{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SGZ57SD7DMJTLISNYY2HWNLQPH","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":"37d11004505631b77cc250a6199ce6703c1a80c9b891ff52097619bdf6e43a78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T23:01:31Z","title_canon_sha256":"a0f5d050bb1fe9b5a2e2d8bf318427798fa48e8d52be52190c0fbfb4d109af70"},"schema_version":"1.0","source":{"id":"2502.20586","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.20586","created_at":"2026-07-05T11:59:57Z"},{"alias_kind":"arxiv_version","alias_value":"2502.20586v3","created_at":"2026-07-05T11:59:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20586","created_at":"2026-07-05T11:59:57Z"},{"alias_kind":"pith_short_12","alias_value":"SGZ57SD7DMJT","created_at":"2026-07-05T11:59:57Z"},{"alias_kind":"pith_short_16","alias_value":"SGZ57SD7DMJTLISN","created_at":"2026-07-05T11:59:57Z"},{"alias_kind":"pith_short_8","alias_value":"SGZ57SD7","created_at":"2026-07-05T11:59:57Z"}],"graph_snapshots":[{"event_id":"sha256:2c29efb01b633d3abcb141fafb6467a44da7efc3ce15da42d67140d48d143bb5","target":"graph","created_at":"2026-07-05T11:59:57Z","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/2502.20586/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Low precision (LP) datatypes such as MXFP4 can accelerate matrix multiplications (GEMMs) and reduce training costs. However, directly using MXFP4 instead of BF16 during training significantly degrades model quality. In this work, we present the first near-lossless training recipe that uses MXFP4 GEMMs, which are $2\\times$ faster than FP8 on supported hardware. Our key insight is to compute unbiased gradient estimates with stochastic rounding (SR), resulting in more accurate model updates. However, directly applying SR to MXFP4 can result in high variance from block-level outliers, harming conv","authors_text":"Albert Tseng, Tao Yu, Youngsuk Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T23:01:31Z","title":"Training LLMs with MXFP4"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20586","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:bb0199e1dcd83530789d2aac00b2f7c67e8d1df6624782792cb2a474cd944dfb","target":"record","created_at":"2026-07-05T11:59:57Z","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":"37d11004505631b77cc250a6199ce6703c1a80c9b891ff52097619bdf6e43a78","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-27T23:01:31Z","title_canon_sha256":"a0f5d050bb1fe9b5a2e2d8bf318427798fa48e8d52be52190c0fbfb4d109af70"},"schema_version":"1.0","source":{"id":"2502.20586","kind":"arxiv","version":3}},"canonical_sha256":"91b3dfc87f1b1335a24dc6347b357079f77f54ca9b98122bf15209e32267bbaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91b3dfc87f1b1335a24dc6347b357079f77f54ca9b98122bf15209e32267bbaa","first_computed_at":"2026-07-05T11:59:57.959721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:59:57.959721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MKE/Z8iqjBmEpNGWHmYRUkKB736yj7xk0D28h/4yAUldBaXNy69Ro0OLkW/iXtSwa3gWu1Hd29bUqhw67Q75Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:59:57.960185Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.20586","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb0199e1dcd83530789d2aac00b2f7c67e8d1df6624782792cb2a474cd944dfb","sha256:2c29efb01b633d3abcb141fafb6467a44da7efc3ce15da42d67140d48d143bb5"],"state_sha256":"e99238f866e37fe674b297227bc96aac01c7162c1fdcb73b3a69b07526a198fb"}