{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WQ5TXLTW2ETB4HOKLTWZYQCQVT","short_pith_number":"pith:WQ5TXLTW","schema_version":"1.0","canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","source":{"kind":"arxiv","id":"2408.08964","version":3},"attestation_state":"computed","paper":{"title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abu Raihan Mostofa Kamal, Md Azam Hossain, Md Farhan Ishmam, Md Shahnewaz Siddique, Navid Hasin Alvee, Sadia Alam","submitted_at":"2024-08-16T18:30:22Z","abstract_excerpt":"The widespread availability of code-mixed data can provide valuable insights into low-resource languages like Bengali, which have limited datasets. Sentiment analysis has been a fundamental text classification task across several languages for code-mixed data. However, there has yet to be a large-scale and diverse sentiment analysis dataset on code-mixed Bengali. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali consisting of 20,000 samples with 4 sentiment labels from Facebook, YouTube, and e-commerce sites. We ensure diversity in data sou"},"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":"2408.08964","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T18:30:22Z","cross_cats_sorted":[],"title_canon_sha256":"40d4108f65aed4835ffb428df8af663e653d89f2152d634cc8e8a843a65b27f4","abstract_canon_sha256":"b4a785a4c2a1bc788db3a39f4dd9d3e2f19ae24457404e6421738350acfc4b2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:46:50.015993Z","signature_b64":"8g7bGpGCmHIatcplyI4Z6J3LP31gRUGcXM1YeCuHq5UUD6IC7l59LrgWhok9zgPEYKXoY17fWgYUYW3Du/m1Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","last_reissued_at":"2026-07-05T09:46:50.015443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:46:50.015443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abu Raihan Mostofa Kamal, Md Azam Hossain, Md Farhan Ishmam, Md Shahnewaz Siddique, Navid Hasin Alvee, Sadia Alam","submitted_at":"2024-08-16T18:30:22Z","abstract_excerpt":"The widespread availability of code-mixed data can provide valuable insights into low-resource languages like Bengali, which have limited datasets. Sentiment analysis has been a fundamental text classification task across several languages for code-mixed data. However, there has yet to be a large-scale and diverse sentiment analysis dataset on code-mixed Bengali. We address this limitation by introducing BnSentMix, a sentiment analysis dataset on code-mixed Bengali consisting of 20,000 samples with 4 sentiment labels from Facebook, YouTube, and e-commerce sites. We ensure diversity in data sou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08964","kind":"arxiv","version":3},"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/2408.08964/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":"2408.08964","created_at":"2026-07-05T09:46:50.015504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.08964v3","created_at":"2026-07-05T09:46:50.015504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08964","created_at":"2026-07-05T09:46:50.015504+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ5TXLTW2ETB","created_at":"2026-07-05T09:46:50.015504+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ5TXLTW2ETB4HOK","created_at":"2026-07-05T09:46:50.015504+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ5TXLTW","created_at":"2026-07-05T09:46:50.015504+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/WQ5TXLTW2ETB4HOKLTWZYQCQVT","json":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT.json","graph_json":"https://pith.science/api/pith-number/WQ5TXLTW2ETB4HOKLTWZYQCQVT/graph.json","events_json":"https://pith.science/api/pith-number/WQ5TXLTW2ETB4HOKLTWZYQCQVT/events.json","paper":"https://pith.science/paper/WQ5TXLTW"},"agent_actions":{"view_html":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT","download_json":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT.json","view_paper":"https://pith.science/paper/WQ5TXLTW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.08964&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ5TXLTW2ETB4HOKLTWZYQCQVT/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ5TXLTW2ETB4HOKLTWZYQCQVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/action/storage_attestation","attest_author":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/action/author_attestation","sign_citation":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/action/citation_signature","submit_replication":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/action/replication_record"}},"created_at":"2026-07-05T09:46:50.015504+00:00","updated_at":"2026-07-05T09:46:50.015504+00:00"}