{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6KZUV5FYWATBUGWAZPMIXU2DVS","short_pith_number":"pith:6KZUV5FY","canonical_record":{"source":{"id":"2409.00626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T06:13:03Z","cross_cats_sorted":[],"title_canon_sha256":"f743627f352f67865be46024d03fd4c9dd304e4b79bfe989c8010433c8bedaac","abstract_canon_sha256":"04dabacfcfd3a11b47d2d4abb3fe09dd2a1d4616ecd7943b473479380bd71459"},"schema_version":"1.0"},"canonical_sha256":"f2b34af4b8b0261a1ac0cbd88bd343ac993cdf45fa640f1a482c8462fb009714","source":{"kind":"arxiv","id":"2409.00626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00626","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00626v2","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00626","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"6KZUV5FYWATB","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"6KZUV5FYWATBUGWA","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"6KZUV5FY","created_at":"2026-07-05T09:16:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6KZUV5FYWATBUGWAZPMIXU2DVS","target":"record","payload":{"canonical_record":{"source":{"id":"2409.00626","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T06:13:03Z","cross_cats_sorted":[],"title_canon_sha256":"f743627f352f67865be46024d03fd4c9dd304e4b79bfe989c8010433c8bedaac","abstract_canon_sha256":"04dabacfcfd3a11b47d2d4abb3fe09dd2a1d4616ecd7943b473479380bd71459"},"schema_version":"1.0"},"canonical_sha256":"f2b34af4b8b0261a1ac0cbd88bd343ac993cdf45fa640f1a482c8462fb009714","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:16:20.822406Z","signature_b64":"zXZZljlkzoT2dTL6G2HomSSGpXznTQoK5fdwPxeLUcrcWG43hmlT0br6FaqbJsgr699BkP1QX+iNk55drDV3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2b34af4b8b0261a1ac0cbd88bd343ac993cdf45fa640f1a482c8462fb009714","last_reissued_at":"2026-07-05T09:16:20.821820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:16:20.821820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.00626","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":"2026-07-05T09:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XG6p2t2RWJM+Nifc2z2prWgsfDGU+VBaypCic3VBLQgm7wjS0c8PsbuX9R2de07WzetzgZ3FIflO+xdsbH1bAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:24:37.612178Z"},"content_sha256":"d4eaf20265aa7ead948c60b945a77e276e346b1183cf26ca12f145db184a865c","schema_version":"1.0","event_id":"sha256:d4eaf20265aa7ead948c60b945a77e276e346b1183cf26ca12f145db184a865c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6KZUV5FYWATBUGWAZPMIXU2DVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Correcting FLORES Evaluation Dataset for Four African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ibrahim Said Ahmad, Idris Abdulmumin, Mahlatse S. Mbooi, Matimba Shingange, Miehleketo Mathebula, Neo Putini, Shamsuddeen Hassan Muhammad, Sthembiso Mkhwanazi, Tajuddeen Gwadabe, Vukosi Marivate","submitted_at":"2024-09-01T06:13:03Z","abstract_excerpt":"This paper describes the corrections made to the FLORES evaluation (dev and devtest) dataset for four African languages, namely Hausa, Northern Sotho (Sepedi), Xitsonga, and isiZulu. The original dataset, though groundbreaking in its coverage of low-resource languages, exhibited various inconsistencies and inaccuracies in the reviewed languages that could potentially hinder the integrity of the evaluation of downstream tasks in natural language processing (NLP), especially machine translation. Through a meticulous review process by native speakers, several corrections were identified and imple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00626","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/2409.00626/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":"2026-07-05T09:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Xbv7akQS1zUpl5mzIH3hE0HSNN5WBmjLNUm2LAMbN8uwCHNy5IhGZXCY+yC4vMlCWHF9U0KWkXuyupPUIp8Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:24:37.612580Z"},"content_sha256":"c8a9ead056281a926d99ea92144194083fe29a5da7312c5502987e7d2bfa6579","schema_version":"1.0","event_id":"sha256:c8a9ead056281a926d99ea92144194083fe29a5da7312c5502987e7d2bfa6579"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/bundle.json","state_url":