{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WQ5TXLTW2ETB4HOKLTWZYQCQVT","short_pith_number":"pith:WQ5TXLTW","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"},"canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","source":{"kind":"arxiv","id":"2408.08964","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08964","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08964v3","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08964","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"WQ5TXLTW2ETB","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"WQ5TXLTW2ETB4HOK","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"WQ5TXLTW","created_at":"2026-07-05T09:46:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WQ5TXLTW2ETB4HOKLTWZYQCQVT","target":"record","payload":{"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"},"canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","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"},"source_kind":"arxiv","source_id":"2408.08964","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yk2Y1xUZrvhhhkC1CjLZJ2Fg4ztjvW480mJcuV+LZC8c3/Mxy98ebf5B6wuE5HPAZbffXu4TNPhKNaVB+bvtBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:47:54.071092Z"},"content_sha256":"048183e9d9b07908f9d3efe247c29de38190a1b89f88faa5e79b40456484efa2","schema_version":"1.0","event_id":"sha256:048183e9d9b07908f9d3efe247c29de38190a1b89f88faa5e79b40456484efa2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WQ5TXLTW2ETB4HOKLTWZYQCQVT","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:46:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i38i/sdjM1iL9fTBun92cQIbaRk/VeS7VXRurHGSQfky8n9ohj4+qiAXQ++p5eMFc3E/vMw/R0eSBC6zOWpxAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:47:54.071623Z"},"content_sha256":"79b74f71db1dc8ac7e80cb7e2f0a10c22ceac5a27f27371d9371c8f8e59fba96","schema_version":"1.0","event_id":"sha256:79b74f71db1dc8ac7e80cb7e2f0a10c22ceac5a27f27371d9371c8f8e59fba96"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/bundle.json","state_url":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T11:47:54Z","links":{"resolver":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT","bundle":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/bundle.json","state":"https://pith.science/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WQ5TXLTW2ETB4HOKLTWZYQCQVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WQ5TXLTW2ETB4HOKLTWZYQCQVT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b4a785a4c2a1bc788db3a39f4dd9d3e2f19ae24457404e6421738350acfc4b2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T18:30:22Z","title_canon_sha256":"40d4108f65aed4835ffb428df8af663e653d89f2152d634cc8e8a843a65b27f4"},"schema_version":"1.0","source":{"id":"2408.08964","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08964","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08964v3","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08964","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_12","alias_value":"WQ5TXLTW2ETB","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_16","alias_value":"WQ5TXLTW2ETB4HOK","created_at":"2026-07-05T09:46:50Z"},{"alias_kind":"pith_short_8","alias_value":"WQ5TXLTW","created_at":"2026-07-05T09:46:50Z"}],"graph_snapshots":[{"event_id":"sha256:79b74f71db1dc8ac7e80cb7e2f0a10c22ceac5a27f27371d9371c8f8e59fba96","target":"graph","created_at":"2026-07-05T09:46:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.08964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abu Raihan Mostofa Kamal, Md Azam Hossain, Md Farhan Ishmam, Md Shahnewaz Siddique, Navid Hasin Alvee, Sadia Alam","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T18:30:22Z","title":"BnSentMix: A Diverse Bengali-English Code-Mixed Dataset for Sentiment Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08964","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:048183e9d9b07908f9d3efe247c29de38190a1b89f88faa5e79b40456484efa2","target":"record","created_at":"2026-07-05T09:46:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b4a785a4c2a1bc788db3a39f4dd9d3e2f19ae24457404e6421738350acfc4b2d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-16T18:30:22Z","title_canon_sha256":"40d4108f65aed4835ffb428df8af663e653d89f2152d634cc8e8a843a65b27f4"},"schema_version":"1.0","source":{"id":"2408.08964","kind":"arxiv","version":3}},"canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b43b3bae76d1261e1dca5ced9c4050acc159d13e17fede8612afae58d35022b3","first_computed_at":"2026-07-05T09:46:50.015443Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:46:50.015443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8g7bGpGCmHIatcplyI4Z6J3LP31gRUGcXM1YeCuHq5UUD6IC7l59LrgWhok9zgPEYKXoY17fWgYUYW3Du/m1Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:46:50.015993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08964","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:048183e9d9b07908f9d3efe247c29de38190a1b89f88faa5e79b40456484efa2","sha256:79b74f71db1dc8ac7e80cb7e2f0a10c22ceac5a27f27371d9371c8f8e59fba96"],"state_sha256":"05e931d2e7506739999ca35e81e743f18067e5713d28c7dc38b6a47a60d87692"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hn0auDF0Yk/hRaRkn6jnSLaRFXMVjjLBc3xZuLw/iwy6OzokSMFUjk539ig4tSsyEMN5GzLHQ/+HVUsZC8huBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:47:54.077627Z","bundle_sha256":"8a38a4e64b5e55ef6eed0bd74196e6282e96649b262eed44f2d640c53d830816"}}