{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:L2NGI737D3G4XQNUHWYM3Z7GHH","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":"516734b724cfdefd5b5bb60fa565a8a2ce8b6480dc5a19a737f6fde0e970d7e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T09:58:57Z","title_canon_sha256":"b305b76ef52175216cdebebc669e98bdbaa8b66fdb1fd39fbabf5bb278b87126"},"schema_version":"1.0","source":{"id":"1909.00180","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.00180","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"arxiv_version","alias_value":"1909.00180v1","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00180","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_12","alias_value":"L2NGI737D3G4","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_16","alias_value":"L2NGI737D3G4XQNU","created_at":"2026-07-05T00:01:06Z"},{"alias_kind":"pith_short_8","alias_value":"L2NGI737","created_at":"2026-07-05T00:01:06Z"}],"graph_snapshots":[{"event_id":"sha256:8c317956b54c5fe74b17cb2d98f0dc2b6871c6e54bc2d818d3435bc5e62ea52e","target":"graph","created_at":"2026-07-05T00:01:06Z","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/1909.00180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is inexplicit and limited. In this paper, we propose a novel cross-lingual pre-training method for unsupervised machine translation by incorporating explicit cross-lingual training signals. Specifically, we first calculate cross-lingual n-gram embeddings and infer an n-gram translation table from them. With those n-gram translation pairs, we propose a new pre-training m","authors_text":"Ming Zhou, Shuai Ma, Shujie Liu, Shuo Ren, Yu Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T09:58:57Z","title":"Explicit Cross-lingual Pre-training for Unsupervised Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00180","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:db173c06ed0f560c26fde26345b967cbc91d142a57caea1b318e59245310cb6b","target":"record","created_at":"2026-07-05T00:01:06Z","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":"516734b724cfdefd5b5bb60fa565a8a2ce8b6480dc5a19a737f6fde0e970d7e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T09:58:57Z","title_canon_sha256":"b305b76ef52175216cdebebc669e98bdbaa8b66fdb1fd39fbabf5bb278b87126"},"schema_version":"1.0","source":{"id":"1909.00180","kind":"arxiv","version":1}},"canonical_sha256":"5e9a647f7f1ecdcbc1b43db0cde7e639c78b3cd2971ff099e27da3c26f761fd2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e9a647f7f1ecdcbc1b43db0cde7e639c78b3cd2971ff099e27da3c26f761fd2","first_computed_at":"2026-07-05T00:01:06.483901Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:01:06.483901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BRFnZA8iLu0eYhoH3QQs1wV4ufe5Qi9Y2h6J/Cy3V/RuhSDCw+/KYorth9ETg5lVKToPfvZ7yQKkRe6vsVwAAg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:01:06.484237Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.00180","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db173c06ed0f560c26fde26345b967cbc91d142a57caea1b318e59245310cb6b","sha256:8c317956b54c5fe74b17cb2d98f0dc2b6871c6e54bc2d818d3435bc5e62ea52e"],"state_sha256":"1da7766413e99dc71487e477975c79e7f540e860c359bac6d153aa8d457beed7"}