{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5UCF4LJ3IBUJ7CGMZC2M27F3FE","short_pith_number":"pith:5UCF4LJ3","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"},"canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","source":{"kind":"arxiv","id":"2602.09388","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09388","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09388v2","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09388","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"5UCF4LJ3IBUJ","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"5UCF4LJ3IBUJ7CGM","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"5UCF4LJ3","created_at":"2026-06-04T01:08:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5UCF4LJ3IBUJ7CGMZC2M27F3FE","target":"record","payload":{"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"},"canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","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"},"source_kind":"arxiv","source_id":"2602.09388","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":"2026-06-04T01:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0flIwQNUqRwAzL0FLrlVWtGAL56ZvZfD+jmhrapDHTri/zAIeG2CeQnWjeZqotNUc5BwW1AyiHEnLZYBCwqiAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:30:56.669988Z"},"content_sha256":"0ebe1bd06fe2220232b4e46c09f2b4156d82f43dab5b200ab96c454af5ca020a","schema_version":"1.0","event_id":"sha256:0ebe1bd06fe2220232b4e46c09f2b4156d82f43dab5b200ab96c454af5ca020a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5UCF4LJ3IBUJ7CGMZC2M27F3FE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w1/fKUPDS6iFhREllywHtQkjqoqSayP9oylhNL8DhoLzpIQlfhQCE33gk26GOIA1AKRPNGWa+h4UsNd5p+ajCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:30:56.670894Z"},"content_sha256":"7e16f95c2abb87972124a0f3f511475e53666a5006936cdc36ad9c461728d264","schema_version":"1.0","event_id":"sha256:7e16f95c2abb87972124a0f3f511475e53666a5006936cdc36ad9c461728d264"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/bundle.json","state_url":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/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":"2026-08-04T21:30:56Z","links":{"resolver":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE","bundle":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/bundle.json","state":"https://pith.science/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5UCF4LJ3IBUJ7CGMZC2M27F3FE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5UCF4LJ3IBUJ7CGMZC2M27F3FE","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":"453bd1651a5fbb0871f479d98aee6347cab7f1e98e64e8b774b753862e6938d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T03:57:07Z","title_canon_sha256":"334195ff0f8bbb4c7f9740c16ee8386ea6810629c1c867eb2319a9dd4a4f8e18"},"schema_version":"1.0","source":{"id":"2602.09388","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.09388","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2602.09388v2","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09388","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"5UCF4LJ3IBUJ","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"5UCF4LJ3IBUJ7CGM","created_at":"2026-06-04T01:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"5UCF4LJ3","created_at":"2026-06-04T01:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:7e16f95c2abb87972124a0f3f511475e53666a5006936cdc36ad9c461728d264","target":"graph","created_at":"2026-06-04T01:08:41Z","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/2602.09388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jianyu Zheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T03:57:07Z","title":"Effective vocabulary expansion of multilingual language models for extremely low-resource languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09388","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":"sha256:0ebe1bd06fe2220232b4e46c09f2b4156d82f43dab5b200ab96c454af5ca020a","target":"record","created_at":"2026-06-04T01:08:41Z","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":"453bd1651a5fbb0871f479d98aee6347cab7f1e98e64e8b774b753862e6938d1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-02-10T03:57:07Z","title_canon_sha256":"334195ff0f8bbb4c7f9740c16ee8386ea6810629c1c867eb2319a9dd4a4f8e18"},"schema_version":"1.0","source":{"id":"2602.09388","kind":"arxiv","version":2}},"canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed045e2d3b40689f88ccc8b4cd7cbb292abf9b12a25b0aba03caa2cfbea87dd8","first_computed_at":"2026-06-04T01:08:41.687439Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:41.687439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TkFf7hvfiGf4Ik78ibYfOLBCUp++RqrMb4udzhPOH7WMmotDMRcQa0FDk1rk+D0DYm+rOLC7eCCPUaxMtdTvDg==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:41.687964Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.09388","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ebe1bd06fe2220232b4e46c09f2b4156d82f43dab5b200ab96c454af5ca020a","sha256:7e16f95c2abb87972124a0f3f511475e53666a5006936cdc36ad9c461728d264"],"state_sha256":"eeb75d85b85dc598435adbfc1b5e9ac0f14d592ee9c6dc3b8cfba5ebb81f78d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JL3ebAv97dTfyoA/Vupeh8SOEaL/LtWQnn3aqdDR4aRDge+nbOkA1jGtAYlGJTIhD1rr/JqUHA+ypStmBHwzBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:30:56.676109Z","bundle_sha256":"bbbad551da73b77d7708a326617614361b0b0406c4c10653d22403bdf85050a6"}}