{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2CCZWEKDIKOQJYNXPTBRNN35FN","short_pith_number":"pith:2CCZWEKD","schema_version":"1.0","canonical_sha256":"d0859b1143429d04e1b77cc316b77d2b5f7fc20418b07b45b79b646692c7c240","source":{"kind":"arxiv","id":"2608.11612","version":1},"attestation_state":"computed","paper":{"title":"Dion3: Full-Stack Orthogonal Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Naeimi, Austin Feng, Berlin Chen, Jack Zhang, John Langford, Kwangjun Ahn, Noah Amsel, Tri Dao","submitted_at":"2026-08-12T03:42:40Z","abstract_excerpt":"The Muon optimizer incurs a significant overhead cost due to its cubic-time Newton-Schulz orthogonalization step. When weights are sharded, communication overhead compounds this computational cost, eroding the benefits of Muon in many settings. We present Dion3, a revision of Muon that targets this overhead at every level of the stack. Our Gram Newton-Schulz algorithm reduces the FLOP cost of orthogonalization, our CuteDSL kernels accelerate it by exploiting symmetry, and our megabatching strategy reduces communication overhead. Moreover, we propose a simple change to the update rule that cuts"},"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":"2608.11612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T03:42:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"73f227a0c095785e75cbbf931ccc1fdae9256d17236397a69b71d18348446ad1","abstract_canon_sha256":"4f716cc9b287915dd058b2ce3d4852b0c437674794e40266d1724bb048f21992"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:22:18.608575Z","signature_b64":"3WIa0ikUxBFmZIP/Gc9mq3IYdaI3msm1C9UnXpneHNTigByOx2uSRWH5nLY1joDHTky49OKwD6asGH7GXEArAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0859b1143429d04e1b77cc316b77d2b5f7fc20418b07b45b79b646692c7c240","last_reissued_at":"2026-08-13T00:22:18.606673Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:22:18.606673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dion3: Full-Stack Orthogonal Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ali Naeimi, Austin Feng, Berlin Chen, Jack Zhang, John Langford, Kwangjun Ahn, Noah Amsel, Tri Dao","submitted_at":"2026-08-12T03:42:40Z","abstract_excerpt":"The Muon optimizer incurs a significant overhead cost due to its cubic-time Newton-Schulz orthogonalization step. When weights are sharded, communication overhead compounds this computational cost, eroding the benefits of Muon in many settings. We present Dion3, a revision of Muon that targets this overhead at every level of the stack. Our Gram Newton-Schulz algorithm reduces the FLOP cost of orthogonalization, our CuteDSL kernels accelerate it by exploiting symmetry, and our megabatching strategy reduces communication overhead. Moreover, we propose a simple change to the update rule that cuts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11612","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/2608.11612/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":"2608.11612","created_at":"2026-08-13T00:22:18.607155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.11612v1","created_at":"2026-08-13T00:22:18.607155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11612","created_at":"2026-08-13T00:22:18.607155+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CCZWEKDIKOQ","created_at":"2026-08-13T00:22:18.607155+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CCZWEKDIKOQJYNX","created_at":"2026-08-13T00:22:18.607155+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CCZWEKD","created_at":"2026-08-13T00:22:18.607155+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/2CCZWEKDIKOQJYNXPTBRNN35FN","json":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN.json","graph_json":"https://pith.science/api/pith-number/2CCZWEKDIKOQJYNXPTBRNN35FN/graph.json","events_json":"https://pith.science/api/pith-number/2CCZWEKDIKOQJYNXPTBRNN35FN/events.json","paper":"https://pith.science/paper/2CCZWEKD"},"agent_actions":{"view_html":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN","download_json":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN.json","view_paper":"https://pith.science/paper/2CCZWEKD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.11612&json=true","fetch_graph":"https://pith.science/api/pith-number/2CCZWEKDIKOQJYNXPTBRNN35FN/graph.json","fetch_events":"https://pith.science/api/pith-number/2CCZWEKDIKOQJYNXPTBRNN35FN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN/action/storage_attestation","attest_author":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN/action/author_attestation","sign_citation":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN/action/citation_signature","submit_replication":"https://pith.science/pith/2CCZWEKDIKOQJYNXPTBRNN35FN/action/replication_record"}},"created_at":"2026-08-13T00:22:18.607155+00:00","updated_at":"2026-08-13T00:22:18.607155+00:00"}