{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:47VMV7KBAISFEFFM7SRXKYTFWF","short_pith_number":"pith:47VMV7KB","canonical_record":{"source":{"id":"2008.07772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-18T07:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"3ff9a96a3f16074fe848edfcb7e89a5c7e7239b0fe968209644a61a2220ede8b","abstract_canon_sha256":"ecdfe107692da0666f9e2c08a1528fb5eb7a5c2e9537378db3362ceac645895e"},"schema_version":"1.0"},"canonical_sha256":"e7eacafd4102245214acfca3756265b1571454c6d0d60e98db4eb2c5207cad92","source":{"kind":"arxiv","id":"2008.07772","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:47VMV7KBAISFEFFM7SRXKYTFWF","target":"record","payload":{"canonical_record":{"source":{"id":"2008.07772","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-18T07:14:54Z","cross_cats_sorted":[],"title_canon_sha256":"3ff9a96a3f16074fe848edfcb7e89a5c7e7239b0fe968209644a61a2220ede8b","abstract_canon_sha256":"ecdfe107692da0666f9e2c08a1528fb5eb7a5c2e9537378db3362ceac645895e"},"schema_version":"1.0"},"canonical_sha256":"e7eacafd4102245214acfca3756265b1571454c6d0d60e98db4eb2c5207cad92","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:05.709026Z","signature_b64":"JpS6u2T/NjU7NZZ+orhVx7kmYKPODPhkHMBCCfazZBung2Vf5Uvr4r4GTPs8WSX6RvLlcolRLD6aqCqaWkizCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7eacafd4102245214acfca3756265b1571454c6d0d60e98db4eb2c5207cad92","last_reissued_at":"2026-07-05T01:43:05.708620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:05.708620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.07772","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":"2026-07-05T01:43:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J5iRYDb1wlxXkBvs7krzlyUFvguF33x7hdTG93G0XwJYOtsHXBuSxUCXg0bSQriTkt2OuxLFhiu5cjdN97NlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:09:06.726140Z"},"content_sha256":"52b642c917848615d8f2a2de86e98cf77398b677936fd92d00cbe6ee192b0993","schema_version":"1.0","event_id":"sha256:52b642c917848615d8f2a2de86e98cf77398b677936fd92d00cbe6ee192b0993"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:47VMV7KBAISFEFFM7SRXKYTFWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Very Deep Transformers for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianfeng Gao, Kevin Duh, Liyuan Liu, XiaoDong Liu","submitted_at":"2020-08-18T07:14:54Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.07772","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/2008.07772/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":"2026-07-05T01:43:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XNiXNA6NaqMFKzLrqWSkT5WWtTqr9/kxGXEpTFR4hEXIyZ0Q5YNB9ET2kPbje7mZDUCfkblr56i+PddIyPutCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:09:06.727039Z"},"content_sha256":"13538044563794691bda1033e2a4c962c5cd20b5973332da625a291775edd304","schema_version":"1.0","event_id":"sha256:13538044563794691bda1033e2a4c962c5cd20b5973332da625a291775edd304"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47VMV7KBAISFEFFM7SRXKYTFWF/bundle.json","state_url":"https://pith.science/pith/47VMV7KBAISFEFFM7SRXKYTFWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47VMV7KBAISFEFFM7SRXKYTFWF/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":"2026-08-06T07:09:06Z","links":{"resolver":"https://pith.science/pith/47VMV7KBAISFEFFM7SRXKYTFWF","bundle":"https://pith.science/pith/47VMV7KBAISFEFFM7SRXKYTFWF/bundle.json","state":"https://pith.science/pith/47VMV7KBAISFEFFM7SRXKYTFWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47VMV7KBAISFEFFM7SRXKYTFWF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RzGxZ5AAgwNwHYBi23PJyHHUwmwB58o6TB3DKADqn4OkwBYcusTQex4pw6gQSeky0NEXuu33mfxsXBhK0xXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:09:06.733598Z","bundle_sha256":"751ace381134fb143206e285313b288b5d32b25934674e050b33357054ccade6"}}