{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LGN6LBLL6FD4RQ5OV3J2CJDCFD","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":"37b61ce6cc66e5bb8c1546195e2eeba3cbbfcfcf28999d76c4bc44e859a5ccf6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T14:33:02Z","title_canon_sha256":"95aa83fef872d8b9e3f2bb78b69ed6b6fa94abd1e2417af6bdbdfcaa050a88df"},"schema_version":"1.0","source":{"id":"2310.09141","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.09141","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"arxiv_version","alias_value":"2310.09141v2","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.09141","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_12","alias_value":"LGN6LBLL6FD4","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_16","alias_value":"LGN6LBLL6FD4RQ5O","created_at":"2026-07-05T07:04:21Z"},{"alias_kind":"pith_short_8","alias_value":"LGN6LBLL","created_at":"2026-07-05T07:04:21Z"}],"graph_snapshots":[{"event_id":"sha256:e79c5e7d9db49164a33af0b871ed10a4df18a9c3db2a6b9191b65f56983abca7","target":"graph","created_at":"2026-07-05T07:04:21Z","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/2310.09141/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language processing (NLP) has made significant progress for well-resourced languages such as English but lagged behind for low-resource languages like Setswana. This paper addresses this gap by presenting PuoBERTa, a customised masked language model trained specifically for Setswana. We cover how we collected, curated, and prepared diverse monolingual texts to generate a high-quality corpus for PuoBERTa's training. Building upon previous efforts in creating monolingual resources for Setswana, we evaluated PuoBERTa across several NLP tasks, including part-of-speech (POS) tagging, named ","authors_text":"Isheanesu Dzingirai, Moseli Mots'oehli, Richard Lastrucci, Valencia Wagner, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T14:33:02Z","title":"PuoBERTa: Training and evaluation of a curated language model for Setswana"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09141","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:e23292fc2c3172763652466c1c4225041c602eb1148688a6f0f4867c56300ea6","target":"record","created_at":"2026-07-05T07:04:21Z","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":"37b61ce6cc66e5bb8c1546195e2eeba3cbbfcfcf28999d76c4bc44e859a5ccf6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T14:33:02Z","title_canon_sha256":"95aa83fef872d8b9e3f2bb78b69ed6b6fa94abd1e2417af6bdbdfcaa050a88df"},"schema_version":"1.0","source":{"id":"2310.09141","kind":"arxiv","version":2}},"canonical_sha256":"599be5856bf147c8c3aeaed3a1246228febfa52a30326bde88c8b065c8d9037c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599be5856bf147c8c3aeaed3a1246228febfa52a30326bde88c8b065c8d9037c","first_computed_at":"2026-07-05T07:04:21.386233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:21.386233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRCsVYpgOKGRQtEaXrSTtFZbZrQM9e4ujGP7mehEPiD+orcmtsOPo/HS133DpdTRTFiGJ5Z0ufAlzp/Ppy2dDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:21.386686Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.09141","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e23292fc2c3172763652466c1c4225041c602eb1148688a6f0f4867c56300ea6","sha256:e79c5e7d9db49164a33af0b871ed10a4df18a9c3db2a6b9191b65f56983abca7"],"state_sha256":"e773b4d046dab0ab4dc05ee138a32f8e96e4a747b92b65f761326d827cc739c7"}