{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLWVKXIW7GGX6IB377HCD45H5Z","short_pith_number":"pith:CLWVKXIW","schema_version":"1.0","canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","source":{"kind":"arxiv","id":"2403.16771","version":2},"attestation_state":"computed","paper":{"title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Kartik Kartik, Md Shad Akhtar, Sanjana Soni, Tanmoy Chakraborty","submitted_at":"2024-03-25T13:50:11Z","abstract_excerpt":"The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically devel"},"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":"2403.16771","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-25T13:50:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"019cf46187d674d75883592f83fe61f91f076ad0a99673b69e35c685dfd6e83a","abstract_canon_sha256":"68b4b8464a2897dc3a09d1a87594c0d19715705e0787770e9e9f0ec27e48a5d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:31.325289Z","signature_b64":"iRm9Cz7s/bILdE5AEegh8Hh7u4Mg1xDIyQXmSg2zjXb3X52slIBSGtVhsWgLsCh/eLkGcwo0jyOsQGWvgZu1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12ed555d16f98d7f203bffce21f3a7ee6de80e2342496e814c71595264c5c065","last_reissued_at":"2026-07-05T08:13:31.324776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:31.324776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthetic Data Generation and Joint Learning for Robust Code-Mixed Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anoop Kunchukuttan, Kartik Kartik, Md Shad Akhtar, Sanjana Soni, Tanmoy Chakraborty","submitted_at":"2024-03-25T13:50:11Z","abstract_excerpt":"The widespread online communication in a modern multilingual world has provided opportunities to blend more than one language (aka code-mixed language) in a single utterance. This has resulted a formidable challenge for the computational models due to the scarcity of annotated data and presence of noise. A potential solution to mitigate the data scarcity problem in low-resource setup is to leverage existing data in resource-rich language through translation. In this paper, we tackle the problem of code-mixed (Hinglish and Bengalish) to English machine translation. First, we synthetically devel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16771","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/2403.16771/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":"2403.16771","created_at":"2026-07-05T08:13:31.324827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16771v2","created_at":"2026-07-05T08:13:31.324827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16771","created_at":"2026-07-05T08:13:31.324827+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLWVKXIW7GGX","created_at":"2026-07-05T08:13:31.324827+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLWVKXIW7GGX6IB3","created_at":"2026-07-05T08:13:31.324827+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLWVKXIW","created_at":"2026-07-05T08:13:31.324827+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/CLWVKXIW7GGX6IB377HCD45H5Z","json":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z.json","graph_json":"https://pith.science/api/pith-number/CLWVKXIW7GGX6IB377HCD45H5Z/graph.json","events_json":"https://pith.science/api/pith-number/CLWVKXIW7GGX6IB377HCD45H5Z/events.json","paper":"https://pith.science/paper/CLWVKXIW"},"agent_actions":{"view_html":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z","download_json":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z.json","view_paper":"https://pith.science/paper/CLWVKXIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16771&json=true","fetch_graph":"https://pith.science/api/pith-number/CLWVKXIW7GGX6IB377HCD45H5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CLWVKXIW7GGX6IB377HCD45H5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/action/storage_attestation","attest_author":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/action/author_attestation","sign_citation":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/action/citation_signature","submit_replication":"https://pith.science/pith/CLWVKXIW7GGX6IB377HCD45H5Z/action/replication_record"}},"created_at":"2026-07-05T08:13:31.324827+00:00","updated_at":"2026-07-05T08:13:31.324827+00:00"}