{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PE3UR3JGKEJGTXWLXGERQBT5F4","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":"0f39bbf2e50a3629d5fafc92400a647202fc5430ae0c86e0c2ec62bddd6846b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T17:04:43Z","title_canon_sha256":"3dc616e8fe833ca0755abf3523a73aa070f0397afffef32107c3035770287096"},"schema_version":"1.0","source":{"id":"2608.02502","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02502","created_at":"2026-08-04T02:43:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02502v1","created_at":"2026-08-04T02:43:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02502","created_at":"2026-08-04T02:43:50Z"},{"alias_kind":"pith_short_12","alias_value":"PE3UR3JGKEJG","created_at":"2026-08-04T02:43:50Z"},{"alias_kind":"pith_short_16","alias_value":"PE3UR3JGKEJGTXWL","created_at":"2026-08-04T02:43:50Z"},{"alias_kind":"pith_short_8","alias_value":"PE3UR3JG","created_at":"2026-08-04T02:43:50Z"}],"graph_snapshots":[{"event_id":"sha256:bea24f96622caad206458f49f6492722de596fce990875de038a177c7b7c79e3","target":"graph","created_at":"2026-08-04T02:43:50Z","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/2608.02502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) performance in visual generative modeling, yet their training remains computationally prohibitive. While the recently proposed Momentum Orthogonalization (Muon) optimizer offers a promising alternative to AdamW, its direct application to DiTs yields suboptimal late-stage convergence. In this paper, we identify the root cause of this bottleneck: standard DiT architectures fuse functionally distinct weights (e.g., within AdaLN and QKV layers) into unified tensors for computational efficiency. Applying Muon to these fused tensors","authors_text":"Chuyan Chen, Kun Yuan, Peng Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T17:04:43Z","title":"CMuon: Accelerating and Stabilizing Diffusion Transformer Training via Chunked Momentum Orthogonalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02502","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":"sha256:567d7655004e98a4746e1543ff2d0cf6b2831d10553a0ac7d915756aa5b8b518","target":"record","created_at":"2026-08-04T02:43:50Z","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":"0f39bbf2e50a3629d5fafc92400a647202fc5430ae0c86e0c2ec62bddd6846b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T17:04:43Z","title_canon_sha256":"3dc616e8fe833ca0755abf3523a73aa070f0397afffef32107c3035770287096"},"schema_version":"1.0","source":{"id":"2608.02502","kind":"arxiv","version":1}},"canonical_sha256":"793748ed26511269decbb98918067d2f29c1e55280af641db87a79551f11783d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"793748ed26511269decbb98918067d2f29c1e55280af641db87a79551f11783d","first_computed_at":"2026-08-04T02:43:50.724748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:43:50.724748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PS/lHjbmHvGFNGmhTynNVVfeXQoGe6v4XVQOj/VWHsfpTbnCBF0PqgXtGxmbEf/nif/6Ab0pDdbkVsSeT6IiAA==","signature_status":"signed_v1","signed_at":"2026-08-04T02:43:50.726972Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02502","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:567d7655004e98a4746e1543ff2d0cf6b2831d10553a0ac7d915756aa5b8b518","sha256:bea24f96622caad206458f49f6492722de596fce990875de038a177c7b7c79e3"],"state_sha256":"ad76ede943413db0796ea6ce726b4a833403de6f5d66a07b9911b6d36d6af58b"}