{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RKW3AALILHZB6H6SCDC7M4OJAA","short_pith_number":"pith:RKW3AALI","schema_version":"1.0","canonical_sha256":"8aadb0016859f21f1fd210c5f671c9000ffede3b8588f8636e71fcf9269bfbf9","source":{"kind":"arxiv","id":"2605.16311","version":1},"attestation_state":"computed","paper":{"title":"SignMuon: Communication-Efficient Distributed Muon Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Kushagara Trivedi, Neel Mishra, Pawan Kumar","submitted_at":"2026-05-04T13:29:55Z","abstract_excerpt":"Distributed training of large neural networks is bottlenecked by full-precision gradient communication and by coordinatewise optimizers that ignore the matrix structure of weight tensors. We propose Sign-Muon, a 1-bit, matrix-aware optimizer that combines majority-vote sign aggregation from signSGD with the polar-step framework of Muon. Each worker forms a Muon-style direction by taking the polar factor of its momentum via a Newton--Schulz iteration, transmits only the entrywise signs, and aggregates by majority vote; an optional local polar step further enforces orthogonality at no extra comm"},"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":"2605.16311","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-04T13:29:55Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"f519488b4c52c0e5a8132e067102af1b253433c39632a86e80ba60da9310fddc","abstract_canon_sha256":"d36bdf7462efc67345b42996518f67b09be3eefff6c0c332fc0f082ce34e264d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:16.507999Z","signature_b64":"lBPlk0C0vT1cdHf9KTUINwEFYuX+AVwcMhyMPi1Q5n+weQOcCWH6km3Sc/wk3YJ1fsNs1QzixInE5nymvfTFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aadb0016859f21f1fd210c5f671c9000ffede3b8588f8636e71fcf9269bfbf9","last_reissued_at":"2026-05-20T00:02:16.507404Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:16.507404Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SignMuon: Communication-Efficient Distributed Muon Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Kushagara Trivedi, Neel Mishra, Pawan Kumar","submitted_at":"2026-05-04T13:29:55Z","abstract_excerpt":"Distributed training of large neural networks is bottlenecked by full-precision gradient communication and by coordinatewise optimizers that ignore the matrix structure of weight tensors. We propose Sign-Muon, a 1-bit, matrix-aware optimizer that combines majority-vote sign aggregation from signSGD with the polar-step framework of Muon. Each worker forms a Muon-style direction by taking the polar factor of its momentum via a Newton--Schulz iteration, transmits only the entrywise signs, and aggregates by majority vote; an optional local polar step further enforces orthogonality at no extra comm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16311","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/2605.16311/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":"2605.16311","created_at":"2026-05-20T00:02:16.507508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16311v1","created_at":"2026-05-20T00:02:16.507508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16311","created_at":"2026-05-20T00:02:16.507508+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKW3AALILHZB","created_at":"2026-05-20T00:02:16.507508+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKW3AALILHZB6H6S","created_at":"2026-05-20T00:02:16.507508+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKW3AALI","created_at":"2026-05-20T00:02:16.507508+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/RKW3AALILHZB6H6SCDC7M4OJAA","json":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA.json","graph_json":"https://pith.science/api/pith-number/RKW3AALILHZB6H6SCDC7M4OJAA/graph.json","events_json":"https://pith.science/api/pith-number/RKW3AALILHZB6H6SCDC7M4OJAA/events.json","paper":"https://pith.science/paper/RKW3AALI"},"agent_actions":{"view_html":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA","download_json":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA.json","view_paper":"https://pith.science/paper/RKW3AALI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16311&json=true","fetch_graph":"https://pith.science/api/pith-number/RKW3AALILHZB6H6SCDC7M4OJAA/graph.json","fetch_events":"https://pith.science/api/pith-number/RKW3AALILHZB6H6SCDC7M4OJAA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA/action/storage_attestation","attest_author":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA/action/author_attestation","sign_citation":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA/action/citation_signature","submit_replication":"https://pith.science/pith/RKW3AALILHZB6H6SCDC7M4OJAA/action/replication_record"}},"created_at":"2026-05-20T00:02:16.507508+00:00","updated_at":"2026-05-20T00:02:16.507508+00:00"}