{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CX6QJDOSCE6HQEC2YD2CDDMG5P","short_pith_number":"pith:CX6QJDOS","canonical_record":{"source":{"id":"2412.03334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T14:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"d5a01a7bca9971ea43502b1957940b586f7c2fff3f00d26c492454dad9c8b317","abstract_canon_sha256":"afa334e2be71adba2193ea6ffa71d948e22e7ab4ddf6f613d6845e42c69e8f47"},"schema_version":"1.0"},"canonical_sha256":"15fd048dd2113c78105ac0f4218d86ebf680d4d40abf2c6f97cae93369c129e8","source":{"kind":"arxiv","id":"2412.03334","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03334","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03334v2","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03334","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"CX6QJDOSCE6H","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"CX6QJDOSCE6HQEC2","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"CX6QJDOS","created_at":"2026-07-05T11:49:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CX6QJDOSCE6HQEC2YD2CDDMG5P","target":"record","payload":{"canonical_record":{"source":{"id":"2412.03334","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T14:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"d5a01a7bca9971ea43502b1957940b586f7c2fff3f00d26c492454dad9c8b317","abstract_canon_sha256":"afa334e2be71adba2193ea6ffa71d948e22e7ab4ddf6f613d6845e42c69e8f47"},"schema_version":"1.0"},"canonical_sha256":"15fd048dd2113c78105ac0f4218d86ebf680d4d40abf2c6f97cae93369c129e8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:48.480418Z","signature_b64":"6nqx9qhIo36RctAMSXdEWJsYDvEz9KfXL4Wno2cpxcNYYJAa9AEbENBD5Rb80vhFQBKqMCoqHJwRRgCeSQw5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15fd048dd2113c78105ac0f4218d86ebf680d4d40abf2c6f97cae93369c129e8","last_reissued_at":"2026-07-05T11:49:48.479977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:48.479977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.03334","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"opo8upLPCe47x1Le3rYZ8LLXoezqo8hqnaB2+6CjDK0kIEwfZW122TRmj8O2Wbqt1zOOlWA7UQ+cheVUWPKFAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:01:47.772280Z"},"content_sha256":"bb99fbfbbbe597c4ff96c081623f6b31016471b42784d48d33349a27c272223a","schema_version":"1.0","event_id":"sha256:bb99fbfbbbe597c4ff96c081623f6b31016471b42784d48d33349a27c272223a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CX6QJDOSCE6HQEC2YD2CDDMG5P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Yankari: A Monolingual Yoruba Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maro Akpobi","submitted_at":"2024-12-04T14:05:18Z","abstract_excerpt":"This paper presents Yankari, a large-scale monolingual dataset for the Yoruba language, aimed at addressing the critical gap in Natural Language Processing (NLP) resources for this important West African language. Despite being spoken by over 30 million people, Yoruba has been severely underrepresented in NLP research and applications. We detail our methodology for creating this dataset, which includes careful source selection, automated quality control, and rigorous data cleaning processes. The Yankari dataset comprises 51,407 documents from 13 diverse sources, totaling over 30 million tokens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03334","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/2412.03334/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":"2026-07-05T11:49:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7MxTUDjL7IthmOcHnerq9pnB7hji2NScTcOZQW4dGNgJfVFMn5pdX3e3/C/msSjIchCKrL1wE1n4XI204xLsBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T00:01:47.773195Z"},"content_sha256":"4ac8d66e99d3899ebee7246ac8bd96e7307291c7b4aab87540b2ce44e278664e","schema_version":"1.0","event_id":"sha256:4ac8d66e99d3899ebee7246ac8bd96e7307291c7b4aab87540b2ce44e278664e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/bundle.json","state_url":"https://pith.science/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/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":"2026-08-18T00:01:47Z","links":{"resolver":"https://pith.science/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P","bundle":"https://pith.science/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/bundle.json","state":"https://pith.science/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CX6QJDOSCE6HQEC2YD2CDDMG5P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CX6QJDOSCE6HQEC2YD2CDDMG5P","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":"afa334e2be71adba2193ea6ffa71d948e22e7ab4ddf6f613d6845e42c69e8f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T14:05:18Z","title_canon_sha256":"d5a01a7bca9971ea43502b1957940b586f7c2fff3f00d26c492454dad9c8b317"},"schema_version":"1.0","source":{"id":"2412.03334","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.03334","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"arxiv_version","alias_value":"2412.03334v2","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03334","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_12","alias_value":"CX6QJDOSCE6H","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_16","alias_value":"CX6QJDOSCE6HQEC2","created_at":"2026-07-05T11:49:48Z"},{"alias_kind":"pith_short_8","alias_value":"CX6QJDOS","created_at":"2026-07-05T11:49:48Z"}],"graph_snapshots":[{"event_id":"sha256:4ac8d66e99d3899ebee7246ac8bd96e7307291c7b4aab87540b2ce44e278664e","target":"graph","created_at":"2026-07-05T11:49:48Z","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/2412.03334/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Yankari, a large-scale monolingual dataset for the Yoruba language, aimed at addressing the critical gap in Natural Language Processing (NLP) resources for this important West African language. Despite being spoken by over 30 million people, Yoruba has been severely underrepresented in NLP research and applications. We detail our methodology for creating this dataset, which includes careful source selection, automated quality control, and rigorous data cleaning processes. The Yankari dataset comprises 51,407 documents from 13 diverse sources, totaling over 30 million tokens","authors_text":"Maro Akpobi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T14:05:18Z","title":"Yankari: A Monolingual Yoruba Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03334","kind":"arxiv","version":2},"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:bb99fbfbbbe597c4ff96c081623f6b31016471b42784d48d33349a27c272223a","target":"record","created_at":"2026-07-05T11:49:48Z","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":"afa334e2be71adba2193ea6ffa71d948e22e7ab4ddf6f613d6845e42c69e8f47","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T14:05:18Z","title_canon_sha256":"d5a01a7bca9971ea43502b1957940b586f7c2fff3f00d26c492454dad9c8b317"},"schema_version":"1.0","source":{"id":"2412.03334","kind":"arxiv","version":2}},"canonical_sha256":"15fd048dd2113c78105ac0f4218d86ebf680d4d40abf2c6f97cae93369c129e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15fd048dd2113c78105ac0f4218d86ebf680d4d40abf2c6f97cae93369c129e8","first_computed_at":"2026-07-05T11:49:48.479977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:49:48.479977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6nqx9qhIo36RctAMSXdEWJsYDvEz9KfXL4Wno2cpxcNYYJAa9AEbENBD5Rb80vhFQBKqMCoqHJwRRgCeSQw5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:49:48.480418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.03334","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb99fbfbbbe597c4ff96c081623f6b31016471b42784d48d33349a27c272223a","sha256:4ac8d66e99d3899ebee7246ac8bd96e7307291c7b4aab87540b2ce44e278664e"],"state_sha256":"c753e5741fb1306f61e177710aba1353cdebb3402565287a593b1b9346f40961"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5HYqiMHmsywickOwqnPAQ70AVORjDDU3bjJkzOidXaLXpjN+oTzZGyyhtsj2HHU222aNF62roRLsm+oLM5lDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T00:01:47.789879Z","bundle_sha256":"d096db71f0f92976ee4edeee7bce69d6d39aee91ca4253d83da0db5cbdd5f64e"}}