{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:ES4GBLUYHRS66JHSZTAEGBRYJ2","short_pith_number":"pith:ES4GBLUY","canonical_record":{"source":{"id":"2012.15671","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"132253b930f91d8f6e00c0000fb1bc8681bc97cb7aa33a96510586c3d3953c89","abstract_canon_sha256":"33a6fe49aae4fea806ee955d056c32dd145987c3665a7b509eb556b023dfe8b5"},"schema_version":"1.0"},"canonical_sha256":"24b860ae983c65ef24f2ccc04306384ea143b049b45854cb67133c98fc6f7659","source":{"kind":"arxiv","id":"2012.15671","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15671","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15671v5","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15671","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"ES4GBLUYHRS6","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"ES4GBLUYHRS66JHS","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"ES4GBLUY","created_at":"2026-07-05T03:35:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:ES4GBLUYHRS66JHSZTAEGBRYJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2012.15671","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"132253b930f91d8f6e00c0000fb1bc8681bc97cb7aa33a96510586c3d3953c89","abstract_canon_sha256":"33a6fe49aae4fea806ee955d056c32dd145987c3665a7b509eb556b023dfe8b5"},"schema_version":"1.0"},"canonical_sha256":"24b860ae983c65ef24f2ccc04306384ea143b049b45854cb67133c98fc6f7659","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:08.092252Z","signature_b64":"qgweLKeLEb6kxe5QXKCUUQZqeAi5JyQ3VArKKrxDMPlqorf1k2a1uMKohhzhflRo22NXK+4v0CcJCuhIyiL6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b860ae983c65ef24f2ccc04306384ea143b049b45854cb67133c98fc6f7659","last_reissued_at":"2026-07-05T03:35:08.091760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:08.091760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.15671","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VyUImvvCO0IOWhv7IfC+mdStcERcjlPLHuWl85Tz8m99R2jRcgsP8CuJ14pm+dU23HCaY3BLwAEKu8JcjS+JBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:25:05.366905Z"},"content_sha256":"f446f0f4cccfbcafc5aec6f17efd8cccf0a0bdcc1de42a7bce64275624f0c456","schema_version":"1.0","event_id":"sha256:f446f0f4cccfbcafc5aec6f17efd8cccf0a0bdcc1de42a7bce64275624f0c456"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:ES4GBLUYHRS66JHSZTAEGBRYJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vocabulary Learning via Optimal Transport for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chun Gan, Hao Zhou, Jingjing Xu, Lei Li, Zaixiang Zheng","submitted_at":"2020-12-31T15:49:49Z","abstract_excerpt":"The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of the role of vocabulary from the perspective of information theory. Motivated by this, we formulate the quest of vocabularization -- finding the best token dictionary with a proper size -- as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15671","kind":"arxiv","version":5},"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/2012.15671/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":"2026-07-05T03:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AN/0ubIkZUBHHvOb57sRPdL5wb/fbvrPru2AQrXBqbJanlAO+EcOQVtrRlYRVcyX5Y70AH2oLI3sTSDzvmsoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T20:25:05.367481Z"},"content_sha256":"852a0cb618b4b4443f862e314d1d207070561107df7716040e1af7a21ce9476e","schema_version":"1.0","event_id":"sha256:852a0cb618b4b4443f862e314d1d207070561107df7716040e1af7a21ce9476e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/bundle.json","state_url":"https://pith.science/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/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":"2026-08-20T20:25:05Z","links":{"resolver":"https://pith.science/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2","bundle":"https://pith.science/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/bundle.json","state":"https://pith.science/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ES4GBLUYHRS66JHSZTAEGBRYJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ES4GBLUYHRS66JHSZTAEGBRYJ2","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":"33a6fe49aae4fea806ee955d056c32dd145987c3665a7b509eb556b023dfe8b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:49:49Z","title_canon_sha256":"132253b930f91d8f6e00c0000fb1bc8681bc97cb7aa33a96510586c3d3953c89"},"schema_version":"1.0","source":{"id":"2012.15671","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.15671","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.15671v5","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.15671","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"ES4GBLUYHRS6","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"ES4GBLUYHRS66JHS","created_at":"2026-07-05T03:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"ES4GBLUY","created_at":"2026-07-05T03:35:08Z"}],"graph_snapshots":[{"event_id":"sha256:852a0cb618b4b4443f862e314d1d207070561107df7716040e1af7a21ce9476e","target":"graph","created_at":"2026-07-05T03:35:08Z","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/2012.15671/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The choice of token vocabulary affects the performance of machine translation. This paper aims to figure out what is a good vocabulary and whether one can find the optimal vocabulary without trial training. To answer these questions, we first provide an alternative understanding of the role of vocabulary from the perspective of information theory. Motivated by this, we formulate the quest of vocabularization -- finding the best token dictionary with a proper size -- as an optimal transport (OT) problem. We propose VOLT, a simple and efficient solution without trial training. Empirical results ","authors_text":"Chun Gan, Hao Zhou, Jingjing Xu, Lei Li, Zaixiang Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:49:49Z","title":"Vocabulary Learning via Optimal Transport for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.15671","kind":"arxiv","version":5},"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:f446f0f4cccfbcafc5aec6f17efd8cccf0a0bdcc1de42a7bce64275624f0c456","target":"record","created_at":"2026-07-05T03:35:08Z","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":"33a6fe49aae4fea806ee955d056c32dd145987c3665a7b509eb556b023dfe8b5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-12-31T15:49:49Z","title_canon_sha256":"132253b930f91d8f6e00c0000fb1bc8681bc97cb7aa33a96510586c3d3953c89"},"schema_version":"1.0","source":{"id":"2012.15671","kind":"arxiv","version":5}},"canonical_sha256":"24b860ae983c65ef24f2ccc04306384ea143b049b45854cb67133c98fc6f7659","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b860ae983c65ef24f2ccc04306384ea143b049b45854cb67133c98fc6f7659","first_computed_at":"2026-07-05T03:35:08.091760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:35:08.091760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qgweLKeLEb6kxe5QXKCUUQZqeAi5JyQ3VArKKrxDMPlqorf1k2a1uMKohhzhflRo22NXK+4v0CcJCuhIyiL6AA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:35:08.092252Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.15671","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f446f0f4cccfbcafc5aec6f17efd8cccf0a0bdcc1de42a7bce64275624f0c456","sha256:852a0cb618b4b4443f862e314d1d207070561107df7716040e1af7a21ce9476e"],"state_sha256":"08e4b075aa77732d212adaab03c5a10ecff6d3741846b275eb9596a9c29f6baf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7ar2g4W3SxPWUoWrQegRcG2PNsnsou+JEmbKD0d4PzZl3K870q9I5Vt/H5QYWXBQnbwIJ9jHrC9IaQ1kLIBXDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T20:25:05.372698Z","bundle_sha256":"b0a2795ec3f0fc5ab0976bcf92bc3cb09b9ed922fc5129e2aa1bc16f2cf01942"}}