{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MJNSP2MSW7S5WYDCPRP2Z3DLAH","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":"9d91185da0c7126caae37684885d3f2673b6bff43f69cfc3bffab73acc8cf3da","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T23:57:30Z","title_canon_sha256":"313722b1ffa0f2b5135ac071d3359579e03a450aeeaa1ded1c14f3bccb69d09b"},"schema_version":"1.0","source":{"id":"2506.15025","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15025","created_at":"2026-07-05T11:23:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15025v1","created_at":"2026-07-05T11:23:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15025","created_at":"2026-07-05T11:23:35Z"},{"alias_kind":"pith_short_12","alias_value":"MJNSP2MSW7S5","created_at":"2026-07-05T11:23:35Z"},{"alias_kind":"pith_short_16","alias_value":"MJNSP2MSW7S5WYDC","created_at":"2026-07-05T11:23:35Z"},{"alias_kind":"pith_short_8","alias_value":"MJNSP2MS","created_at":"2026-07-05T11:23:35Z"}],"graph_snapshots":[{"event_id":"sha256:ad2c9d0af72e63382f4787e0d41dd0427285c080ac580937cc53d7a728aa5e63","target":"graph","created_at":"2026-07-05T11:23:35Z","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/2506.15025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretraining large language models is a costly process. To make this process more efficient, several methods have been proposed to optimize model architecture/parametrization and hardware use. On the parametrization side, $\\mu P$ (Maximal Update Parametrization) parametrizes model weights and learning rate (LR) in a way that makes hyperparameters (HPs) transferable with width (embedding dimension): HPs can be tuned for a small model and used for larger models without additional tuning. While $\\mu$P showed impressive results in practice, recent empirical studies have reported conflicting observa","authors_text":"Liyuan Liu, Soufiane Hayou","cross_cats":["cs.AI","cs.CL","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T23:57:30Z","title":"Optimal Embedding Learning Rate in LLMs: The Effect of Vocabulary Size"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15025","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":"sha256:6b3e4ab7fa0fb4b835dcc2876b24ce0f0ee85cfd45642a5519a356e4efb7fa92","target":"record","created_at":"2026-07-05T11:23:35Z","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":"9d91185da0c7126caae37684885d3f2673b6bff43f69cfc3bffab73acc8cf3da","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-17T23:57:30Z","title_canon_sha256":"313722b1ffa0f2b5135ac071d3359579e03a450aeeaa1ded1c14f3bccb69d09b"},"schema_version":"1.0","source":{"id":"2506.15025","kind":"arxiv","version":1}},"canonical_sha256":"625b27e992b7e5db60627c5facec6b01eacc3d118d3dd3814847872d736fce3c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"625b27e992b7e5db60627c5facec6b01eacc3d118d3dd3814847872d736fce3c","first_computed_at":"2026-07-05T11:23:35.734835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:35.734835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4UZtgR+AD2O/ktAByQdU77IhepoZ8ExRkLwnaK2xeF64CWCrijQcb8HdSaP5USyg+FoG1+oHuWGC1jehWasGAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:35.735414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15025","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b3e4ab7fa0fb4b835dcc2876b24ce0f0ee85cfd45642a5519a356e4efb7fa92","sha256:ad2c9d0af72e63382f4787e0d41dd0427285c080ac580937cc53d7a728aa5e63"],"state_sha256":"ac8bb9522aef3a9e5e2e99a9b89cef2d82ec6c1b6ff38db5a63a581582839089"}