{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:S4GRXBGQHTALLL2TNFBMYVOBEH","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":"bec43545d7be0a82c87823d593d91320069f82946ce1425dc1485c21e532e787","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T16:28:06Z","title_canon_sha256":"773d8fa0f42a8c2562bf80523f48ccc5315b3bffca2e80c6986dbba4c3203215"},"schema_version":"1.0","source":{"id":"2201.08277","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.08277","created_at":"2026-07-05T04:32:54Z"},{"alias_kind":"arxiv_version","alias_value":"2201.08277v3","created_at":"2026-07-05T04:32:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08277","created_at":"2026-07-05T04:32:54Z"},{"alias_kind":"pith_short_12","alias_value":"S4GRXBGQHTAL","created_at":"2026-07-05T04:32:54Z"},{"alias_kind":"pith_short_16","alias_value":"S4GRXBGQHTALLL2T","created_at":"2026-07-05T04:32:54Z"},{"alias_kind":"pith_short_8","alias_value":"S4GRXBGQ","created_at":"2026-07-05T04:32:54Z"}],"graph_snapshots":[{"event_id":"sha256:9b3d36ad060ecd9cf7a769c596c9439c37a0c494c8de6ac5cc3475110e24dabb","target":"graph","created_at":"2026-07-05T04:32:54Z","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/2201.08277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria (Hausa, Igbo, Nigerian-Pidgin, and Yor\\`ub\\'a ) consisting of around 30,000 annotated tweets per language (and 14,000 for Nigerian-Pidgin), including a significant fraction of code-mixed tweets. We propose text collection, filtering, processing and labeling methods that enable us to create datasets for these low-resource languages.","authors_text":"Alipio Jeorge, Anuoluwapo Aremu, Bello Shehu Bello, Chris Chinenye Emezue, David Ifeoluwa Adelani, Ibrahim Said Ahmad, Idris Abdulmumin, Monojit Choudhury, Pavel Brazdil, Saheed Salahudeen Abdullahi, Sebastian Ruder, Shamsuddeen Hassan Muhammad","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T16:28:06Z","title":"NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08277","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":"sha256:21ba353492724a074da8ac047eb44bb5103cd7a9a75372357c858b2ae5befcf3","target":"record","created_at":"2026-07-05T04:32:54Z","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":"bec43545d7be0a82c87823d593d91320069f82946ce1425dc1485c21e532e787","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-20T16:28:06Z","title_canon_sha256":"773d8fa0f42a8c2562bf80523f48ccc5315b3bffca2e80c6986dbba4c3203215"},"schema_version":"1.0","source":{"id":"2201.08277","kind":"arxiv","version":3}},"canonical_sha256":"970d1b84d03cc0b5af536942cc55c121e66e646ad82e3a6c0ab3b8b27c0dba14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"970d1b84d03cc0b5af536942cc55c121e66e646ad82e3a6c0ab3b8b27c0dba14","first_computed_at":"2026-07-05T04:32:54.935690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:54.935690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hOnYhJzg36x5Vwjrx8uBvahKnvPx18hEnvKDjWiMkbAB3wowxuFjFxq5bandM4SsjDAVCTdUG8xOmc6ERg/FAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:54.936209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.08277","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:21ba353492724a074da8ac047eb44bb5103cd7a9a75372357c858b2ae5befcf3","sha256:9b3d36ad060ecd9cf7a769c596c9439c37a0c494c8de6ac5cc3475110e24dabb"],"state_sha256":"7fbc94b28c2198ab41b99b440bd3178ab87cc874acc22801b340309cd53edc50"}