{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VVUA2OKWXYW2KTGZC6G6DNPO3P","short_pith_number":"pith:VVUA2OKW","schema_version":"1.0","canonical_sha256":"ad680d3956be2da54cd9178de1b5eedbf5b7fb33aec9ded1242f85b68eea7140","source":{"kind":"arxiv","id":"2506.00332","version":2},"attestation_state":"computed","paper":{"title":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CL","authors_text":"Akshat Gupta, Insyirah Mujtahid, Kokil Jaidka, Svetlana Churina","submitted_at":"2025-05-31T01:09:04Z","abstract_excerpt":"Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. "},"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":"2506.00332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-31T01:09:04Z","cross_cats_sorted":["cs.SI"],"title_canon_sha256":"c2110f14c803bc73818651631e1f6d6b39bd1384f9ba54f22b8b736dbd6a1c88","abstract_canon_sha256":"81b176e0fc3e3a0679b3b3435320145e8f8c5d96ddbed6ad37e72a00ae3575b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:47.619971Z","signature_b64":"YLLH0HhpplYWY6NFr0v4idczddt9ouCzh/1gnUNz8cBr9Yo10CWGdXI9DlonvgDhTdS5+gtqy/IvKOgtD9mRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad680d3956be2da54cd9178de1b5eedbf5b7fb33aec9ded1242f85b68eea7140","last_reissued_at":"2026-07-05T11:21:47.619441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:47.619441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling Codemixing in Chats: The NUS ABC Codemixed Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SI"],"primary_cat":"cs.CL","authors_text":"Akshat Gupta, Insyirah Mujtahid, Kokil Jaidka, Svetlana Churina","submitted_at":"2025-05-31T01:09:04Z","abstract_excerpt":"Code-mixing involves the seamless integration of linguistic elements from multiple languages within a single discourse, reflecting natural multilingual communication patterns. Despite its prominence in informal interactions such as social media, chat messages and instant-messaging exchanges, there has been a lack of publicly available corpora that are author-labeled and suitable for modeling human conversations and relationships. This study introduces the first labeled and general-purpose corpus for understanding code-mixing in context while maintaining rigorous privacy and ethical standards. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00332","kind":"arxiv","version":2},"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/2506.00332/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":"2506.00332","created_at":"2026-07-05T11:21:47.619505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00332v2","created_at":"2026-07-05T11:21:47.619505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00332","created_at":"2026-07-05T11:21:47.619505+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVUA2OKWXYW2","created_at":"2026-07-05T11:21:47.619505+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVUA2OKWXYW2KTGZ","created_at":"2026-07-05T11:21:47.619505+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVUA2OKW","created_at":"2026-07-05T11:21:47.619505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30790","citing_title":"Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P","json":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P.json","graph_json":"https://pith.science/api/pith-number/VVUA2OKWXYW2KTGZC6G6DNPO3P/graph.json","events_json":"https://pith.science/api/pith-number/VVUA2OKWXYW2KTGZC6G6DNPO3P/events.json","paper":"https://pith.science/paper/VVUA2OKW"},"agent_actions":{"view_html":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P","download_json":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P.json","view_paper":"https://pith.science/paper/VVUA2OKW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00332&json=true","fetch_graph":"https://pith.science/api/pith-number/VVUA2OKWXYW2KTGZC6G6DNPO3P/graph.json","fetch_events":"https://pith.science/api/pith-number/VVUA2OKWXYW2KTGZC6G6DNPO3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P/action/storage_attestation","attest_author":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P/action/author_attestation","sign_citation":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P/action/citation_signature","submit_replication":"https://pith.science/pith/VVUA2OKWXYW2KTGZC6G6DNPO3P/action/replication_record"}},"created_at":"2026-07-05T11:21:47.619505+00:00","updated_at":"2026-07-05T11:21:47.619505+00:00"}