{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5UCF4LJ3IBUJ7CGMZC2M27F3FE","short_pith_number":"pith:5UCF4LJ3","schema_version":"1.0","canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","source":{"kind":"arxiv","id":"2602.09388","version":2},"attestation_state":"computed","paper":{"title":"Effective vocabulary expansion of multilingual language models for extremely low-resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianyu Zheng","submitted_at":"2026-02-10T03:57:07Z","abstract_excerpt":"Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models. However, few works address how to extend mPLMs to low-resource languages that were previously unsupported. To tackle this issue, we expand the model's vocabulary using a target language corpus. We then screen out a subset from the model's original vocabulary, which is biased towards representing the source language(e.g. English), and utilize bilingual dictionarie"},"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":"2602.09388","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T03:57:07Z","cross_cats_sorted":[],"title_canon_sha256":"334195ff0f8bbb4c7f9740c16ee8386ea6810629c1c867eb2319a9dd4a4f8e18","abstract_canon_sha256":"453bd1651a5fbb0871f479d98aee6347cab7f1e98e64e8b774b753862e6938d1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:41.687964Z","signature_b64":"TkFf7hvfiGf4Ik78ibYfOLBCUp++RqrMb4udzhPOH7WMmotDMRcQa0FDk1rk+D0DYm+rOLC7eCCPUaxMtdTvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","last_reissued_at":"2026-06-04T01:08:41.687439Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:41.687439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective vocabulary expansion of multilingual language models for extremely low-resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianyu Zheng","submitted_at":"2026-02-10T03:57:07Z","abstract_excerpt":"Multilingual pre-trained language models(mPLMs) offer significant benefits for many low-resource languages. To further expand the range of languages these models can support, many works focus on continued pre-training of these models. However, few works address how to extend mPLMs to low-resource languages that were previously unsupported. To tackle this issue, we expand the model's vocabulary using a target language corpus. We then screen out a subset from the model's original vocabulary, which is biased towards representing the source language(e.g. English), and utilize bilingual dictionarie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09388","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/2602.09388/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":"2602.09388","created_at":"2026-06-04T01:08:41.687507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.09388v2","created_at":"2026-06-04T01:08:41.687507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09388","created_at":"2026-06-04T01:08:41.687507+00:00"},{"alias_kind":"pith_short_12","alias_value":"5UCF4LJ3IBUJ","created_at":"2026-06-04T01:08:41.687507+00:00"},{"alias_kind":"pith_short_16","alias_value":"5UCF4LJ3IBUJ7CGM","created_at":"2026-06-04T01:08:41.687507+00:00"},{"alias_kind":"pith_short_8","alias_value":"5UCF4LJ3","created_at":"2026-06-04T01:08:41.687507+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/5UCF4LJ3IBUJ7CGMZC2M27F3FE","json":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE.json","graph_json":"https://pith.science/api/pith-number/5UCF4LJ3IBUJ7CGMZC2M27F3FE/graph.json","events_json":"https://pith.science/api/pith-number/5UCF4LJ3IBUJ7CGMZC2M27F3FE/events.json","paper":"https://pith.science/paper/5UCF4LJ3"},"agent_actions":{"view_html":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE","download_json":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE.json","view_paper":"https://pith.science/paper/5UCF4LJ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.09388&json=true","fetch_graph":"https://pith.science/api/pith-number/5UCF4LJ3IBUJ7CGMZC2M27F3FE/graph.json","fetch_events":"https://pith.science/api/pith-number/5UCF4LJ3IBUJ7CGMZC2M27F3FE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/action/storage_attestation","attest_author":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/action/author_attestation","sign_citation":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/action/citation_signature","submit_replication":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/action/replication_record"}},"created_at":"2026-06-04T01:08:41.687507+00:00","updated_at":"2026-06-04T01:08:41.687507+00:00"}