{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R66ETIMNFMM3D4DCYT4T4RYWNI","short_pith_number":"pith:R66ETIMN","schema_version":"1.0","canonical_sha256":"8fbc49a18d2b19b1f062c4f93e47166a2ee7e0bd2632a340cd44a1f0d2f4187b","source":{"kind":"arxiv","id":"2306.04964","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Phaltankar, Aryan Patil, Gauri Takawane, Mukta S. Takalikar, Raviraj Joshi, Varad Patwardhan","submitted_at":"2023-06-08T06:43:10Z","abstract_excerpt":"The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especially English with a regional language, on social media platforms. Existing deep-learning models do not take advantage of the implicit language information in the code-mixed text. Our study aims to improve BERT-based models performance on low-resource Code-Mixed Hindi-English Datasets by experimenting with language augmentation approaches. We propose a pipeline to improve code-mixed systems that comprise data preprocessi"},"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":"2306.04964","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T06:43:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8ec8d7df1e164eb1062dfdae2775660fe5eb44416d04e774a88e7655c27985d7","abstract_canon_sha256":"4943afc348352d65c21ae0d4fcef5a41b66babfaffc465e081766bb4c4f33cd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:44.085615Z","signature_b64":"/mHaYTqamqLzY35vGJMzzAcsGqja2Z1zL80qb6/SzfL/kYQ57Nxq/9unvHNv0KgaMLySfpynu3pjYmiR9m6LDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fbc49a18d2b19b1f062c4f93e47166a2ee7e0bd2632a340cd44a1f0d2f4187b","last_reissued_at":"2026-07-05T06:18:44.085128Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:44.085128Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Language Identification to Enhance Code-Mixed Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhishek Phaltankar, Aryan Patil, Gauri Takawane, Mukta S. Takalikar, Raviraj Joshi, Varad Patwardhan","submitted_at":"2023-06-08T06:43:10Z","abstract_excerpt":"The usage of more than one language in the same text is referred to as Code Mixed. It is evident that there is a growing degree of adaption of the use of code-mixed data, especially English with a regional language, on social media platforms. Existing deep-learning models do not take advantage of the implicit language information in the code-mixed text. Our study aims to improve BERT-based models performance on low-resource Code-Mixed Hindi-English Datasets by experimenting with language augmentation approaches. We propose a pipeline to improve code-mixed systems that comprise data preprocessi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.04964","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/2306.04964/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":"2306.04964","created_at":"2026-07-05T06:18:44.085184+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.04964v1","created_at":"2026-07-05T06:18:44.085184+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.04964","created_at":"2026-07-05T06:18:44.085184+00:00"},{"alias_kind":"pith_short_12","alias_value":"R66ETIMNFMM3","created_at":"2026-07-05T06:18:44.085184+00:00"},{"alias_kind":"pith_short_16","alias_value":"R66ETIMNFMM3D4DC","created_at":"2026-07-05T06:18:44.085184+00:00"},{"alias_kind":"pith_short_8","alias_value":"R66ETIMN","created_at":"2026-07-05T06:18:44.085184+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI","json":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI.json","graph_json":"https://pith.science/api/pith-number/R66ETIMNFMM3D4DCYT4T4RYWNI/graph.json","events_json":"https://pith.science/api/pith-number/R66ETIMNFMM3D4DCYT4T4RYWNI/events.json","paper":"https://pith.science/paper/R66ETIMN"},"agent_actions":{"view_html":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI","download_json":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI.json","view_paper":"https://pith.science/paper/R66ETIMN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.04964&json=true","fetch_graph":"https://pith.science/api/pith-number/R66ETIMNFMM3D4DCYT4T4RYWNI/graph.json","fetch_events":"https://pith.science/api/pith-number/R66ETIMNFMM3D4DCYT4T4RYWNI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI/action/storage_attestation","attest_author":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI/action/author_attestation","sign_citation":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI/action/citation_signature","submit_replication":"https://pith.science/pith/R66ETIMNFMM3D4DCYT4T4RYWNI/action/replication_record"}},"created_at":"2026-07-05T06:18:44.085184+00:00","updated_at":"2026-07-05T06:18:44.085184+00:00"}