{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HPRJRRSWLHFTSR4EGOKNH23ME3","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":"30e3dca0a1fde90cccf64c7670b93aaa0df00fd92350cf5d507ffa4ec3f718f4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T08:43:20Z","title_canon_sha256":"a8ef8072981ce9ce771a6d0ab441684c34bc9208aea357873f8a3111122499f2"},"schema_version":"1.0","source":{"id":"2206.00330","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00330","created_at":"2026-07-05T06:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00330v2","created_at":"2026-07-05T06:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00330","created_at":"2026-07-05T06:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"HPRJRRSWLHFT","created_at":"2026-07-05T06:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"HPRJRRSWLHFTSR4E","created_at":"2026-07-05T06:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"HPRJRRSW","created_at":"2026-07-05T06:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:95f165837cef42ab7b122b511e92f19a92b891044b51ae0eacbbea292dfe1351","target":"graph","created_at":"2026-07-05T06:14:04Z","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/2206.00330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"From the perspective of the layer normalization (LN) positions, the architectures of Transformers can be categorized into two types: Post-LN and Pre-LN. Recent Transformers tend to be Pre-LN because, in Post-LN with deep Transformers (e.g., those with ten or more layers), the training is often unstable, resulting in useless models. However, Post-LN has consistently achieved better performance than Pre-LN in relatively shallow Transformers (e.g., those with six or fewer layers). This study first investigates the reason for these discrepant observations empirically and theoretically and made the","authors_text":"Jun Suzuki, Sho Takase, Shun Kiyono, Sosuke Kobayashi","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T08:43:20Z","title":"B2T Connection: Serving Stability and Performance in Deep Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00330","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":"sha256:52e31e70fb99021c1fc3baf5b51a4f4893b05a21329838d7e191714409c6ae87","target":"record","created_at":"2026-07-05T06:14:04Z","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":"30e3dca0a1fde90cccf64c7670b93aaa0df00fd92350cf5d507ffa4ec3f718f4","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-01T08:43:20Z","title_canon_sha256":"a8ef8072981ce9ce771a6d0ab441684c34bc9208aea357873f8a3111122499f2"},"schema_version":"1.0","source":{"id":"2206.00330","kind":"arxiv","version":2}},"canonical_sha256":"3be298c65659cb3947843394d3eb6c26c871b5815fb64f9a65dd91a3acb61af9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3be298c65659cb3947843394d3eb6c26c871b5815fb64f9a65dd91a3acb61af9","first_computed_at":"2026-07-05T06:14:04.187893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:04.187893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YstMkZth3n5NDIVMRjeHlfkYufqhAT0q/xD8RJhPo5EqjHni5GcUXjCJcm71MHPMdd2m9/92v6JoJCVWiQIRBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:04.188338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00330","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52e31e70fb99021c1fc3baf5b51a4f4893b05a21329838d7e191714409c6ae87","sha256:95f165837cef42ab7b122b511e92f19a92b891044b51ae0eacbbea292dfe1351"],"state_sha256":"05627ebdfa8553f61b0f85daadfc8f8ccbb364d002dcb66e345d434bc5938c70"}