{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HKACEKVMBXLKR4JNYS3XI26WSM","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":"80e3417bf8fab4e2cafa37804df467f0fc5c79efd29e43532abc2c298a2c87db","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T15:36:38Z","title_canon_sha256":"44c780711ca0898d8eb7326fa7123d14e5d72f78aedb03db30c7f742aa2f8107"},"schema_version":"1.0","source":{"id":"2203.00555","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00555","created_at":"2026-07-05T04:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00555v1","created_at":"2026-07-05T04:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00555","created_at":"2026-07-05T04:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"HKACEKVMBXLK","created_at":"2026-07-05T04:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"HKACEKVMBXLKR4JN","created_at":"2026-07-05T04:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"HKACEKVM","created_at":"2026-07-05T04:01:18Z"}],"graph_snapshots":[{"event_id":"sha256:9b4968ec7f5977a4211bbed8d842c50cc75a56532eafe34c13d5e5bd471a6e3b","target":"graph","created_at":"2026-07-05T04:01:18Z","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/2203.00555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose a simple yet effective method to stabilize extremely deep Transformers. Specifically, we introduce a new normalization function (DeepNorm) to modify the residual connection in Transformer, accompanying with theoretically derived initialization. In-depth theoretical analysis shows that model updates can be bounded in a stable way. The proposed method combines the best of two worlds, i.e., good performance of Post-LN and stable training of Pre-LN, making DeepNorm a preferred alternative. We successfully scale Transformers up to 1,000 layers (i.e., 2,500 attention and fe","authors_text":"Dongdong Zhang, Furu Wei, Hongyu Wang, Li Dong, Shaohan Huang, Shuming Ma","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T15:36:38Z","title":"DeepNet: Scaling Transformers to 1,000 Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00555","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:ea7acd4f189a1da73ef8466cd5d68948a73a0a5ab26276ae3ec199fc2dd8071c","target":"record","created_at":"2026-07-05T04:01:18Z","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":"80e3417bf8fab4e2cafa37804df467f0fc5c79efd29e43532abc2c298a2c87db","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T15:36:38Z","title_canon_sha256":"44c780711ca0898d8eb7326fa7123d14e5d72f78aedb03db30c7f742aa2f8107"},"schema_version":"1.0","source":{"id":"2203.00555","kind":"arxiv","version":1}},"canonical_sha256":"3a80222aac0dd6a8f12dc4b7746bd6932f4fd01fa9394e52867d55fd0c132bfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a80222aac0dd6a8f12dc4b7746bd6932f4fd01fa9394e52867d55fd0c132bfd","first_computed_at":"2026-07-05T04:01:18.520429Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:18.520429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+98BfqP4Ad1a0mVSgGXETmHBjhPkGd6QKwouyE9X0ksMjvKJeSWkYu/hnTnlq1JsVFyjKLU3jpOTAR7eYI56CA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:18.520908Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00555","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea7acd4f189a1da73ef8466cd5d68948a73a0a5ab26276ae3ec199fc2dd8071c","sha256:9b4968ec7f5977a4211bbed8d842c50cc75a56532eafe34c13d5e5bd471a6e3b"],"state_sha256":"b0c795d47a21b83ab71260d01fbfbbf24f4a6800cc1907fbfa7a6b7dd091c4da"}