{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:XLXC4YBLKNBWMU5MUDSW4ETUGA","short_pith_number":"pith:XLXC4YBL","canonical_record":{"source":{"id":"1812.08621","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T15:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"810f058431149bafe4adc66d071717984e0a559648cc81e7a2a09960d24644a2","abstract_canon_sha256":"548bdad91f0514d831fc5fbe5047a2a2535e486060bc4be3927e6d43498abd1a"},"schema_version":"1.0"},"canonical_sha256":"baee2e602b53436653aca0e56e12743036bfd4c47107ecf2ea21ff64fccb4106","source":{"kind":"arxiv","id":"1812.08621","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08621","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08621v4","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08621","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"XLXC4YBLKNBW","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XLXC4YBLKNBWMU5M","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XLXC4YBL","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:XLXC4YBLKNBWMU5MUDSW4ETUGA","target":"record","payload":{"canonical_record":{"source":{"id":"1812.08621","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T15:02:39Z","cross_cats_sorted":[],"title_canon_sha256":"810f058431149bafe4adc66d071717984e0a559648cc81e7a2a09960d24644a2","abstract_canon_sha256":"548bdad91f0514d831fc5fbe5047a2a2535e486060bc4be3927e6d43498abd1a"},"schema_version":"1.0"},"canonical_sha256":"baee2e602b53436653aca0e56e12743036bfd4c47107ecf2ea21ff64fccb4106","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:42.782113Z","signature_b64":"VU2pSCV/24CIWFfgacFEaiso61tu5trBRYgHFv1b6KGHvZoEUlANtHNHWChDGSJG5gfNIHqTGALgLgVZUKqODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"baee2e602b53436653aca0e56e12743036bfd4c47107ecf2ea21ff64fccb4106","last_reissued_at":"2026-05-17T23:43:42.781446Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:42.781446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1812.08621","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jhEdj4eqp0CBwy5BJnIlff6/ZSX8Lx2YKoDPwuEt2WvkhmYv0NutSE/dmG+LuJnnnqZinkUPA8+H5prTj3QfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:38:57.121644Z"},"content_sha256":"5acb65826847f83b479853eea40c30786d02bf1720b08df7ec88a923fc357f4f","schema_version":"1.0","event_id":"sha256:5acb65826847f83b479853eea40c30786d02bf1720b08df7ec88a923fc357f4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:XLXC4YBLKNBWMU5MUDSW4ETUGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"How Much Does Tokenization Affect Neural Machine Translation?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Helle, Francisco Casacuberta, Manuel Herranz, Mercedes Garc{\\i}a-Mart{\\i}nez, Miguel Domingo","submitted_at":"2018-12-20T15:02:39Z","abstract_excerpt":"Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08621","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-17T23:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fiexBrpaiaeTYH7rjJSu/vcB+b2T+mxP55xdWBVgC29S/C4yl40j+yp8IpNxH/gF3JAjeoKP4S+lZYYcW/AaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T08:38:57.122277Z"},"content_sha256":"5acd4d592e67298d5467e12d6ee3fe4c5c85f477260256f67c11d51db37f1588","schema_version":"1.0","event_id":"sha256:5acd4d592e67298d5467e12d6ee3fe4c5c85f477260256f67c11d51db37f1588"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/bundle.json","state_url":"https://pith.science/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/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":"2026-05-28T08:38:57Z","links":{"resolver":"https://pith.science/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA","bundle":"https://pith.science/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/bundle.json","state":"https://pith.science/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLXC4YBLKNBWMU5MUDSW4ETUGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:XLXC4YBLKNBWMU5MUDSW4ETUGA","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":"548bdad91f0514d831fc5fbe5047a2a2535e486060bc4be3927e6d43498abd1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T15:02:39Z","title_canon_sha256":"810f058431149bafe4adc66d071717984e0a559648cc81e7a2a09960d24644a2"},"schema_version":"1.0","source":{"id":"1812.08621","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1812.08621","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"1812.08621v4","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.08621","created_at":"2026-05-17T23:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"XLXC4YBLKNBW","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"XLXC4YBLKNBWMU5M","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"XLXC4YBL","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:5acd4d592e67298d5467e12d6ee3fe4c5c85f477260256f67c11d51db37f1588","target":"graph","created_at":"2026-05-17T23:43:42Z","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":"Tokenization or segmentation is a wide concept that covers simple processes such as separating punctuation from words, or more sophisticated processes such as applying morphological knowledge. Neural Machine Translation (NMT) requires a limited-size vocabulary for computational cost and enough examples to estimate word embeddings. Separating punctuation and splitting tokens into words or subwords has proven to be helpful to reduce vocabulary and increase the number of examples of each word, improving the translation quality. Tokenization is more challenging when dealing with languages with no ","authors_text":"Alexandre Helle, Francisco Casacuberta, Manuel Herranz, Mercedes Garc{\\i}a-Mart{\\i}nez, Miguel Domingo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T15:02:39Z","title":"How Much Does Tokenization Affect Neural Machine Translation?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.08621","kind":"arxiv","version":4},"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":"sha256:5acb65826847f83b479853eea40c30786d02bf1720b08df7ec88a923fc357f4f","target":"record","created_at":"2026-05-17T23:43:42Z","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":"548bdad91f0514d831fc5fbe5047a2a2535e486060bc4be3927e6d43498abd1a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-20T15:02:39Z","title_canon_sha256":"810f058431149bafe4adc66d071717984e0a559648cc81e7a2a09960d24644a2"},"schema_version":"1.0","source":{"id":"1812.08621","kind":"arxiv","version":4}},"canonical_sha256":"baee2e602b53436653aca0e56e12743036bfd4c47107ecf2ea21ff64fccb4106","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"baee2e602b53436653aca0e56e12743036bfd4c47107ecf2ea21ff64fccb4106","first_computed_at":"2026-05-17T23:43:42.781446Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:42.781446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VU2pSCV/24CIWFfgacFEaiso61tu5trBRYgHFv1b6KGHvZoEUlANtHNHWChDGSJG5gfNIHqTGALgLgVZUKqODQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:42.782113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1812.08621","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5acb65826847f83b479853eea40c30786d02bf1720b08df7ec88a923fc357f4f","sha256:5acd4d592e67298d5467e12d6ee3fe4c5c85f477260256f67c11d51db37f1588"],"state_sha256":"3af0b66b5c5ef25633cd20e0b92b11931cf03e98fead5b5981af6a3333c9a8ae"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bjiWoBthBAyasb7o9RDui6luvuCh6isG7il78YKCS77UkeA4l6ZJc5CWoyGgHbU9Aw5WpEUTeyCinUJaRDZeBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T08:38:57.125086Z","bundle_sha256":"52858fa7f66559d2e4478bb462f1bffddf8c6e4801bd1e20f7b28faa846d905e"}}