{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2CCZWEKDIKOQJYNXPTBRNN35FN","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":"4f716cc9b287915dd058b2ce3d4852b0c437674794e40266d1724bb048f21992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T03:42:40Z","title_canon_sha256":"73f227a0c095785e75cbbf931ccc1fdae9256d17236397a69b71d18348446ad1"},"schema_version":"1.0","source":{"id":"2608.11612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11612","created_at":"2026-08-13T00:22:18Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11612v1","created_at":"2026-08-13T00:22:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11612","created_at":"2026-08-13T00:22:18Z"},{"alias_kind":"pith_short_12","alias_value":"2CCZWEKDIKOQ","created_at":"2026-08-13T00:22:18Z"},{"alias_kind":"pith_short_16","alias_value":"2CCZWEKDIKOQJYNX","created_at":"2026-08-13T00:22:18Z"},{"alias_kind":"pith_short_8","alias_value":"2CCZWEKD","created_at":"2026-08-13T00:22:18Z"}],"graph_snapshots":[{"event_id":"sha256:34637a9c8e52b43309b0b98ed07eb8021df4b44cd050de7e85dc8755bc1a351f","target":"graph","created_at":"2026-08-13T00:22:18Z","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/2608.11612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Ali Naeimi, Austin Feng, Berlin Chen, Jack Zhang, John Langford, Kwangjun Ahn, Noah Amsel, Tri Dao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T03:42:40Z","title":"Dion3: Full-Stack Orthogonal Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11612","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":"sha256:7f8a11ed6f6df8897c8a338a035cb1514205222b62e8f6fed058903a20e90506","target":"record","created_at":"2026-08-13T00:22:18Z","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":"4f716cc9b287915dd058b2ce3d4852b0c437674794e40266d1724bb048f21992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T03:42:40Z","title_canon_sha256":"73f227a0c095785e75cbbf931ccc1fdae9256d17236397a69b71d18348446ad1"},"schema_version":"1.0","source":{"id":"2608.11612","kind":"arxiv","version":1}},"canonical_sha256":"d0859b1143429d04e1b77cc316b77d2b5f7fc20418b07b45b79b646692c7c240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0859b1143429d04e1b77cc316b77d2b5f7fc20418b07b45b79b646692c7c240","first_computed_at":"2026-08-13T00:22:18.606673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:22:18.606673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3WIa0ikUxBFmZIP/Gc9mq3IYdaI3msm1C9UnXpneHNTigByOx2uSRWH5nLY1joDHTky49OKwD6asGH7GXEArAw==","signature_status":"signed_v1","signed_at":"2026-08-13T00:22:18.608575Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f8a11ed6f6df8897c8a338a035cb1514205222b62e8f6fed058903a20e90506","sha256:34637a9c8e52b43309b0b98ed07eb8021df4b44cd050de7e85dc8755bc1a351f"],"state_sha256":"919c16488657b9c931d52a0a058410f3dd613ffc22e9cbcf33ee4e692685aada"}