{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W2MQDI53FHZI5FPVMAVQ3INXQ2","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":"f241eb925429b10ab387b582058da529d6d758638fe2c0fbcf315d838ca54193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-18T16:47:45Z","title_canon_sha256":"a5104797a885e2b53db46ec80463be1c534249d21ccc252847c050b67fc0a442"},"schema_version":"1.0","source":{"id":"2110.09456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09456","created_at":"2026-07-05T03:27:36Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09456v2","created_at":"2026-07-05T03:27:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09456","created_at":"2026-07-05T03:27:36Z"},{"alias_kind":"pith_short_12","alias_value":"W2MQDI53FHZI","created_at":"2026-07-05T03:27:36Z"},{"alias_kind":"pith_short_16","alias_value":"W2MQDI53FHZI5FPV","created_at":"2026-07-05T03:27:36Z"},{"alias_kind":"pith_short_8","alias_value":"W2MQDI53","created_at":"2026-07-05T03:27:36Z"}],"graph_snapshots":[{"event_id":"sha256:b772fe54ee9cd81ef35049090275566bc0f138a173d267fd32ba3542c2f2c297","target":"graph","created_at":"2026-07-05T03:27:36Z","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/2110.09456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"During pretraining, the Pre-LayerNorm transformer suffers from a gradient magnitude mismatch: gradients at early layers are much larger than at later layers. These issues can be alleviated by our proposed NormFormer architecture, which adds three normalization operations to each layer: a Layer Norm after self attention, head-wise scaling of self-attention outputs, and a Layer Norm after the first fully connected layer. The extra operations incur negligible compute cost (+0.4% parameter increase), but improve pretraining perplexity and downstream task performance for both causal and masked lang","authors_text":"Jason Weston, Myle Ott, Sam Shleifer","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-18T16:47:45Z","title":"NormFormer: Improved Transformer Pretraining with Extra Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09456","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:afa583883edeeee09f174653b68790646ebd7f70a3445d31d9fb210b07d7663f","target":"record","created_at":"2026-07-05T03:27:36Z","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":"f241eb925429b10ab387b582058da529d6d758638fe2c0fbcf315d838ca54193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-18T16:47:45Z","title_canon_sha256":"a5104797a885e2b53db46ec80463be1c534249d21ccc252847c050b67fc0a442"},"schema_version":"1.0","source":{"id":"2110.09456","kind":"arxiv","version":2}},"canonical_sha256":"b69901a3bb29f28e95f5602b0da1b7868a1692a641d18f5ac8e4a169c189cc12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b69901a3bb29f28e95f5602b0da1b7868a1692a641d18f5ac8e4a169c189cc12","first_computed_at":"2026-07-05T03:27:36.557699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:36.557699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ygrH/pbCXfHg5BjBnti/j5/QcujxmGdEYB3s8VNrt86+xMYeyNUnDJfrBlz2c3nzqnRrCmK7vaIBS0qju2xyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:36.558085Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afa583883edeeee09f174653b68790646ebd7f70a3445d31d9fb210b07d7663f","sha256:b772fe54ee9cd81ef35049090275566bc0f138a173d267fd32ba3542c2f2c297"],"state_sha256":"7ecac27f57eee3069a0d92de5b86903e665b1624c26c3dd8f20598149522fa6f"}