{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LNDB44GR6UEAELPNGQHFLTBBP3","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":"6bcf5b7fee23f462543a35bd58be7895b7d4c60e8e9f1e9cb618a61fa4020242","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-25T14:43:46Z","title_canon_sha256":"6460824c3be0a99a555f3618b9220ddb80111c0fecdd5fe1474e991c2dcf58b1"},"schema_version":"1.0","source":{"id":"1807.09639","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.09639","created_at":"2026-05-18T00:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"1807.09639v1","created_at":"2026-05-18T00:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.09639","created_at":"2026-05-18T00:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"LNDB44GR6UEA","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LNDB44GR6UEAELPN","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LNDB44GR","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:cc7383973339702afd334671dc8879c6afadafa58097551f5adb645c13a2707c","target":"graph","created_at":"2026-05-18T00:09:50Z","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"},"paper":{"abstract_excerpt":"For different language pairs, word-level neural machine translation (NMT) models with a fixed-size vocabulary suffer from the same problem of representing out-of-vocabulary (OOV) words. The common practice usually replaces all these rare or unknown words with a <UNK> token, which limits the translation performance to some extent. Most of recent work handled such a problem by splitting words into characters or other specially extracted subword units to enable open-vocabulary translation. Byte pair encoding (BPE) is one of the successful attempts that has been shown extremely competitive by prov","authors_text":"Hai Zhao, Yingting Wu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-25T14:43:46Z","title":"Finding Better Subword Segmentation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.09639","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:e94505df204f6c15f22d380b670ae243f01af6e59a623a8095f20e8eb677f9ab","target":"record","created_at":"2026-05-18T00:09:50Z","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":"6bcf5b7fee23f462543a35bd58be7895b7d4c60e8e9f1e9cb618a61fa4020242","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-25T14:43:46Z","title_canon_sha256":"6460824c3be0a99a555f3618b9220ddb80111c0fecdd5fe1474e991c2dcf58b1"},"schema_version":"1.0","source":{"id":"1807.09639","kind":"arxiv","version":1}},"canonical_sha256":"5b461e70d1f508022ded340e55cc217ee44d87648f92bd06ac443ef370c7fc8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b461e70d1f508022ded340e55cc217ee44d87648f92bd06ac443ef370c7fc8d","first_computed_at":"2026-05-18T00:09:50.744985Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:50.744985Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vlztl1tqZcqdOeIk6Hm7YFQlKMMijHHNZOhbqUpR+opYMXmzRyVZHB3lPbs5fNRo3oxtmhufVR+E2gJHfoBLAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:50.745635Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.09639","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e94505df204f6c15f22d380b670ae243f01af6e59a623a8095f20e8eb677f9ab","sha256:cc7383973339702afd334671dc8879c6afadafa58097551f5adb645c13a2707c"],"state_sha256":"e7782d84b14e8b373b5f5efb0ce4177a631f9f972ca861232106b55e907e0caf"}