{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:47VMV7KBAISFEFFM7SRXKYTFWF","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":"ecdfe107692da0666f9e2c08a1528fb5eb7a5c2e9537378db3362ceac645895e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-18T07:14:54Z","title_canon_sha256":"3ff9a96a3f16074fe848edfcb7e89a5c7e7239b0fe968209644a61a2220ede8b"},"schema_version":"1.0","source":{"id":"2008.07772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.07772","created_at":"2026-07-05T01:43:05Z"},{"alias_kind":"arxiv_version","alias_value":"2008.07772v2","created_at":"2026-07-05T01:43:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.07772","created_at":"2026-07-05T01:43:05Z"},{"alias_kind":"pith_short_12","alias_value":"47VMV7KBAISF","created_at":"2026-07-05T01:43:05Z"},{"alias_kind":"pith_short_16","alias_value":"47VMV7KBAISFEFFM","created_at":"2026-07-05T01:43:05Z"},{"alias_kind":"pith_short_8","alias_value":"47VMV7KB","created_at":"2026-07-05T01:43:05Z"}],"graph_snapshots":[{"event_id":"sha256:13538044563794691bda1033e2a4c962c5cd20b5973332da625a291775edd304","target":"graph","created_at":"2026-07-05T01:43:05Z","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/2008.07772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore the application of very deep Transformer models for Neural Machine Translation (NMT). Using a simple yet effective initialization technique that stabilizes training, we show that it is feasible to build standard Transformer-based models with up to 60 encoder layers and 12 decoder layers. These deep models outperform their baseline 6-layer counterparts by as much as 2.5 BLEU, and achieve new state-of-the-art benchmark results on WMT14 English-French (43.8 BLEU and 46.4 BLEU with back-translation) and WMT14 English-German (30.1 BLEU).The code and trained models will be publicly availa","authors_text":"Jianfeng Gao, Kevin Duh, Liyuan Liu, XiaoDong Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-18T07:14:54Z","title":"Very Deep Transformers for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07772","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":"sha256:52b642c917848615d8f2a2de86e98cf77398b677936fd92d00cbe6ee192b0993","target":"record","created_at":"2026-07-05T01:43:05Z","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":"ecdfe107692da0666f9e2c08a1528fb5eb7a5c2e9537378db3362ceac645895e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-18T07:14:54Z","title_canon_sha256":"3ff9a96a3f16074fe848edfcb7e89a5c7e7239b0fe968209644a61a2220ede8b"},"schema_version":"1.0","source":{"id":"2008.07772","kind":"arxiv","version":2}},"canonical_sha256":"e7eacafd4102245214acfca3756265b1571454c6d0d60e98db4eb2c5207cad92","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7eacafd4102245214acfca3756265b1571454c6d0d60e98db4eb2c5207cad92","first_computed_at":"2026-07-05T01:43:05.708620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:43:05.708620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JpS6u2T/NjU7NZZ+orhVx7kmYKPODPhkHMBCCfazZBung2Vf5Uvr4r4GTPs8WSX6RvLlcolRLD6aqCqaWkizCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:43:05.709026Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.07772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52b642c917848615d8f2a2de86e98cf77398b677936fd92d00cbe6ee192b0993","sha256:13538044563794691bda1033e2a4c962c5cd20b5973332da625a291775edd304"],"state_sha256":"45c99c1adecd79aaa06d10926ac2c112377fa565e2e8873c0b5fd6b650f86e3e"}