{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WB7J2Q4UKVVJK7ZJNSWGSMUSKB","short_pith_number":"pith:WB7J2Q4U","schema_version":"1.0","canonical_sha256":"b07e9d4394556a957f296cac693292506870983d8c23cbdf82ededcd1759cfef","source":{"kind":"arxiv","id":"2503.07990","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Multilingual Language Models for Code-Switched Input Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katherine Xie, Nitya Babbar, Vicky Chen, Yoanna Turura","submitted_at":"2025-03-11T02:49:41Z","abstract_excerpt":"Code-switching, or alternating between languages within a single conversation, presents challenges for multilingual language models on NLP tasks. This research investigates if pre-training Multilingual BERT (mBERT) on code-switched datasets improves the model's performance on critical NLP tasks such as part of speech tagging, sentiment analysis, named entity recognition, and language identification. We use a dataset of Spanglish tweets for pre-training and evaluate the pre-trained model against a baseline model.\n  Our findings show that our pre-trained mBERT model outperforms or matches the ba"},"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":"2503.07990","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T02:49:41Z","cross_cats_sorted":[],"title_canon_sha256":"a26d75789aa9fe0899230d7e66d7d18ba70d14c67a48e4058a80be709b997e8b","abstract_canon_sha256":"671212c0329c61a9103ee15aac90126ec778f63d6b174c0a87882da1500fb228"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:48.168809Z","signature_b64":"+XDDnnL09abmFK4zCgEehyp2+5Ybk5HZAIQih0HtW98aN1QG5v/VX2+Uij0FagtWJn02pJSG1sw2oCPxlU0JBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b07e9d4394556a957f296cac693292506870983d8c23cbdf82ededcd1759cfef","last_reissued_at":"2026-07-05T10:28:48.168291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:48.168291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Multilingual Language Models for Code-Switched Input Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katherine Xie, Nitya Babbar, Vicky Chen, Yoanna Turura","submitted_at":"2025-03-11T02:49:41Z","abstract_excerpt":"Code-switching, or alternating between languages within a single conversation, presents challenges for multilingual language models on NLP tasks. This research investigates if pre-training Multilingual BERT (mBERT) on code-switched datasets improves the model's performance on critical NLP tasks such as part of speech tagging, sentiment analysis, named entity recognition, and language identification. We use a dataset of Spanglish tweets for pre-training and evaluate the pre-trained model against a baseline model.\n  Our findings show that our pre-trained mBERT model outperforms or matches the ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07990","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/2503.07990/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":"2503.07990","created_at":"2026-07-05T10:28:48.168364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07990v1","created_at":"2026-07-05T10:28:48.168364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07990","created_at":"2026-07-05T10:28:48.168364+00:00"},{"alias_kind":"pith_short_12","alias_value":"WB7J2Q4UKVVJ","created_at":"2026-07-05T10:28:48.168364+00:00"},{"alias_kind":"pith_short_16","alias_value":"WB7J2Q4UKVVJK7ZJ","created_at":"2026-07-05T10:28:48.168364+00:00"},{"alias_kind":"pith_short_8","alias_value":"WB7J2Q4U","created_at":"2026-07-05T10:28:48.168364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20279","citing_title":"What Language(s) Does Aya-23 Think In? How Multilinguality Affects Internal Language Representations","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB","json":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB.json","graph_json":"https://pith.science/api/pith-number/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/graph.json","events_json":"https://pith.science/api/pith-number/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/events.json","paper":"https://pith.science/paper/WB7J2Q4U"},"agent_actions":{"view_html":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB","download_json":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB.json","view_paper":"https://pith.science/paper/WB7J2Q4U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07990&json=true","fetch_graph":"https://pith.science/api/pith-number/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/graph.json","fetch_events":"https://pith.science/api/pith-number/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/action/storage_attestation","attest_author":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/action/author_attestation","sign_citation":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/action/citation_signature","submit_replication":"https://pith.science/pith/WB7J2Q4UKVVJK7ZJNSWGSMUSKB/action/replication_record"}},"created_at":"2026-07-05T10:28:48.168364+00:00","updated_at":"2026-07-05T10:28:48.168364+00:00"}