{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WB7J2Q4UKVVJK7ZJNSWGSMUSKB","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":"671212c0329c61a9103ee15aac90126ec778f63d6b174c0a87882da1500fb228","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T02:49:41Z","title_canon_sha256":"a26d75789aa9fe0899230d7e66d7d18ba70d14c67a48e4058a80be709b997e8b"},"schema_version":"1.0","source":{"id":"2503.07990","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07990","created_at":"2026-07-05T10:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07990v1","created_at":"2026-07-05T10:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07990","created_at":"2026-07-05T10:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"WB7J2Q4UKVVJ","created_at":"2026-07-05T10:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"WB7J2Q4UKVVJK7ZJ","created_at":"2026-07-05T10:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"WB7J2Q4U","created_at":"2026-07-05T10:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:024e506c07b9d3a2a313dd21e58b24fcbd7fa26996bcead5545eced199d919bc","target":"graph","created_at":"2026-07-05T10:28:48Z","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/2503.07990/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Katherine Xie, Nitya Babbar, Vicky Chen, Yoanna Turura","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T02:49:41Z","title":"Enhancing Multilingual Language Models for Code-Switched Input Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07990","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":"sha256:362dd5b2eb5e3c0adb8e1bbe90ac164e04159a3dad6534feb94099e1205e2c79","target":"record","created_at":"2026-07-05T10:28:48Z","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":"671212c0329c61a9103ee15aac90126ec778f63d6b174c0a87882da1500fb228","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-11T02:49:41Z","title_canon_sha256":"a26d75789aa9fe0899230d7e66d7d18ba70d14c67a48e4058a80be709b997e8b"},"schema_version":"1.0","source":{"id":"2503.07990","kind":"arxiv","version":1}},"canonical_sha256":"b07e9d4394556a957f296cac693292506870983d8c23cbdf82ededcd1759cfef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b07e9d4394556a957f296cac693292506870983d8c23cbdf82ededcd1759cfef","first_computed_at":"2026-07-05T10:28:48.168291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:48.168291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+XDDnnL09abmFK4zCgEehyp2+5Ybk5HZAIQih0HtW98aN1QG5v/VX2+Uij0FagtWJn02pJSG1sw2oCPxlU0JBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:48.168809Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07990","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:362dd5b2eb5e3c0adb8e1bbe90ac164e04159a3dad6534feb94099e1205e2c79","sha256:024e506c07b9d3a2a313dd21e58b24fcbd7fa26996bcead5545eced199d919bc"],"state_sha256":"487efedd034a3d012022efc4ea424029364376d03949678d3b9a0b72439f4b27"}