{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VSZXNJTFUPVQKAFHZAY7SH2ANO","short_pith_number":"pith:VSZXNJTF","schema_version":"1.0","canonical_sha256":"acb376a665a3eb0500a7c831f91f406bb67c43904af9c4a161ef9e60de3499d0","source":{"kind":"arxiv","id":"2506.14012","version":1},"attestation_state":"computed","paper":{"title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Mohamed, Guokan Shang, Michalis Vazirgiannis, Yang Zhang","submitted_at":"2025-06-16T21:19:27Z","abstract_excerpt":"Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly prevalent in online content, where users naturally mix languages in everyday communication. As a result, Large Language Models (LLMs), now central to content processing and generation, are frequently exposed to code-switched inputs. Given their widespread use, it is crucial to understand how LLMs process and reason about such mixed-language text. This paper presents a systematic evaluation of LLM comprehension under "},"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":"2506.14012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-16T21:19:27Z","cross_cats_sorted":[],"title_canon_sha256":"942572f046ffb39c76054c2817c65a833b5c6dc9a6896f315a691d7a9655591f","abstract_canon_sha256":"662048346ece235bc5ff5eb4c6734303b9b51942678b0b77d33c102293eed2e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:47.330543Z","signature_b64":"tDAy8ZxcantZLRu0ZG8glE4RBPuTDlVG2mp9E0iqf9scp13YtTI4skFASo0UiWTS+RRoAmeqEkx39yh/FwC3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acb376a665a3eb0500a7c831f91f406bb67c43904af9c4a161ef9e60de3499d0","last_reissued_at":"2026-07-05T11:22:47.330030Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:47.330030Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in the Mix: Evaluating LLM Understanding of Code-Switched Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amr Mohamed, Guokan Shang, Michalis Vazirgiannis, Yang Zhang","submitted_at":"2025-06-16T21:19:27Z","abstract_excerpt":"Code-switching (CSW) is the act of alternating between two or more languages within a single discourse. This phenomenon is widespread in multilingual communities, and increasingly prevalent in online content, where users naturally mix languages in everyday communication. As a result, Large Language Models (LLMs), now central to content processing and generation, are frequently exposed to code-switched inputs. Given their widespread use, it is crucial to understand how LLMs process and reason about such mixed-language text. This paper presents a systematic evaluation of LLM comprehension under "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.14012","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/2506.14012/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":"2506.14012","created_at":"2026-07-05T11:22:47.330091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.14012v1","created_at":"2026-07-05T11:22:47.330091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.14012","created_at":"2026-07-05T11:22:47.330091+00:00"},{"alias_kind":"pith_short_12","alias_value":"VSZXNJTFUPVQ","created_at":"2026-07-05T11:22:47.330091+00:00"},{"alias_kind":"pith_short_16","alias_value":"VSZXNJTFUPVQKAFH","created_at":"2026-07-05T11:22:47.330091+00:00"},{"alias_kind":"pith_short_8","alias_value":"VSZXNJTF","created_at":"2026-07-05T11:22:47.330091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07422","citing_title":"The Masked Advantage: Uncovering Local-Language Access to Cultural Knowledge in LLMs","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04127","citing_title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.10670","citing_title":"Towards Fine-Grained Code-Switch Speech Translation with Semantic Space Alignment","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11181","citing_title":"Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04127","citing_title":"Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO","json":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO.json","graph_json":"https://pith.science/api/pith-number/VSZXNJTFUPVQKAFHZAY7SH2ANO/graph.json","events_json":"https://pith.science/api/pith-number/VSZXNJTFUPVQKAFHZAY7SH2ANO/events.json","paper":"https://pith.science/paper/VSZXNJTF"},"agent_actions":{"view_html":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO","download_json":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO.json","view_paper":"https://pith.science/paper/VSZXNJTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.14012&json=true","fetch_graph":"https://pith.science/api/pith-number/VSZXNJTFUPVQKAFHZAY7SH2ANO/graph.json","fetch_events":"https://pith.science/api/pith-number/VSZXNJTFUPVQKAFHZAY7SH2ANO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO/action/storage_attestation","attest_author":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO/action/author_attestation","sign_citation":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO/action/citation_signature","submit_replication":"https://pith.science/pith/VSZXNJTFUPVQKAFHZAY7SH2ANO/action/replication_record"}},"created_at":"2026-07-05T11:22:47.330091+00:00","updated_at":"2026-07-05T11:22:47.330091+00:00"}