{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TY327D4UHHLXAFYHPDFBZIH3HV","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":"26267a54a473b2f34beea29e13ff55920edbf5cbef8b6a5777dd5a4dccafabfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-28T16:36:41Z","title_canon_sha256":"2993d3480a76e30a3c2d01645044075ec2d643cec219821b8288fb5e27cb2da9"},"schema_version":"1.0","source":{"id":"2004.13640","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13640","created_at":"2026-07-05T00:59:01Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13640v1","created_at":"2026-07-05T00:59:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13640","created_at":"2026-07-05T00:59:01Z"},{"alias_kind":"pith_short_12","alias_value":"TY327D4UHHLX","created_at":"2026-07-05T00:59:01Z"},{"alias_kind":"pith_short_16","alias_value":"TY327D4UHHLXAFYH","created_at":"2026-07-05T00:59:01Z"},{"alias_kind":"pith_short_8","alias_value":"TY327D4U","created_at":"2026-07-05T00:59:01Z"}],"graph_snapshots":[{"event_id":"sha256:e4916fd15a00329f7981e922689cfcf27ba9b4e0465afb677702cb37eb6d8723","target":"graph","created_at":"2026-07-05T00:59:01Z","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/2004.13640/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual BERT (M-BERT) has been a huge success in both supervised and zero-shot cross-lingual transfer learning. However, this success has focused only on the top 104 languages in Wikipedia that it was trained on. In this paper, we propose a simple but effective approach to extend M-BERT (E-BERT) so that it can benefit any new language, and show that our approach benefits languages that are already in M-BERT as well. We perform an extensive set of experiments with Named Entity Recognition (NER) on 27 languages, only 16 of which are in M-BERT, and show an average increase of about 6% F1 on ","authors_text":"Dan Roth, Karthikeyan K, Stephen Mayhew, Zihan Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-28T16:36:41Z","title":"Extending Multilingual BERT to Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13640","kind":"arxiv","version":1},"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":"sha256:0ced41218517b53519c6f49628d5ed796371711d54ed3c87243365a4e3333193","target":"record","created_at":"2026-07-05T00:59:01Z","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":"26267a54a473b2f34beea29e13ff55920edbf5cbef8b6a5777dd5a4dccafabfc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-28T16:36:41Z","title_canon_sha256":"2993d3480a76e30a3c2d01645044075ec2d643cec219821b8288fb5e27cb2da9"},"schema_version":"1.0","source":{"id":"2004.13640","kind":"arxiv","version":1}},"canonical_sha256":"9e37af8f9439d770170778ca1ca0fb3d646fa6a412027b7964058478b61300f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e37af8f9439d770170778ca1ca0fb3d646fa6a412027b7964058478b61300f3","first_computed_at":"2026-07-05T00:59:01.500143Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:01.500143Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fClUvwPS4xTHwGPwtN6hYphhzSyVtcEOW9iFCAvi1JNm86JMUgTw3yFfu0gwkl49oNVr/bHVtsBndjjF2DqRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:01.500499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13640","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ced41218517b53519c6f49628d5ed796371711d54ed3c87243365a4e3333193","sha256:e4916fd15a00329f7981e922689cfcf27ba9b4e0465afb677702cb37eb6d8723"],"state_sha256":"b16fd12c6d55778098460a2e9ed9168a91119d1e8db7a99013a50136c0d83cd3"}