{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VZPRE4B5QTC6PWBAFRWP66TZB3","short_pith_number":"pith:VZPRE4B5","schema_version":"1.0","canonical_sha256":"ae5f12703d84c5e7d8202c6cff7a790ef57a1f61689da8e7062a5c140aa7f9bd","source":{"kind":"arxiv","id":"2010.12777","version":1},"attestation_state":"computed","paper":{"title":"Improving Multilingual Models with Language-Clustered Vocabularies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Garrette, Hyung Won Chung, Jason Riesa, Kiat Chuan Tan","submitted_at":"2020-10-24T04:49:15Z","abstract_excerpt":"State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating those vocabularies are not ideal for massively multilingual applications. In this work, we introduce a novel procedure for multilingual vocabulary generation that combines the separately trained vocabularies of several automatically derived language clusters, thus balancing the trade-off between cross-lingual subword sharing and language-specific vocabularies. Our experiments show improvements across languages on key"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2010.12777","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T04:49:15Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7855866dcad8d95a935d77c5c8f3747ed5f07e9182dae0adcd72fac7dc96e906","abstract_canon_sha256":"900fb5b5555f29880867adb5f965c806caa87204d41a371082cf609c68fa68dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:45:48.210418Z","signature_b64":"kGd34F/tk+TsWXAOVG9MHOGtvVyI2NDL0Ht/yRxbmz8d9rxcNyASTSPCgfyTSKY5zs3tCNDm8mKpxg1WVMiiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae5f12703d84c5e7d8202c6cff7a790ef57a1f61689da8e7062a5c140aa7f9bd","last_reissued_at":"2026-07-05T01:45:48.210063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:45:48.210063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Multilingual Models with Language-Clustered Vocabularies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dan Garrette, Hyung Won Chung, Jason Riesa, Kiat Chuan Tan","submitted_at":"2020-10-24T04:49:15Z","abstract_excerpt":"State-of-the-art multilingual models depend on vocabularies that cover all of the languages the model will expect to see at inference time, but the standard methods for generating those vocabularies are not ideal for massively multilingual applications. In this work, we introduce a novel procedure for multilingual vocabulary generation that combines the separately trained vocabularies of several automatically derived language clusters, thus balancing the trade-off between cross-lingual subword sharing and language-specific vocabularies. Our experiments show improvements across languages on key"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12777","kind":"arxiv","version":1},"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/2010.12777/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2010.12777","created_at":"2026-07-05T01:45:48.210125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12777v1","created_at":"2026-07-05T01:45:48.210125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12777","created_at":"2026-07-05T01:45:48.210125+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZPRE4B5QTC6","created_at":"2026-07-05T01:45:48.210125+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZPRE4B5QTC6PWBA","created_at":"2026-07-05T01:45:48.210125+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZPRE4B5","created_at":"2026-07-05T01:45:48.210125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3","json":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3.json","graph_json":"https://pith.science/api/pith-number/VZPRE4B5QTC6PWBAFRWP66TZB3/graph.json","events_json":"https://pith.science/api/pith-number/VZPRE4B5QTC6PWBAFRWP66TZB3/events.json","paper":"https://pith.science/paper/VZPRE4B5"},"agent_actions":{"view_html":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3","download_json":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3.json","view_paper":"https://pith.science/paper/VZPRE4B5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12777&json=true","fetch_graph":"https://pith.science/api/pith-number/VZPRE4B5QTC6PWBAFRWP66TZB3/graph.json","fetch_events":"https://pith.science/api/pith-number/VZPRE4B5QTC6PWBAFRWP66TZB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3/action/storage_attestation","attest_author":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3/action/author_attestation","sign_citation":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3/action/citation_signature","submit_replication":"https://pith.science/pith/VZPRE4B5QTC6PWBAFRWP66TZB3/action/replication_record"}},"created_at":"2026-07-05T01:45:48.210125+00:00","updated_at":"2026-07-05T01:45:48.210125+00:00"}