{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KUMWQOJIFRLUASJQD4XYXIAMDS","short_pith_number":"pith:KUMWQOJI","canonical_record":{"source":{"id":"2608.04607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-08-05T09:14:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6aa22c5695f6a4cb6339fd8c7c0a3eb3c6194c8d17219e981a1cc05300b496a","abstract_canon_sha256":"713f0af45a1b5587ab837e6b87fabfa56480d6a137d39e79dfb81e7a5553ba47"},"schema_version":"1.0"},"canonical_sha256":"55196839282c574049301f2f8ba00c1ca9d70951d8c9186c1081bc8b12af2d70","source":{"kind":"arxiv","id":"2608.04607","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04607","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04607v1","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04607","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"KUMWQOJIFRLU","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_16","alias_value":"KUMWQOJIFRLUASJQ","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_8","alias_value":"KUMWQOJI","created_at":"2026-08-06T01:36:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KUMWQOJIFRLUASJQD4XYXIAMDS","target":"record","payload":{"canonical_record":{"source":{"id":"2608.04607","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-08-05T09:14:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a6aa22c5695f6a4cb6339fd8c7c0a3eb3c6194c8d17219e981a1cc05300b496a","abstract_canon_sha256":"713f0af45a1b5587ab837e6b87fabfa56480d6a137d39e79dfb81e7a5553ba47"},"schema_version":"1.0"},"canonical_sha256":"55196839282c574049301f2f8ba00c1ca9d70951d8c9186c1081bc8b12af2d70","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:36:15.535547Z","signature_b64":"dVVGrYDgYevGSksRf6BhH0M7pWgnuzuYSr4wv5Cq/9s1tlb19y/nmLgqTe5g6OwiPoWngB+aGrpgrf1xAvfKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55196839282c574049301f2f8ba00c1ca9d70951d8c9186c1081bc8b12af2d70","last_reissued_at":"2026-08-06T01:36:15.534135Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:36:15.534135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.04607","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXJObuhV5IkdyFLGYufIPYXMUT4NOTjD+sJrwpHkqspe6kHYziycRIHuYkt/+rhZwk0IzRxjPCqgbEerLaVxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:42.593638Z"},"content_sha256":"8690d02af12436cd817f427692f8dd450f8cee89cec9021e453464c2cc79dfab","schema_version":"1.0","event_id":"sha256:8690d02af12436cd817f427692f8dd450f8cee89cec9021e453464c2cc79dfab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KUMWQOJIFRLUASJQD4XYXIAMDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Arnulf Jentzen, Steffen Dereich, Thang Do","submitted_at":"2026-08-05T09:14:22Z","abstract_excerpt":"Stochastic gradient descent (SGD) optimization methods are the standard instruments for the training of deep neural networks (DNNs). In many relevant artificial intelligence (AI) systems - such as popular large language models (LLMs)-not the standard SGD scheme is used as the optimization method but instead suitable accelerated variants of SGD are employed. One of the most popular methods of such accelerated SGD variants is the momentum orthogonalized by Newton-Schulz (MUON) optimizer proposed by Jordan et al. in 2024. The MUON optimizer exploits the special matrix structure of the weight para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04607","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/2608.04607/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-06T01:36:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fdf1B2j6rfB/e0EGcCKwBBYI+91+AxZq1J/HIiTzrolOSqvZrJ2akDXIuBhkEp65qTlOjgukcoyXqryy5jarBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:54:42.594432Z"},"content_sha256":"bbc137c4f84d52a0152b1c447def220faa0cfb4ec73af2c7595e13fcc8f81c99","schema_version":"1.0","event_id":"sha256:bbc137c4f84d52a0152b1c447def220faa0cfb4ec73af2c7595e13fcc8f81c99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/bundle.json","state_url":"https://pith.science/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T23:54:42Z","links":{"resolver":"https://pith.science/pith/KUMWQOJIFRLUASJQD4XYXIAMDS","bundle":"https://pith.science/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/bundle.json","state":"https://pith.science/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KUMWQOJIFRLUASJQD4XYXIAMDS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KUMWQOJIFRLUASJQD4XYXIAMDS","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":"713f0af45a1b5587ab837e6b87fabfa56480d6a137d39e79dfb81e7a5553ba47","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-08-05T09:14:22Z","title_canon_sha256":"a6aa22c5695f6a4cb6339fd8c7c0a3eb3c6194c8d17219e981a1cc05300b496a"},"schema_version":"1.0","source":{"id":"2608.04607","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.04607","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"arxiv_version","alias_value":"2608.04607v1","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04607","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_12","alias_value":"KUMWQOJIFRLU","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_16","alias_value":"KUMWQOJIFRLUASJQ","created_at":"2026-08-06T01:36:15Z"},{"alias_kind":"pith_short_8","alias_value":"KUMWQOJI","created_at":"2026-08-06T01:36:15Z"}],"graph_snapshots":[{"event_id":"sha256:bbc137c4f84d52a0152b1c447def220faa0cfb4ec73af2c7595e13fcc8f81c99","target":"graph","created_at":"2026-08-06T01:36:15Z","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/2608.04607/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stochastic gradient descent (SGD) optimization methods are the standard instruments for the training of deep neural networks (DNNs). In many relevant artificial intelligence (AI) systems - such as popular large language models (LLMs)-not the standard SGD scheme is used as the optimization method but instead suitable accelerated variants of SGD are employed. One of the most popular methods of such accelerated SGD variants is the momentum orthogonalized by Newton-Schulz (MUON) optimizer proposed by Jordan et al. in 2024. The MUON optimizer exploits the special matrix structure of the weight para","authors_text":"Arnulf Jentzen, Steffen Dereich, Thang Do","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-08-05T09:14:22Z","title":"On MUON optimization: From non-convergence to an error analysis with Polar Express and the Newton-Schulz polynomial from implementations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04607","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":"sha256:8690d02af12436cd817f427692f8dd450f8cee89cec9021e453464c2cc79dfab","target":"record","created_at":"2026-08-06T01:36:15Z","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":"713f0af45a1b5587ab837e6b87fabfa56480d6a137d39e79dfb81e7a5553ba47","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2026-08-05T09:14:22Z","title_canon_sha256":"a6aa22c5695f6a4cb6339fd8c7c0a3eb3c6194c8d17219e981a1cc05300b496a"},"schema_version":"1.0","source":{"id":"2608.04607","kind":"arxiv","version":1}},"canonical_sha256":"55196839282c574049301f2f8ba00c1ca9d70951d8c9186c1081bc8b12af2d70","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55196839282c574049301f2f8ba00c1ca9d70951d8c9186c1081bc8b12af2d70","first_computed_at":"2026-08-06T01:36:15.534135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-06T01:36:15.534135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dVVGrYDgYevGSksRf6BhH0M7pWgnuzuYSr4wv5Cq/9s1tlb19y/nmLgqTe5g6OwiPoWngB+aGrpgrf1xAvfKCg==","signature_status":"signed_v1","signed_at":"2026-08-06T01:36:15.535547Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.04607","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8690d02af12436cd817f427692f8dd450f8cee89cec9021e453464c2cc79dfab","sha256:bbc137c4f84d52a0152b1c447def220faa0cfb4ec73af2c7595e13fcc8f81c99"],"state_sha256":"094f180d4711db6b80e739bc1fd45f928c5bab4f370cf9bdee4e12bac6a9f7a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oIJR+dDSbRLVVfNXviGif6ZfNxiyh6nfpawx4JZ4CYd5g/uPph7MEz5m2edCIfAxsi1YK7MQ3ZACCsoEzgBlCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:54:42.600890Z","bundle_sha256":"3f022708193000e3d7ee30b3b25841d35f705ce7562e7703b95717960efcbaf9"}}