{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6BBITQMBZFXIS5BUMBL2H22W5T","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":"531b8ff0db66be5054d0fe89ba71a312d154718432ab36a2317d0afd930526af","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T18:04:50Z","title_canon_sha256":"5fa5ccf226a058f442e77cc37a69241ad3c7a00c95ca276cb50805274ba60dde"},"schema_version":"1.0","source":{"id":"2501.17116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17116","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17116v2","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17116","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_12","alias_value":"6BBITQMBZFXI","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_16","alias_value":"6BBITQMBZFXIS5BU","created_at":"2026-05-20T00:00:17Z"},{"alias_kind":"pith_short_8","alias_value":"6BBITQMB","created_at":"2026-05-20T00:00:17Z"}],"graph_snapshots":[{"event_id":"sha256:6d2e573b25254540afb94235fcb78049b0a996b3e1a09bc5b7b75796f98efc86","target":"graph","created_at":"2026-05-20T00:00:17Z","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/2501.17116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing computational demands of training large language models (LLMs) necessitate more efficient methods. Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce these costs. While FP8 precision has demonstrated feasibility, leveraging FP4 remains a challenge due to significant quantization errors and limited representational capacity. This work introduces the first FP4 training framework for LLMs, addressing these challenges with two key innovations: a differentiable quantization estimator for precise weight updates and an outlier clamping and","authors_text":"Baining Guo, Guoshuai Zhao, Peng Cheng, Ruizhe Wang, Xiao Liu, Yeyun Gong, Zhengjun Zha, Ziyue Yang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T18:04:50Z","title":"Optimizing Large Language Model Training Using FP4 Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17116","kind":"arxiv","version":2},"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":"sha256:19eafbf636ca7a12c78e94d44738298451de524371ad54b60f42b79c0e972fdd","target":"record","created_at":"2026-05-20T00:00:17Z","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":"531b8ff0db66be5054d0fe89ba71a312d154718432ab36a2317d0afd930526af","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-28T18:04:50Z","title_canon_sha256":"5fa5ccf226a058f442e77cc37a69241ad3c7a00c95ca276cb50805274ba60dde"},"schema_version":"1.0","source":{"id":"2501.17116","kind":"arxiv","version":2}},"canonical_sha256":"f04289c181c96e8974346057a3eb56ececd38686d9bd0cfca475676ebba66ee6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f04289c181c96e8974346057a3eb56ececd38686d9bd0cfca475676ebba66ee6","first_computed_at":"2026-05-20T00:00:17.404117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:17.404117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lvp8FgJcmQprNUYHE5MpcNjG5S7SyeGV1evX4v4h9qemogJLu5lhlsSYB6u/k9n26qU+bOVm/lAII25cfXJ2AA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:17.404678Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19eafbf636ca7a12c78e94d44738298451de524371ad54b60f42b79c0e972fdd","sha256:6d2e573b25254540afb94235fcb78049b0a996b3e1a09bc5b7b75796f98efc86"],"state_sha256":"0e5912ec5fed0dbd7b02c8912f1fa66e9dd35b7d3c98ca21afc7bfbfdefebba6"}