{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CCU6BTQWUHJ4NNUWBN6MXGXRVD","short_pith_number":"pith:CCU6BTQW","canonical_record":{"source":{"id":"2505.23725","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"0a11aafd19bbcda014f782f5cb47851b237835b4c03d40763a999f54ecccf550","abstract_canon_sha256":"41fda863e203c38591fd51ace09a84c393a73e4f0ffee1b48712f0b3ac371d89"},"schema_version":"1.0"},"canonical_sha256":"10a9e0ce16a1d3c6b6960b7ccb9af1a8d5aa8ef792845d22546a73ba524bb63b","source":{"kind":"arxiv","id":"2505.23725","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23725","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23725v3","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23725","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"CCU6BTQWUHJ4","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"CCU6BTQWUHJ4NNUW","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"CCU6BTQW","created_at":"2026-06-03T01:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CCU6BTQWUHJ4NNUWBN6MXGXRVD","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23725","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"0a11aafd19bbcda014f782f5cb47851b237835b4c03d40763a999f54ecccf550","abstract_canon_sha256":"41fda863e203c38591fd51ace09a84c393a73e4f0ffee1b48712f0b3ac371d89"},"schema_version":"1.0"},"canonical_sha256":"10a9e0ce16a1d3c6b6960b7ccb9af1a8d5aa8ef792845d22546a73ba524bb63b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:04.558322Z","signature_b64":"OyyazROtnYXcdlS8SPUvRSjehbpaxa9wcZml2ZqGFKx02Nrd4SgB1BOVtXyPoUTaR4A0VVHoPtgN9HVyGy1eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10a9e0ce16a1d3c6b6960b7ccb9af1a8d5aa8ef792845d22546a73ba524bb63b","last_reissued_at":"2026-06-03T01:05:04.557791Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:04.557791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23725","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-03T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZHaRIied0PtUUgC3ZnhtqQjVdPCOuzUoA5WrsEJ/hPYOGGsbvacae/g0cv+9b69i8r+aw1dlqHo6mA7xxjKkAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:34:54.117712Z"},"content_sha256":"6b5eaaac1dedf71c1c588e4d310e88ad7ccaebbfb4e462238037360bc5ba5e85","schema_version":"1.0","event_id":"sha256:6b5eaaac1dedf71c1c588e4d310e88ad7ccaebbfb4e462238037360bc5ba5e85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CCU6BTQWUHJ4NNUWBN6MXGXRVD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Defazio, Benjamin Th\\'erien, Eugene Belilovsky, Irina Rish, Xiaolong Huang","submitted_at":"2025-05-29T17:55:37Z","abstract_excerpt":"DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints. However, DiLoCo's performance has been shown to degrade as the number of workers (K) increases (Charles et al., 2025). In this work, we posit that a related but often overlooked factor in DiLoCo's behavior is the choice of inner optimizer, which shapes the pseudogradient used by the outer optimizer. Given the recent success of Muon relative to AdamW for data parallel (DP) training, we examine how Muon's normalized opti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23725","kind":"arxiv","version":3},"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/2505.23725/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":"2026-06-03T01:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5R999M5BEYXGJessTMRyxpylKO4Rq3GJHjApSyaCOregt3dxt8FbrPn9v8+jGbnG6FZIFYTOt4i1wUHIskoBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T20:34:54.118455Z"},"content_sha256":"f9e1d2281602bd09f5b7463e99aeb47bdef96f028dfa1536187cf46020d88056","schema_version":"1.0","event_id":"sha256:f9e1d2281602bd09f5b7463e99aeb47bdef96f028dfa1536187cf46020d88056"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/bundle.json","state_url":"https://pith.science/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/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":"2026-06-05T20:34:54Z","links":{"resolver":"https://pith.science/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD","bundle":"https://pith.science/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/bundle.json","state":"https://pith.science/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CCU6BTQWUHJ4NNUWBN6MXGXRVD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CCU6BTQWUHJ4NNUWBN6MXGXRVD","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":"41fda863e203c38591fd51ace09a84c393a73e4f0ffee1b48712f0b3ac371d89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:55:37Z","title_canon_sha256":"0a11aafd19bbcda014f782f5cb47851b237835b4c03d40763a999f54ecccf550"},"schema_version":"1.0","source":{"id":"2505.23725","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23725","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23725v3","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23725","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"CCU6BTQWUHJ4","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"CCU6BTQWUHJ4NNUW","created_at":"2026-06-03T01:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"CCU6BTQW","created_at":"2026-06-03T01:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:f9e1d2281602bd09f5b7463e99aeb47bdef96f028dfa1536187cf46020d88056","target":"graph","created_at":"2026-06-03T01:05:04Z","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/2505.23725/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"DiLoCo is a powerful framework for training large language models (LLMs), enabling larger optimal batch sizes and increased accelerator utilization under networking constraints. However, DiLoCo's performance has been shown to degrade as the number of workers (K) increases (Charles et al., 2025). In this work, we posit that a related but often overlooked factor in DiLoCo's behavior is the choice of inner optimizer, which shapes the pseudogradient used by the outer optimizer. Given the recent success of Muon relative to AdamW for data parallel (DP) training, we examine how Muon's normalized opti","authors_text":"Aaron Defazio, Benjamin Th\\'erien, Eugene Belilovsky, Irina Rish, Xiaolong Huang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:55:37Z","title":"MuLoCo: Muon is a practical inner optimizer for DiLoCo"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23725","kind":"arxiv","version":3},"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":"sha256:6b5eaaac1dedf71c1c588e4d310e88ad7ccaebbfb4e462238037360bc5ba5e85","target":"record","created_at":"2026-06-03T01:05:04Z","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":"41fda863e203c38591fd51ace09a84c393a73e4f0ffee1b48712f0b3ac371d89","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-29T17:55:37Z","title_canon_sha256":"0a11aafd19bbcda014f782f5cb47851b237835b4c03d40763a999f54ecccf550"},"schema_version":"1.0","source":{"id":"2505.23725","kind":"arxiv","version":3}},"canonical_sha256":"10a9e0ce16a1d3c6b6960b7ccb9af1a8d5aa8ef792845d22546a73ba524bb63b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10a9e0ce16a1d3c6b6960b7ccb9af1a8d5aa8ef792845d22546a73ba524bb63b","first_computed_at":"2026-06-03T01:05:04.557791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:04.557791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OyyazROtnYXcdlS8SPUvRSjehbpaxa9wcZml2ZqGFKx02Nrd4SgB1BOVtXyPoUTaR4A0VVHoPtgN9HVyGy1eDw==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:04.558322Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23725","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b5eaaac1dedf71c1c588e4d310e88ad7ccaebbfb4e462238037360bc5ba5e85","sha256:f9e1d2281602bd09f5b7463e99aeb47bdef96f028dfa1536187cf46020d88056"],"state_sha256":"4591b62a7eaebec131571a685c276b141dfb010525ca972a9e298b9a73feb5b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ziAjdotr944HdXK+oQQ+Z5q5jdMP4FxSxcyCNkDMRIMvdtGHBaeoKeGHSDgnrC2r59r3aepTOdNSYj2i4rfpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T20:34:54.122623Z","bundle_sha256":"98a4fe24b286d72c0ce804808e833911cce3e81a26cc0156e99afd0a370bc708"}}