{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UDUCMZDHGCEALDOZNDUGOLLXN6","short_pith_number":"pith:UDUCMZDH","schema_version":"1.0","canonical_sha256":"a0e82664673088058dd968e8672d776f9c12d609afafb348460aba064fb4b6a2","source":{"kind":"arxiv","id":"2310.18023","version":2},"attestation_state":"computed","paper":{"title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antara Mahmud, Antonios Anastasopoulos, Dhiman Goswami, Marcos Zampieri, Md Nishat Raihan","submitted_at":"2023-10-27T09:59:24Z","abstract_excerpt":"Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several datasets have been build with the goal of training computational models for code-mixing. Although it is very common to observe code-mixing with multiple languages, most datasets available contain code-mixed between only two languages. In this paper, we introduce SentMix-3L, a novel dataset for sentiment analysis containing code-mixed data between three languages Bangla, English, and Hindi. We carry out a comprehensive evaluation using SentMix-3L. We show that zero-shot prompting "},"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":"2310.18023","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T09:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"74190c1311bd8bfd6b2e04ea40d7d0511fd3c2b410e39781ea1ec78d690dc9db","abstract_canon_sha256":"59aeec03d90f9fa61ccc70fb492bbc077b7e78a20fd4342948083d6ecfa75041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:18:12.337668Z","signature_b64":"0H+WRy+T3Z1vJ6LDHLEgWah9j3iUpmNMxYybHXT+59cr4rgcuIzAvNvlvs4mmBhCpU+d24vSoH9HybxdOEyQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0e82664673088058dd968e8672d776f9c12d609afafb348460aba064fb4b6a2","last_reissued_at":"2026-07-05T07:18:12.337179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:18:12.337179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SentMix-3L: A Bangla-English-Hindi Code-Mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antara Mahmud, Antonios Anastasopoulos, Dhiman Goswami, Marcos Zampieri, Md Nishat Raihan","submitted_at":"2023-10-27T09:59:24Z","abstract_excerpt":"Code-mixing is a well-studied linguistic phenomenon when two or more languages are mixed in text or speech. Several datasets have been build with the goal of training computational models for code-mixing. Although it is very common to observe code-mixing with multiple languages, most datasets available contain code-mixed between only two languages. In this paper, we introduce SentMix-3L, a novel dataset for sentiment analysis containing code-mixed data between three languages Bangla, English, and Hindi. We carry out a comprehensive evaluation using SentMix-3L. We show that zero-shot prompting "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18023","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/2310.18023/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":"2310.18023","created_at":"2026-07-05T07:18:12.337239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18023v2","created_at":"2026-07-05T07:18:12.337239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18023","created_at":"2026-07-05T07:18:12.337239+00:00"},{"alias_kind":"pith_short_12","alias_value":"UDUCMZDHGCEA","created_at":"2026-07-05T07:18:12.337239+00:00"},{"alias_kind":"pith_short_16","alias_value":"UDUCMZDHGCEALDOZ","created_at":"2026-07-05T07:18:12.337239+00:00"},{"alias_kind":"pith_short_8","alias_value":"UDUCMZDH","created_at":"2026-07-05T07:18:12.337239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09073","citing_title":"CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6","json":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6.json","graph_json":"https://pith.science/api/pith-number/UDUCMZDHGCEALDOZNDUGOLLXN6/graph.json","events_json":"https://pith.science/api/pith-number/UDUCMZDHGCEALDOZNDUGOLLXN6/events.json","paper":"https://pith.science/paper/UDUCMZDH"},"agent_actions":{"view_html":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6","download_json":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6.json","view_paper":"https://pith.science/paper/UDUCMZDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18023&json=true","fetch_graph":"https://pith.science/api/pith-number/UDUCMZDHGCEALDOZNDUGOLLXN6/graph.json","fetch_events":"https://pith.science/api/pith-number/UDUCMZDHGCEALDOZNDUGOLLXN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6/action/storage_attestation","attest_author":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6/action/author_attestation","sign_citation":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6/action/citation_signature","submit_replication":"https://pith.science/pith/UDUCMZDHGCEALDOZNDUGOLLXN6/action/replication_record"}},"created_at":"2026-07-05T07:18:12.337239+00:00","updated_at":"2026-07-05T07:18:12.337239+00:00"}