"https://pith.science/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/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":"2026-07-06T16:24:37Z","links":{"resolver":"https://pith.science/pith/6KZUV5FYWATBUGWAZPMIXU2DVS","bundle":"https://pith.science/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/bundle.json","state":"https://pith.science/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6KZUV5FYWATBUGWAZPMIXU2DVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6KZUV5FYWATBUGWAZPMIXU2DVS","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":"04dabacfcfd3a11b47d2d4abb3fe09dd2a1d4616ecd7943b473479380bd71459","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T06:13:03Z","title_canon_sha256":"f743627f352f67865be46024d03fd4c9dd304e4b79bfe989c8010433c8bedaac"},"schema_version":"1.0","source":{"id":"2409.00626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.00626","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2409.00626v2","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00626","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"6KZUV5FYWATB","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"6KZUV5FYWATBUGWA","created_at":"2026-07-05T09:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"6KZUV5FY","created_at":"2026-07-05T09:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:c8a9ead056281a926d99ea92144194083fe29a5da7312c5502987e7d2bfa6579","target":"graph","created_at":"2026-07-05T09:16:20Z","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/2409.00626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper describes the corrections made to the FLORES evaluation (dev and devtest) dataset for four African languages, namely Hausa, Northern Sotho (Sepedi), Xitsonga, and isiZulu. The original dataset, though groundbreaking in its coverage of low-resource languages, exhibited various inconsistencies and inaccuracies in the reviewed languages that could potentially hinder the integrity of the evaluation of downstream tasks in natural language processing (NLP), especially machine translation. Through a meticulous review process by native speakers, several corrections were identified and imple","authors_text":"Ibrahim Said Ahmad, Idris Abdulmumin, Mahlatse S. Mbooi, Matimba Shingange, Miehleketo Mathebula, Neo Putini, Shamsuddeen Hassan Muhammad, Sthembiso Mkhwanazi, Tajuddeen Gwadabe, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T06:13:03Z","title":"Correcting FLORES Evaluation Dataset for Four African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00626","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:d4eaf20265aa7ead948c60b945a77e276e346b1183cf26ca12f145db184a865c","target":"record","created_at":"2026-07-05T09:16:20Z","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":"04dabacfcfd3a11b47d2d4abb3fe09dd2a1d4616ecd7943b473479380bd71459","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-01T06:13:03Z","title_canon_sha256":"f743627f352f67865be46024d03fd4c9dd304e4b79bfe989c8010433c8bedaac"},"schema_version":"1.0","source":{"id":"2409.00626","kind":"arxiv","version":2}},"canonical_sha256":"f2b34af4b8b0261a1ac0cbd88bd343ac993cdf45fa640f1a482c8462fb009714","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f2b34af4b8b0261a1ac0cbd88bd343ac993cdf45fa640f1a482c8462fb009714","first_computed_at":"2026-07-05T09:16:20.821820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:20.821820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zXZZljlkzoT2dTL6G2HomSSGpXznTQoK5fdwPxeLUcrcWG43hmlT0br6FaqbJsgr699BkP1QX+iNk55drDV3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:20.822406Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.00626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4eaf20265aa7ead948c60b945a77e276e346b1183cf26ca12f145db184a865c","sha256:c8a9ead056281a926d99ea92144194083fe29a5da7312c5502987e7d2bfa6579"],"state_sha256":"fcd9df40e0c921d1c48da51729b779789533e4b0b0bf70f743cacf439f1dfa40"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DXEla2+Qthev9UyzBZDWminL0u/90GperJhqIEAPP9AvvvEbrTzUiM3nQJUWTTDDKfc0ozf+xPb5YjLzlCI5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:24:37.614606Z","bundle_sha256":"7fef3216b7a1603d126ca536c185e1f370cc3dd9629e24c76758220f9a9208f1"}}