrika Mustafi, Bharath K. Sriperumbudur, Soumya Mukherjee","submitted_at":"2026-05-22T17:28:53Z","abstract_excerpt":"We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized Muon optimizer. The key observation is that the regularized orthogonalization map is the gradient of a smooth Fenchel-dual smoothing of the nuclear norm. This identifies the (regularized) Muon update as a mirror/prox step in the update variable, with momentum acting as the dual coordinate. We use this structure to lift Muon from a single matrix parameter to finite-particle probability objectives of the form $J(\\rho)=R"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23871","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/2605.23871/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":"2605.23871","created_at":"2026-05-25T02:02:36.974283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.23871v1","created_at":"2026-05-25T02:02:36.974283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23871","created_at":"2026-05-25T02:02:36.974283+00:00"},{"alias_kind":"pith_short_12","alias_value":"AT4VBOJYJ7PL","created_at":"2026-05-25T02:02:36.974283+00:00"},{"alias_kind":"pith_short_16","alias_value":"AT4VBOJYJ7PLOPN7","created_at":"2026-05-25T02:02:36.974283+00:00"},{"alias_kind":"pith_short_8","alias_value":"AT4VBOJY","created_at":"2026-05-25T02:02:36.974283+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/AT4VBOJYJ7PLOPN7ANRDSPO55J","json":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J.json","graph_json":"https://pith.science/api/pith-number/AT4VBOJYJ7PLOPN7ANRDSPO55J/graph.json","events_json":"https://pith.science/api/pith-number/AT4VBOJYJ7PLOPN7ANRDSPO55J/events.json","paper":"https://pith.science/paper/AT4VBOJY"},"agent_actions":{"view_html":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J","download_json":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J.json","view_paper":"https://pith.science/paper/AT4VBOJY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.23871&json=true","fetch_graph":"https://pith.science/api/pith-number/AT4VBOJYJ7PLOPN7ANRDSPO55J/graph.json","fetch_events":"https://pith.science/api/pith-number/AT4VBOJYJ7PLOPN7ANRDSPO55J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J/action/storage_attestation","attest_author":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J/action/author_attestation","sign_citation":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J/action/citation_signature","submit_replication":"https://pith.science/pith/AT4VBOJYJ7PLOPN7ANRDSPO55J/action/replication_record"}},"created_at":"2026-05-25T02:02:36.974283+00:00","updated_at":"2026-05-25T02:02:36.974283+00:00"}