{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:GQRKJTF4GH3IFAOEZJPYJXCHPB","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":"61231e449a0e84582dcbc4e6d262079c0b81d26f70e241a1d74f4d48d44e5e32","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T08:08:26Z","title_canon_sha256":"fd8c2884d0a1eb9d4084b5eaf73e4df3541ad8fc496e7656f5cf976d18dc712f"},"schema_version":"1.0","source":{"id":"2305.14858","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14858","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14858v2","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14858","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"GQRKJTF4GH3I","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"GQRKJTF4GH3IFAOE","created_at":"2026-07-05T07:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"GQRKJTF4","created_at":"2026-07-05T07:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:f7a1a112095f1985770c76ceaba6731ed63a178ad521b45d9743fa39bbfe66b2","target":"graph","created_at":"2026-07-05T07:05:09Z","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/2305.14858/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformers have achieved great success in machine learning applications. Normalization techniques, such as Layer Normalization (LayerNorm, LN) and Root Mean Square Normalization (RMSNorm), play a critical role in accelerating and stabilizing the training of Transformers. While LayerNorm recenters and rescales input vectors, RMSNorm only rescales the vectors by their RMS value. Despite being more computationally efficient, RMSNorm may compromise the representation ability of Transformers. There is currently no consensus regarding the preferred normalization technique, as some models employ La","authors_text":"David Z. Pan, Hanqing Zhu, Jiaqi Gu, Zixuan Jiang","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T08:08:26Z","title":"Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14858","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:e52f640099c65da16586fdfbc2293ed110bad4d21793d7e91691bef71d3fdb99","target":"record","created_at":"2026-07-05T07:05:09Z","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":"61231e449a0e84582dcbc4e6d262079c0b81d26f70e241a1d74f4d48d44e5e32","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-24T08:08:26Z","title_canon_sha256":"fd8c2884d0a1eb9d4084b5eaf73e4df3541ad8fc496e7656f5cf976d18dc712f"},"schema_version":"1.0","source":{"id":"2305.14858","kind":"arxiv","version":2}},"canonical_sha256":"3422a4ccbc31f68281c4ca5f84dc4778624d08b2d7239ea242ebdae958dbcf09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3422a4ccbc31f68281c4ca5f84dc4778624d08b2d7239ea242ebdae958dbcf09","first_computed_at":"2026-07-05T07:05:09.057820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:05:09.057820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dfMjyLbJEgyxgxZ/+Okj5M4eeoTZLiALuveSjKlJ7IX99wQH9wxsStwyrT9axznmJPSvuMq2vmEwV9ne1F6uBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:05:09.058307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14858","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e52f640099c65da16586fdfbc2293ed110bad4d21793d7e91691bef71d3fdb99","sha256:f7a1a112095f1985770c76ceaba6731ed63a178ad521b45d9743fa39bbfe66b2"],"state_sha256":"a81c33af598b3b9cb13bc64903d33b84708bb13929120eef1e411836994d9062"}