{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MTCHCM255R5K5TFFJTAPH7R476","short_pith_number":"pith:MTCHCM25","schema_version":"1.0","canonical_sha256":"64c471335dec7aaecca54cc0f3fe3cff958cc004e8c23f032fb56ddc4a2cb864","source":{"kind":"arxiv","id":"2506.07274","version":1},"attestation_state":"computed","paper":{"title":"Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carlos G\\'omez-Rodr\\'iguez, Muhammad Imran, Nelvin Licona-Guevara, Nemika Tyagi, Olga Kellert","submitted_at":"2025-06-08T20:23:57Z","abstract_excerpt":"Code-switching presents a complex challenge for syntactic analysis, especially in low-resource language settings where annotated data is scarce. While recent work has explored the use of large language models (LLMs) for sequence-level tagging, few approaches systematically investigate how well these models capture syntactic structure in code-switched contexts. Moreover, existing parsers trained on monolingual treebanks often fail to generalize to multilingual and mixed-language input. To address this gap, we introduce the BiLingua Parser, an LLM-based annotation pipeline designed to produce Un"},"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":"2506.07274","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-08T20:23:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2748c645e0abb1fb107bcd64ea0b8c2791c26bf3ee313077612d337d12c23d73","abstract_canon_sha256":"a2c70cf6b77ce9649dcfb82317d6cc1b90018740a430792c5b3db499507de001"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:24.261702Z","signature_b64":"9Ne3LOFkPL/VwHKQBu6AWkhlXROisxUmO/XIccztHV3SMlepd4vjy5yyhdlQUeyPFNlQ29SAqHla5Zd5uFMaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64c471335dec7aaecca54cc0f3fe3cff958cc004e8c23f032fb56ddc4a2cb864","last_reissued_at":"2026-07-05T11:18:24.261202Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:24.261202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parsing the Switch: LLM-Based UD Annotation for Complex Code-Switched and Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Carlos G\\'omez-Rodr\\'iguez, Muhammad Imran, Nelvin Licona-Guevara, Nemika Tyagi, Olga Kellert","submitted_at":"2025-06-08T20:23:57Z","abstract_excerpt":"Code-switching presents a complex challenge for syntactic analysis, especially in low-resource language settings where annotated data is scarce. While recent work has explored the use of large language models (LLMs) for sequence-level tagging, few approaches systematically investigate how well these models capture syntactic structure in code-switched contexts. Moreover, existing parsers trained on monolingual treebanks often fail to generalize to multilingual and mixed-language input. To address this gap, we introduce the BiLingua Parser, an LLM-based annotation pipeline designed to produce Un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07274","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/2506.07274/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":"2506.07274","created_at":"2026-07-05T11:18:24.261261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07274v1","created_at":"2026-07-05T11:18:24.261261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07274","created_at":"2026-07-05T11:18:24.261261+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTCHCM255R5K","created_at":"2026-07-05T11:18:24.261261+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTCHCM255R5K5TFF","created_at":"2026-07-05T11:18:24.261261+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTCHCM25","created_at":"2026-07-05T11:18:24.261261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.07037","citing_title":"Beyond Monolingual Assumptions: A Survey of Code-Switched NLP in the Era of Large Language Models across Modalities","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476","json":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476.json","graph_json":"https://pith.science/api/pith-number/MTCHCM255R5K5TFFJTAPH7R476/graph.json","events_json":"https://pith.science/api/pith-number/MTCHCM255R5K5TFFJTAPH7R476/events.json","paper":"https://pith.science/paper/MTCHCM25"},"agent_actions":{"view_html":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476","download_json":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476.json","view_paper":"https://pith.science/paper/MTCHCM25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07274&json=true","fetch_graph":"https://pith.science/api/pith-number/MTCHCM255R5K5TFFJTAPH7R476/graph.json","fetch_events":"https://pith.science/api/pith-number/MTCHCM255R5K5TFFJTAPH7R476/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476/action/storage_attestation","attest_author":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476/action/author_attestation","sign_citation":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476/action/citation_signature","submit_replication":"https://pith.science/pith/MTCHCM255R5K5TFFJTAPH7R476/action/replication_record"}},"created_at":"2026-07-05T11:18:24.261261+00:00","updated_at":"2026-07-05T11:18:24.261261+00:00"}