{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:I7CF65FIOHJIRQZ2CJFJV5O2ML","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":"370b04f65efddc5e888951a217353f825e00af85dcb41c4fb62519f5550b62e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T18:47:02Z","title_canon_sha256":"2228446d0e81bf335b2c3144dbe1cc6a4cfb01e6bc47987b201687723155ed94"},"schema_version":"1.0","source":{"id":"1810.08641","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.08641","created_at":"2026-05-18T00:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"1810.08641v1","created_at":"2026-05-18T00:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.08641","created_at":"2026-05-18T00:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"I7CF65FIOHJI","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_16","alias_value":"I7CF65FIOHJIRQZ2","created_at":"2026-05-18T12:32:28Z"},{"alias_kind":"pith_short_8","alias_value":"I7CF65FI","created_at":"2026-05-18T12:32:28Z"}],"graph_snapshots":[{"event_id":"sha256:78e0072303938a7aacaeda33fcdb32066faa1c66f4ef01815a122f92868d9b91","target":"graph","created_at":"2026-05-18T00:02:43Z","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":"In neural machine translation (NMT), it is has become standard to translate using subword units to allow for an open vocabulary and improve accuracy on infrequent words. Byte-pair encoding (BPE) and its variants are the predominant approach to generating these subwords, as they are unsupervised, resource-free, and empirically effective. However, the granularity of these subword units is a hyperparameter to be tuned for each language and task, using methods such as grid search. Tuning may be done inexhaustively or skipped entirely due to resource constraints, leading to sub-optimal performance.","authors_text":"Alex Coda, Andrew Runge, Elizabeth Salesky, Graham Neubig, Jan Niehues","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T18:47:02Z","title":"Optimizing Segmentation Granularity for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.08641","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:df2727a9de2d9d8f5b060e3158d0b659086546a6aacecce296157db09be6dc7c","target":"record","created_at":"2026-05-18T00:02:43Z","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":"370b04f65efddc5e888951a217353f825e00af85dcb41c4fb62519f5550b62e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-19T18:47:02Z","title_canon_sha256":"2228446d0e81bf335b2c3144dbe1cc6a4cfb01e6bc47987b201687723155ed94"},"schema_version":"1.0","source":{"id":"1810.08641","kind":"arxiv","version":1}},"canonical_sha256":"47c45f74a871d288c33a124a9af5da62c2d169fc5bc4014e17c85db2a4eef3fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47c45f74a871d288c33a124a9af5da62c2d169fc5bc4014e17c85db2a4eef3fb","first_computed_at":"2026-05-18T00:02:43.945615Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:43.945615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BLZ5Evm/8EXSm5ajRIuEwHAaPY8kziTlYKSw+LoPSWQPegWvnhfYTfqpgbE1pX4eQcRWeMkFcBxNZXVRnGM2Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:43.946207Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.08641","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df2727a9de2d9d8f5b060e3158d0b659086546a6aacecce296157db09be6dc7c","sha256:78e0072303938a7aacaeda33fcdb32066faa1c66f4ef01815a122f92868d9b91"],"state_sha256":"5a2cdc05f6092bb5afb489e899a6dec6ab7c802fb2118dcc73662984e36f4a62"}