{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:I3N4V54IITD2W2BCN5YF5W7PUS","short_pith_number":"pith:I3N4V54I","canonical_record":{"source":{"id":"1909.03341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-07T21:29:46Z","cross_cats_sorted":[],"title_canon_sha256":"62f6e4b4d2e71cc7fc6448742e63eff93d793288a2659fbc8dbf8a2844180dc8","abstract_canon_sha256":"e279306e5e103c2f7f1dc597165df7fdcaaeb5e2838aa325445595bbc7a589b6"},"schema_version":"1.0"},"canonical_sha256":"46dbcaf78844c7ab68226f705edbefa48418a2321dbaef9d0679f89ef18b9c3d","source":{"kind":"arxiv","id":"1909.03341","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03341","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03341v2","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03341","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"I3N4V54IITD2","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"I3N4V54IITD2W2BC","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"I3N4V54I","created_at":"2026-07-05T00:24:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:I3N4V54IITD2W2BCN5YF5W7PUS","target":"record","payload":{"canonical_record":{"source":{"id":"1909.03341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-07T21:29:46Z","cross_cats_sorted":[],"title_canon_sha256":"62f6e4b4d2e71cc7fc6448742e63eff93d793288a2659fbc8dbf8a2844180dc8","abstract_canon_sha256":"e279306e5e103c2f7f1dc597165df7fdcaaeb5e2838aa325445595bbc7a589b6"},"schema_version":"1.0"},"canonical_sha256":"46dbcaf78844c7ab68226f705edbefa48418a2321dbaef9d0679f89ef18b9c3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:24:18.087126Z","signature_b64":"AOhaIQBwFDrHBd3ScCL6fyTq9rAn0JkBK7RGJkshtNnsTPa6rcS6cxMwUO/3Nc0s8MfwqAQqQpHbc6u3iIasDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46dbcaf78844c7ab68226f705edbefa48418a2321dbaef9d0679f89ef18b9c3d","last_reissued_at":"2026-07-05T00:24:18.086628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:24:18.086628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.03341","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1fVsRRcX1qDTvrc+WWkevXdNYY0iArVdPodUR/QIN7Ek7iTMw9UW8d4nbcWjjUSP1/ct4P4mCSSMgKPzvA9nCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:15:45.809963Z"},"content_sha256":"c6dc6c6579e568b53f5b79c30a46cf4638773a0c1df03b58b6fda027fe85b68e","schema_version":"1.0","event_id":"sha256:c6dc6c6579e568b53f5b79c30a46cf4638773a0c1df03b58b6fda027fe85b68e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:I3N4V54IITD2W2BCN5YF5W7PUS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural Machine Translation with Byte-Level Subwords","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changhan Wang, Jiatao Gu, Kyunghyun Cho","submitted_at":"2019-09-07T21:29:46Z","abstract_excerpt":"Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese however can unnecessarily take up vocabulary slots and limit its compactness. Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue. High computational cost has however prevented it from being widely deployed or used in practice. In this paper, we investigate byte-level subwords, specifically byte-level BPE (BBPE), w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03341","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.03341/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:24:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6RitestLtOfH9fQ8Q+tTJLOPWiTQyzspvl9y1IfzXOowytD/42VNUcR+ZnhybEaM3/LxS13fTMTmplRV85cCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:15:45.810565Z"},"content_sha256":"596eac77a9e4c05ebdcf4fdbdc1c0fe89e5a95c004c50e40c5cb383b7bc7315e","schema_version":"1.0","event_id":"sha256:596eac77a9e4c05ebdcf4fdbdc1c0fe89e5a95c004c50e40c5cb383b7bc7315e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I3N4V54IITD2W2BCN5YF5W7PUS/bundle.json","state_url":"https://pith.science/pith/I3N4V54IITD2W2BCN5YF5W7PUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I3N4V54IITD2W2BCN5YF5W7PUS/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":"2026-08-08T12:15:45Z","links":{"resolver":"https://pith.science/pith/I3N4V54IITD2W2BCN5YF5W7PUS","bundle":"https://pith.science/pith/I3N4V54IITD2W2BCN5YF5W7PUS/bundle.json","state":"https://pith.science/pith/I3N4V54IITD2W2BCN5YF5W7PUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I3N4V54IITD2W2BCN5YF5W7PUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:I3N4V54IITD2W2BCN5YF5W7PUS","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":"e279306e5e103c2f7f1dc597165df7fdcaaeb5e2838aa325445595bbc7a589b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-07T21:29:46Z","title_canon_sha256":"62f6e4b4d2e71cc7fc6448742e63eff93d793288a2659fbc8dbf8a2844180dc8"},"schema_version":"1.0","source":{"id":"1909.03341","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03341","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03341v2","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03341","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"I3N4V54IITD2","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"I3N4V54IITD2W2BC","created_at":"2026-07-05T00:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"I3N4V54I","created_at":"2026-07-05T00:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:596eac77a9e4c05ebdcf4fdbdc1c0fe89e5a95c004c50e40c5cb383b7bc7315e","target":"graph","created_at":"2026-07-05T00:24:18Z","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/1909.03341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Almost all existing machine translation models are built on top of character-based vocabularies: characters, subwords or words. Rare characters from noisy text or character-rich languages such as Japanese and Chinese however can unnecessarily take up vocabulary slots and limit its compactness. Representing text at the level of bytes and using the 256 byte set as vocabulary is a potential solution to this issue. High computational cost has however prevented it from being widely deployed or used in practice. In this paper, we investigate byte-level subwords, specifically byte-level BPE (BBPE), w","authors_text":"Changhan Wang, Jiatao Gu, Kyunghyun Cho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-07T21:29:46Z","title":"Neural Machine Translation with Byte-Level Subwords"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03341","kind":"arxiv","version":2},"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:c6dc6c6579e568b53f5b79c30a46cf4638773a0c1df03b58b6fda027fe85b68e","target":"record","created_at":"2026-07-05T00:24:18Z","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":"e279306e5e103c2f7f1dc597165df7fdcaaeb5e2838aa325445595bbc7a589b6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-07T21:29:46Z","title_canon_sha256":"62f6e4b4d2e71cc7fc6448742e63eff93d793288a2659fbc8dbf8a2844180dc8"},"schema_version":"1.0","source":{"id":"1909.03341","kind":"arxiv","version":2}},"canonical_sha256":"46dbcaf78844c7ab68226f705edbefa48418a2321dbaef9d0679f89ef18b9c3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"46dbcaf78844c7ab68226f705edbefa48418a2321dbaef9d0679f89ef18b9c3d","first_computed_at":"2026-07-05T00:24:18.086628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:24:18.086628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AOhaIQBwFDrHBd3ScCL6fyTq9rAn0JkBK7RGJkshtNnsTPa6rcS6cxMwUO/3Nc0s8MfwqAQqQpHbc6u3iIasDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:24:18.087126Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03341","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6dc6c6579e568b53f5b79c30a46cf4638773a0c1df03b58b6fda027fe85b68e","sha256:596eac77a9e4c05ebdcf4fdbdc1c0fe89e5a95c004c50e40c5cb383b7bc7315e"],"state_sha256":"bfbc9f09c10553c10ea9b0ffb9812eedabfdf9c49f8162aefc19caa5435d84a0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UIgF97S9lmhWn+ez0eZUVmu/H+oKPzUN/6XXic2khUSKffbsWB2eObsHolVK8I+thsNzcfcB/eQrNxYesiuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:15:45.815863Z","bundle_sha256":"de5cefc362d2bb38e3095a5943ae30ad62f18142a885fa63fe4821127e7a65ae"}}