{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QCWJSSAYNFCNMVDPOR5SCQ2Q3Z","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":"89019a16a903c5468b13b820a789488087ab7eb2aaf3bb2a0e5747504047f270","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T09:20:09Z","title_canon_sha256":"766be308b676ff41ef210d848b42494079d5e85b55c44293bb6853a7146a4c00"},"schema_version":"1.0","source":{"id":"2303.03750","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.03750","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"arxiv_version","alias_value":"2303.03750v2","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03750","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_12","alias_value":"QCWJSSAYNFCN","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_16","alias_value":"QCWJSSAYNFCNMVDP","created_at":"2026-07-05T05:58:20Z"},{"alias_kind":"pith_short_8","alias_value":"QCWJSSAY","created_at":"2026-07-05T05:58:20Z"}],"graph_snapshots":[{"event_id":"sha256:c162c12512f49bcf641af16484eb29f90a1f46b3b9390d8a46cb486864dcb086","target":"graph","created_at":"2026-07-05T05:58:20Z","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/2303.03750/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces two multilingual government themed corpora in various South African languages. The corpora were collected by gathering the South African Government newspaper (Vuk'uzenzele), as well as South African government speeches (ZA-gov-multilingual), that are translated into all 11 South African official languages. The corpora can be used for a myriad of downstream NLP tasks. The corpora were created to allow researchers to study the language used in South African government publications, with a focus on understanding how South African government officials communicate with their c","authors_text":"Andani Madodonga, Daniel Njini, Isheanesu Dzingirai, Jenalea Rajab, Matimba Shingange, Richard Lastrucci, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T09:20:09Z","title":"Preparing the Vuk'uzenzele and ZA-gov-multilingual South African multilingual corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03750","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:e4376fd7678d12bf3233c817aa165095b727bf1d52e419e769b2cc1c083462f6","target":"record","created_at":"2026-07-05T05:58:20Z","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":"89019a16a903c5468b13b820a789488087ab7eb2aaf3bb2a0e5747504047f270","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-07T09:20:09Z","title_canon_sha256":"766be308b676ff41ef210d848b42494079d5e85b55c44293bb6853a7146a4c00"},"schema_version":"1.0","source":{"id":"2303.03750","kind":"arxiv","version":2}},"canonical_sha256":"80ac9948186944d6546f747b214350de48bf9ace5d5dd445eeec8049cfad395d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80ac9948186944d6546f747b214350de48bf9ace5d5dd445eeec8049cfad395d","first_computed_at":"2026-07-05T05:58:20.039199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:58:20.039199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LASMmZtYosC26sc3yGP+TbF0UnXVWartS9z3LuaDH5OFaJEqkT3Am/sKgAwO6GEa+hAahl2UK5DRUauEQhycDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:58:20.039705Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.03750","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4376fd7678d12bf3233c817aa165095b727bf1d52e419e769b2cc1c083462f6","sha256:c162c12512f49bcf641af16484eb29f90a1f46b3b9390d8a46cb486864dcb086"],"state_sha256":"7966d303c14d3b917663e7833dad3598129415c75c3817a691d203b35e862c8c"}