{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GPS25F6JYVZFFTBCH5FBU6FDGZ","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":"0b9e4d65771158e0d4d7a32a890385c43bfb9649317f09d962710015e541b217","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T11:50:49Z","title_canon_sha256":"720655077d66a88967a999d7d3248b163724c7d19ba99adc824e8a75b95a3dde"},"schema_version":"1.0","source":{"id":"2004.02577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.02577","created_at":"2026-07-05T00:53:00Z"},{"alias_kind":"arxiv_version","alias_value":"2004.02577v1","created_at":"2026-07-05T00:53:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.02577","created_at":"2026-07-05T00:53:00Z"},{"alias_kind":"pith_short_12","alias_value":"GPS25F6JYVZF","created_at":"2026-07-05T00:53:00Z"},{"alias_kind":"pith_short_16","alias_value":"GPS25F6JYVZFFTBC","created_at":"2026-07-05T00:53:00Z"},{"alias_kind":"pith_short_8","alias_value":"GPS25F6J","created_at":"2026-07-05T00:53:00Z"}],"graph_snapshots":[{"event_id":"sha256:a6c9cd19c24340a55bdb91091c4abe6eab9c6cea9597cb5e1714b33647804a6e","target":"graph","created_at":"2026-07-05T00:53:00Z","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/2004.02577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which leads to translation errors for low frequency and out-of-vocabulary terminology. This paper proposes a dictionary-based data augmentation (DDA) method for cross-domain NMT. DDA synthesizes a domain-specific dictionary with general domain corpora to automatically generate a large-scale pseudo-IND parallel corpus. The generated pseudo-IND data can be used to en","authors_text":"Chongxuan Huang, Qun Liu, Tianhao Li, Wei Peng, Yun Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T11:50:49Z","title":"Dictionary-based Data Augmentation for Cross-Domain Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.02577","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":"sha256:96e8a36de097984e24029f25c98f5dbd1158ce75008d7edacaf941063d056f12","target":"record","created_at":"2026-07-05T00:53:00Z","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":"0b9e4d65771158e0d4d7a32a890385c43bfb9649317f09d962710015e541b217","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-06T11:50:49Z","title_canon_sha256":"720655077d66a88967a999d7d3248b163724c7d19ba99adc824e8a75b95a3dde"},"schema_version":"1.0","source":{"id":"2004.02577","kind":"arxiv","version":1}},"canonical_sha256":"33e5ae97c9c57252cc223f4a1a78a3366dc98067d243405a2dd4da4b5e7d579c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33e5ae97c9c57252cc223f4a1a78a3366dc98067d243405a2dd4da4b5e7d579c","first_computed_at":"2026-07-05T00:53:00.601212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:53:00.601212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t2+IgpkImrsOIJgBP/rGziLRGCJFj8pMOwpyCePLaIjQVYLlFzbC3JJnJFmqLMiO7LwdGlUgF0gdhtR06XNjAw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:53:00.601712Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.02577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96e8a36de097984e24029f25c98f5dbd1158ce75008d7edacaf941063d056f12","sha256:a6c9cd19c24340a55bdb91091c4abe6eab9c6cea9597cb5e1714b33647804a6e"],"state_sha256":"f73b71947e3bae8f0ddd038b085c628f953068eb65a41ddb2118ea8ec7c5813a"}