{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4QM7ZOQIDLY2CK2EPYCSWI2YXE","short_pith_number":"pith:4QM7ZOQI","schema_version":"1.0","canonical_sha256":"e419fcba081af1a12b447e052b2358b93010e94448e084f1fe22374fdfff28c0","source":{"kind":"arxiv","id":"2305.15722","version":2},"attestation_state":"computed","paper":{"title":"Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data","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, Raviraj Joshi, Varad Patwardhan","submitted_at":"2023-05-25T05:10:28Z","abstract_excerpt":"The term \"Code Mixed\" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect foreign elements in a language and process them correctly, as a considerable number of individuals are using code-mixed languages that could not be comprehended by understanding one of those languages. In this work, we focus on low-resource Hindi-English code-mixed language and enhancing the performance of different code-mixed natural language processing tasks su"},"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":"2305.15722","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-25T05:10:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c559c5f7a345fab2740d6a84390fb9c64122df85232929cf522413f5cf53abf4","abstract_canon_sha256":"6f255740af1b322762b31a94fddd06b74642d6420942b87c49052dd85f666577"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:11.399688Z","signature_b64":"+tJ4Qdk0Z8ND68bzktQumJoScqui1BfPEE7yoC+FxdFZNgRHHGKPfV0DHY4AYEw8n2PgMVJO4IkSj0p8fBjGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e419fcba081af1a12b447e052b2358b93010e94448e084f1fe22374fdfff28c0","last_reissued_at":"2026-07-05T06:14:11.399146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:11.399146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative Study of Pre-Trained BERT Models for Code-Mixed Hindi-English Data","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, Raviraj Joshi, Varad Patwardhan","submitted_at":"2023-05-25T05:10:28Z","abstract_excerpt":"The term \"Code Mixed\" refers to the use of more than one language in the same text. This phenomenon is predominantly observed on social media platforms, with an increasing amount of adaptation as time goes on. It is critical to detect foreign elements in a language and process them correctly, as a considerable number of individuals are using code-mixed languages that could not be comprehended by understanding one of those languages. In this work, we focus on low-resource Hindi-English code-mixed language and enhancing the performance of different code-mixed natural language processing tasks su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15722","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/2305.15722/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":"2305.15722","created_at":"2026-07-05T06:14:11.399205+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15722v2","created_at":"2026-07-05T06:14:11.399205+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15722","created_at":"2026-07-05T06:14:11.399205+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QM7ZOQIDLY2","created_at":"2026-07-05T06:14:11.399205+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QM7ZOQIDLY2CK2E","created_at":"2026-07-05T06:14:11.399205+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QM7ZOQI","created_at":"2026-07-05T06:14:11.399205+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/4QM7ZOQIDLY2CK2EPYCSWI2YXE","json":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE.json","graph_json":"https://pith.science/api/pith-number/4QM7ZOQIDLY2CK2EPYCSWI2YXE/graph.json","events_json":"https://pith.science/api/pith-number/4QM7ZOQIDLY2CK2EPYCSWI2YXE/events.json","paper":"https://pith.science/paper/4QM7ZOQI"},"agent_actions":{"view_html":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE","download_json":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE.json","view_paper":"https://pith.science/paper/4QM7ZOQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15722&json=true","fetch_graph":"https://pith.science/api/pith-number/4QM7ZOQIDLY2CK2EPYCSWI2YXE/graph.json","fetch_events":"https://pith.science/api/pith-number/4QM7ZOQIDLY2CK2EPYCSWI2YXE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE/action/storage_attestation","attest_author":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE/action/author_attestation","sign_citation":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE/action/citation_signature","submit_replication":"https://pith.science/pith/4QM7ZOQIDLY2CK2EPYCSWI2YXE/action/replication_record"}},"created_at":"2026-07-05T06:14:11.399205+00:00","updated_at":"2026-07-05T06:14:11.399205+00:00"}