{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZHE5LMQIXJRVCGUN44IBNH7JYS","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":"a46894127806282325edbf1e79d6540e8d737459528ccc3177635a50e0bf86eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T12:23:45Z","title_canon_sha256":"7dc1113d1d7d9597abebce7c80c490290dffb51e8213ae08c2cefacc8face931"},"schema_version":"1.0","source":{"id":"2507.03526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03526","created_at":"2026-07-05T11:32:01Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03526v1","created_at":"2026-07-05T11:32:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03526","created_at":"2026-07-05T11:32:01Z"},{"alias_kind":"pith_short_12","alias_value":"ZHE5LMQIXJRV","created_at":"2026-07-05T11:32:01Z"},{"alias_kind":"pith_short_16","alias_value":"ZHE5LMQIXJRVCGUN","created_at":"2026-07-05T11:32:01Z"},{"alias_kind":"pith_short_8","alias_value":"ZHE5LMQI","created_at":"2026-07-05T11:32:01Z"}],"graph_snapshots":[{"event_id":"sha256:c09d0dcb34bd77f6409acabbd8f487a6149b8b8993a70af720a53acc89ff7762","target":"graph","created_at":"2026-07-05T11:32:01Z","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/2507.03526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we introduce a novel approach for optimizing LLM training by adjusting learning rates across weights of different components in Transformer models. Traditional methods often apply a uniform learning rate across all network layers, potentially overlooking the unique dynamics of each part. Remarkably, our introduced relative learning rates, RLRS, method accelerates the training process by up to $23\\%$, particularly in complex models such as Mixture of Experts (MoE). Hyperparameters of RLRS can be efficiently tuned on smaller models and then effectively reused on models up to $27\\ti","authors_text":"Jakub Krajewski, Jan Ludziejewski, Jan Ma{\\l}a\\'snicki, Kamil Adamczewski, Kamil Ciebiera, Maciej Pi\\'oro, Maciej Stefaniak, Marek Cygan, Micha{\\l} Krutul, Piotr Sankowski, Sebastian Jaszczur","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T12:23:45Z","title":"Decoupled Relative Learning Rate Schedules"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03526","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":"sha256:5132398853182119302cc3cb8db3177e328f71108ab461e644b73fb925f63905","target":"record","created_at":"2026-07-05T11:32:01Z","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":"a46894127806282325edbf1e79d6540e8d737459528ccc3177635a50e0bf86eb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-04T12:23:45Z","title_canon_sha256":"7dc1113d1d7d9597abebce7c80c490290dffb51e8213ae08c2cefacc8face931"},"schema_version":"1.0","source":{"id":"2507.03526","kind":"arxiv","version":1}},"canonical_sha256":"c9c9d5b208ba63511a8de710169fe9c4a4f5c8e43069d52c0dbac029028625bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9c9d5b208ba63511a8de710169fe9c4a4f5c8e43069d52c0dbac029028625bc","first_computed_at":"2026-07-05T11:32:01.001335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:01.001335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O1EqSwC59+WOh3vg1U6u1Hswd4J2j1MnnmTgnSBj5rYC+DGYUUbOtmZ/q23IxhOaTZm9aH2WzJFFTP0lck65Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:01.001834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5132398853182119302cc3cb8db3177e328f71108ab461e644b73fb925f63905","sha256:c09d0dcb34bd77f6409acabbd8f487a6149b8b8993a70af720a53acc89ff7762"],"state_sha256":"7ded6db5891783bb4f26515dff150d6ff2e02c1dc625fc22fa6b9bef8400ae54"}