{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DVLKKOYY5CHTK2UHVFYGB7Y4HS","short_pith_number":"pith:DVLKKOYY","canonical_record":{"source":{"id":"1910.05895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T02:23:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6e5afb961bdd5450368913676a91af293da3cba1e83d8038eadbb3dd626eb7de","abstract_canon_sha256":"cf11f382462d522b30e508bb383901f3cba67dad4e11777c0cc1fbc79a69b42c"},"schema_version":"1.0"},"canonical_sha256":"1d56a53b18e88f356a87a97060ff1c3c948141424dee64e71711909e7e606357","source":{"kind":"arxiv","id":"1910.05895","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05895","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05895v2","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05895","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"DVLKKOYY5CHT","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"DVLKKOYY5CHTK2UH","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"DVLKKOYY","created_at":"2026-07-05T00:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DVLKKOYY5CHTK2UHVFYGB7Y4HS","target":"record","payload":{"canonical_record":{"source":{"id":"1910.05895","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T02:23:43Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"6e5afb961bdd5450368913676a91af293da3cba1e83d8038eadbb3dd626eb7de","abstract_canon_sha256":"cf11f382462d522b30e508bb383901f3cba67dad4e11777c0cc1fbc79a69b42c"},"schema_version":"1.0"},"canonical_sha256":"1d56a53b18e88f356a87a97060ff1c3c948141424dee64e71711909e7e606357","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:54.970913Z","signature_b64":"g0BtYxxtX24tUlm6vBVU6hYRBkRYA1NL00EFIS8ISMtsm5YM7lslmI62c/72FMjkic+GjcP6ROHjQfzVEecjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d56a53b18e88f356a87a97060ff1c3c948141424dee64e71711909e7e606357","last_reissued_at":"2026-07-05T00:28:54.970447Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:54.970447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.05895","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9RlB55Sw4z0Mnj1xee0gfrmTJIls9N8KBF1uELF99XMbAAy0x3BMP/VABVntEwGEZ4oFM9+5aIC8QrlQl6ABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:21:06.298401Z"},"content_sha256":"c9a4914cd276308c113fe41774563fb19a53c5127beb751b3eb56688088e2f51","schema_version":"1.0","event_id":"sha256:c9a4914cd276308c113fe41774563fb19a53c5127beb751b3eb56688088e2f51"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DVLKKOYY5CHTK2UHVFYGB7Y4HS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers without Tears: Improving the Normalization of Self-Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Julian Salazar, Toan Q. Nguyen","submitted_at":"2019-10-14T02:23:43Z","abstract_excerpt":"We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PreNorm) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, we propose $\\ell_2$ normalization with a single scale parameter (ScaleNorm) for faster training and better performance. Finally, we reaffirm the effectiveness of normalizing word embeddings to a fixed length (FixNorm). On five low-resource translation pairs from TED Talks-based corpora, these changes always converge, giving an average +1.1 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05895","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.05895/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cI66eQoMg9H29ttXNd1P1cYn/f8IlJCyPto6Neu7tR0veuIZdRYgv8PF4hC7o4/7K9EBPXde1YNMGkXGX1fYCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T15:21:06.299221Z"},"content_sha256":"808b264961f80b2d507a2f815e858749c2ca215bbce02f4fdb19990446b8df9e","schema_version":"1.0","event_id":"sha256:808b264961f80b2d507a2f815e858749c2ca215bbce02f4fdb19990446b8df9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/bundle.json","state_url":"https://pith.science/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T15:21:06Z","links":{"resolver":"https://pith.science/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS","bundle":"https://pith.science/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/bundle.json","state":"https://pith.science/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DVLKKOYY5CHTK2UHVFYGB7Y4HS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DVLKKOYY5CHTK2UHVFYGB7Y4HS","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":"cf11f382462d522b30e508bb383901f3cba67dad4e11777c0cc1fbc79a69b42c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T02:23:43Z","title_canon_sha256":"6e5afb961bdd5450368913676a91af293da3cba1e83d8038eadbb3dd626eb7de"},"schema_version":"1.0","source":{"id":"1910.05895","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.05895","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"1910.05895v2","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05895","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"DVLKKOYY5CHT","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"DVLKKOYY5CHTK2UH","created_at":"2026-07-05T00:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"DVLKKOYY","created_at":"2026-07-05T00:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:808b264961f80b2d507a2f815e858749c2ca215bbce02f4fdb19990446b8df9e","target":"graph","created_at":"2026-07-05T00:28:54Z","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/1910.05895/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We evaluate three simple, normalization-centric changes to improve Transformer training. First, we show that pre-norm residual connections (PreNorm) and smaller initializations enable warmup-free, validation-based training with large learning rates. Second, we propose $\\ell_2$ normalization with a single scale parameter (ScaleNorm) for faster training and better performance. Finally, we reaffirm the effectiveness of normalizing word embeddings to a fixed length (FixNorm). On five low-resource translation pairs from TED Talks-based corpora, these changes always converge, giving an average +1.1 ","authors_text":"Julian Salazar, Toan Q. Nguyen","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T02:23:43Z","title":"Transformers without Tears: Improving the Normalization of Self-Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05895","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:c9a4914cd276308c113fe41774563fb19a53c5127beb751b3eb56688088e2f51","target":"record","created_at":"2026-07-05T00:28:54Z","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":"cf11f382462d522b30e508bb383901f3cba67dad4e11777c0cc1fbc79a69b42c","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-14T02:23:43Z","title_canon_sha256":"6e5afb961bdd5450368913676a91af293da3cba1e83d8038eadbb3dd626eb7de"},"schema_version":"1.0","source":{"id":"1910.05895","kind":"arxiv","version":2}},"canonical_sha256":"1d56a53b18e88f356a87a97060ff1c3c948141424dee64e71711909e7e606357","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d56a53b18e88f356a87a97060ff1c3c948141424dee64e71711909e7e606357","first_computed_at":"2026-07-05T00:28:54.970447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:28:54.970447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g0BtYxxtX24tUlm6vBVU6hYRBkRYA1NL00EFIS8ISMtsm5YM7lslmI62c/72FMjkic+GjcP6ROHjQfzVEecjBA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:28:54.970913Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.05895","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9a4914cd276308c113fe41774563fb19a53c5127beb751b3eb56688088e2f51","sha256:808b264961f80b2d507a2f815e858749c2ca215bbce02f4fdb19990446b8df9e"],"state_sha256":"e24540724dd32b7792dfadb0a9d2fd6ebd118f06044cb2045eb78891c3059dbe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MKQUGvhkeWxTRUoiHh/RcSY5vtdKqI380FpIMXwBEUpINt39wUr4ZwU1bGKkzIst+cKGJr8P8l7C6pVhWpq3Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T15:21:06.306315Z","bundle_sha256":"7193f8d11148e9fc31d6a42dea1c9485732fa1686b31aeeb8146e22d4b829759"}}