{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LGN6LBLL6FD4RQ5OV3J2CJDCFD","short_pith_number":"pith:LGN6LBLL","canonical_record":{"source":{"id":"2310.09141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T14:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"95aa83fef872d8b9e3f2bb78b69ed6b6fa94abd1e2417af6bdbdfcaa050a88df","abstract_canon_sha256":"37b61ce6cc66e5bb8c1546195e2eeba3cbbfcfcf28999d76c4bc44e859a5ccf6"},"schema_version":"1.0"},"canonical_sha256":"599be5856bf147c8c3aeaed3a1246228febfa52a30326bde88c8b065c8d9037c","source":{"kind":"arxiv","id":"2310.09141","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LGN6LBLL6FD4RQ5OV3J2CJDCFD","target":"record","payload":{"canonical_record":{"source":{"id":"2310.09141","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-13T14:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"95aa83fef872d8b9e3f2bb78b69ed6b6fa94abd1e2417af6bdbdfcaa050a88df","abstract_canon_sha256":"37b61ce6cc66e5bb8c1546195e2eeba3cbbfcfcf28999d76c4bc44e859a5ccf6"},"schema_version":"1.0"},"canonical_sha256":"599be5856bf147c8c3aeaed3a1246228febfa52a30326bde88c8b065c8d9037c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:21.386686Z","signature_b64":"LRCsVYpgOKGRQtEaXrSTtFZbZrQM9e4ujGP7mehEPiD+orcmtsOPo/HS133DpdTRTFiGJ5Z0ufAlzp/Ppy2dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599be5856bf147c8c3aeaed3a1246228febfa52a30326bde88c8b065c8d9037c","last_reissued_at":"2026-07-05T07:04:21.386233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:21.386233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.09141","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":"2026-07-05T07:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Du8bw9W6QTq5Cw+F2I3IxglHIUOAelD6kVf5d4+iEi20i32QK5loByYcNiKlxIZNNgqaq5zXcPMdvOyI8i0ACw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:29:23.449284Z"},"content_sha256":"e23292fc2c3172763652466c1c4225041c602eb1148688a6f0f4867c56300ea6","schema_version":"1.0","event_id":"sha256:e23292fc2c3172763652466c1c4225041c602eb1148688a6f0f4867c56300ea6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LGN6LBLL6FD4RQ5OV3J2CJDCFD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PuoBERTa: Training and evaluation of a curated language model for Setswana","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Isheanesu Dzingirai, Moseli Mots'oehli, Richard Lastrucci, Valencia Wagner, Vukosi Marivate","submitted_at":"2023-10-13T14:33:02Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.09141","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/2310.09141/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":"2026-07-05T07:04:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i7uJszrGsPGJbh9oKv9GXEb7zychAwLzWRNYWc2C5DkdB/2xFR3mlDTpK4Qh5QlmwBykVnsZMfDyFHnxT+qTCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:29:23.449675Z"},"content_sha256":"e79c5e7d9db49164a33af0b871ed10a4df18a9c3db2a6b9191b65f56983abca7","schema_version":"1.0","event_id":"sha256:e79c5e7d9db49164a33af0b871ed10a4df18a9c3db2a6b9191b65f56983abca7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/bundle.json","state_url":"https://pith.science/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/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":"2026-07-06T14:29:23Z","links":{"resolver":"https://pith.science/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD","bundle":"https://pith.science/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/bundle.json","state":"https://pith.science/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGN6LBLL6FD4RQ5OV3J2CJDCFD/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lhu1ISERpEPd1Q4PpcA97xZk10NBQEoOuDG2Kt95gEMlpOn5RvK5fdP7W7x369Yg/92QWbC8OS/lOdR/cB9KBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:29:23.451574Z","bundle_sha256":"265119a862cdd2de71b3976661ac5fad422f015f057af22bc68c35125867772e"}}