{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SAPHDR3RTV7JA7AOOA3IFA7A2V","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":"5cd7a634e3eaad5549936455628f9e05555e72d47c1c18f517c33dec2ecf310f","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T00:33:03Z","title_canon_sha256":"96b527f13f4517567d030e3b983a85804127c2c03c3dde2625963c5de93683f9"},"schema_version":"1.0","source":{"id":"2002.04745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.04745","created_at":"2026-07-05T01:13:57Z"},{"alias_kind":"arxiv_version","alias_value":"2002.04745v2","created_at":"2026-07-05T01:13:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.04745","created_at":"2026-07-05T01:13:57Z"},{"alias_kind":"pith_short_12","alias_value":"SAPHDR3RTV7J","created_at":"2026-07-05T01:13:57Z"},{"alias_kind":"pith_short_16","alias_value":"SAPHDR3RTV7JA7AO","created_at":"2026-07-05T01:13:57Z"},{"alias_kind":"pith_short_8","alias_value":"SAPHDR3R","created_at":"2026-07-05T01:13:57Z"}],"graph_snapshots":[{"event_id":"sha256:f472637293e5cd1d5565a5c4f9f1e41a9a0bc937e184f13fb2099293882cbcdc","target":"graph","created_at":"2026-07-05T01:13:57Z","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/2002.04745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Transformer is widely used in natural language processing tasks. To train a Transformer however, one usually needs a carefully designed learning rate warm-up stage, which is shown to be crucial to the final performance but will slow down the optimization and bring more hyper-parameter tunings. In this paper, we first study theoretically why the learning rate warm-up stage is essential and show that the location of layer normalization matters. Specifically, we prove with mean field theory that at initialization, for the original-designed Post-LN Transformer, which places the layer normaliza","authors_text":"Chen Xing, Di He, Huishuai Zhang, Kai Zheng, Liwei Wang, Ruibin Xiong, Shuxin Zheng, Tie-Yan Liu, Yanyan Lan, Yunchang Yang","cross_cats":["cs.CL","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T00:33:03Z","title":"On Layer Normalization in the Transformer Architecture"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.04745","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":"sha256:75a754410c7fc99473f659704b15ab8b61d6e726c8ac803378e89e30b75ea941","target":"record","created_at":"2026-07-05T01:13:57Z","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":"5cd7a634e3eaad5549936455628f9e05555e72d47c1c18f517c33dec2ecf310f","cross_cats_sorted":["cs.CL","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-12T00:33:03Z","title_canon_sha256":"96b527f13f4517567d030e3b983a85804127c2c03c3dde2625963c5de93683f9"},"schema_version":"1.0","source":{"id":"2002.04745","kind":"arxiv","version":2}},"canonical_sha256":"901e71c7719d7e907c0e70368283e0d54ef163f6c0192cebe8280fe74d8d9ab2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"901e71c7719d7e907c0e70368283e0d54ef163f6c0192cebe8280fe74d8d9ab2","first_computed_at":"2026-07-05T01:13:57.975174Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:13:57.975174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5xX1oAt4/sILf78oOBOHF1lwdPlySU3H76XNRoVhv+EuJxSz3c4Q6ApK0MogW9vb08zU7sRwXHOMUSUSZIMrCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:13:57.975666Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.04745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:75a754410c7fc99473f659704b15ab8b61d6e726c8ac803378e89e30b75ea941","sha256:f472637293e5cd1d5565a5c4f9f1e41a9a0bc937e184f13fb2099293882cbcdc"],"state_sha256":"f265b50f59a21c42387a464e0b59112e1fa67f8e23869dba38d69e610a904e3f"}