{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6OZ4PPEFRWUBS7OYUISZIHT6CV","short_pith_number":"pith:6OZ4PPEF","canonical_record":{"source":{"id":"2306.07426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T21:02:12Z","cross_cats_sorted":[],"title_canon_sha256":"a64f553dd1c0939fe0d97ca0726f327e58d12807adebe50a65eecfac271e8e16","abstract_canon_sha256":"8eac596ae6917950d0c3e1bfb989ec7c6c2f756b1cb85f14cfd01b58b220a62e"},"schema_version":"1.0"},"canonical_sha256":"f3b3c7bc858da8197dd8a225941e7e154866dbfbe119d0a21a442a3e2f3efbf6","source":{"kind":"arxiv","id":"2306.07426","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07426","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07426v1","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07426","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"6OZ4PPEFRWUB","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"6OZ4PPEFRWUBS7OY","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"6OZ4PPEF","created_at":"2026-07-05T06:20:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6OZ4PPEFRWUBS7OYUISZIHT6CV","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07426","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T21:02:12Z","cross_cats_sorted":[],"title_canon_sha256":"a64f553dd1c0939fe0d97ca0726f327e58d12807adebe50a65eecfac271e8e16","abstract_canon_sha256":"8eac596ae6917950d0c3e1bfb989ec7c6c2f756b1cb85f14cfd01b58b220a62e"},"schema_version":"1.0"},"canonical_sha256":"f3b3c7bc858da8197dd8a225941e7e154866dbfbe119d0a21a442a3e2f3efbf6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:04.211669Z","signature_b64":"7xZ0UEScTUH+QAxt+jVDWlG+KJR61ZIVbPCijKYlM1nLVoVh+qd8HrAk7fD2NLKoYwL13Ibf1WW3KwKlwsbnBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b3c7bc858da8197dd8a225941e7e154866dbfbe119d0a21a442a3e2f3efbf6","last_reissued_at":"2026-07-05T06:20:04.211178Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:04.211178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07426","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3yr3eYRFjeWyUzdLvJE+KcQcoBmWREk4PbQs6jeXpqryiQBNw9CtRLBlW0YHIfGkqI27Hfihv2bEqHSVBUhuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:26:04.219901Z"},"content_sha256":"866fc148781a32bbba906103517e07917a869f93ae48a29cfb01a2a59be2ecad","schema_version":"1.0","event_id":"sha256:866fc148781a32bbba906103517e07917a869f93ae48a29cfb01a2a59be2ecad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6OZ4PPEFRWUBS7OYUISZIHT6CV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andani Madodonga, Matthew Adendorff, Vukosi Marivate","submitted_at":"2023-06-12T21:02:12Z","abstract_excerpt":"Local/Native South African languages are classified as low-resource languages. As such, it is essential to build the resources for these languages so that they can benefit from advances in the field of natural language processing. In this work, the focus was to create annotated news datasets for the isiZulu and Siswati native languages based on news topic classification tasks and present the findings from these baseline classification models. Due to the shortage of data for these native South African languages, the datasets that were created were augmented and oversampled to increase data size"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07426","kind":"arxiv","version":1},"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/2306.07426/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":"2026-07-05T06:20:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7gHJpijuozLsprdHJeIzCQlVYMYXFrHIvL0MWYgTYt/9Z/Pqan0iVTm4yq22AigFto+BEfCg/wxQX1W/V1WYBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:26:04.220359Z"},"content_sha256":"cbb6a2acf4ae5a307fb50611abd8b71d24c09d7d370241b576310f9a919aa401","schema_version":"1.0","event_id":"sha256:cbb6a2acf4ae5a307fb50611abd8b71d24c09d7d370241b576310f9a919aa401"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/bundle.json","state_url":"https://pith.science/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/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":"2026-07-06T16:26:04Z","links":{"resolver":"https://pith.science/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV","bundle":"https://pith.science/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/bundle.json","state":"https://pith.science/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6OZ4PPEFRWUBS7OYUISZIHT6CV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6OZ4PPEFRWUBS7OYUISZIHT6CV","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":"8eac596ae6917950d0c3e1bfb989ec7c6c2f756b1cb85f14cfd01b58b220a62e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T21:02:12Z","title_canon_sha256":"a64f553dd1c0939fe0d97ca0726f327e58d12807adebe50a65eecfac271e8e16"},"schema_version":"1.0","source":{"id":"2306.07426","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07426","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07426v1","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07426","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_12","alias_value":"6OZ4PPEFRWUB","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_16","alias_value":"6OZ4PPEFRWUBS7OY","created_at":"2026-07-05T06:20:04Z"},{"alias_kind":"pith_short_8","alias_value":"6OZ4PPEF","created_at":"2026-07-05T06:20:04Z"}],"graph_snapshots":[{"event_id":"sha256:cbb6a2acf4ae5a307fb50611abd8b71d24c09d7d370241b576310f9a919aa401","target":"graph","created_at":"2026-07-05T06:20:04Z","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/2306.07426/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Local/Native South African languages are classified as low-resource languages. As such, it is essential to build the resources for these languages so that they can benefit from advances in the field of natural language processing. In this work, the focus was to create annotated news datasets for the isiZulu and Siswati native languages based on news topic classification tasks and present the findings from these baseline classification models. Due to the shortage of data for these native South African languages, the datasets that were created were augmented and oversampled to increase data size","authors_text":"Andani Madodonga, Matthew Adendorff, Vukosi Marivate","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T21:02:12Z","title":"Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07426","kind":"arxiv","version":1},"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":"sha256:866fc148781a32bbba906103517e07917a869f93ae48a29cfb01a2a59be2ecad","target":"record","created_at":"2026-07-05T06:20:04Z","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":"8eac596ae6917950d0c3e1bfb989ec7c6c2f756b1cb85f14cfd01b58b220a62e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T21:02:12Z","title_canon_sha256":"a64f553dd1c0939fe0d97ca0726f327e58d12807adebe50a65eecfac271e8e16"},"schema_version":"1.0","source":{"id":"2306.07426","kind":"arxiv","version":1}},"canonical_sha256":"f3b3c7bc858da8197dd8a225941e7e154866dbfbe119d0a21a442a3e2f3efbf6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3b3c7bc858da8197dd8a225941e7e154866dbfbe119d0a21a442a3e2f3efbf6","first_computed_at":"2026-07-05T06:20:04.211178Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:04.211178Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7xZ0UEScTUH+QAxt+jVDWlG+KJR61ZIVbPCijKYlM1nLVoVh+qd8HrAk7fD2NLKoYwL13Ibf1WW3KwKlwsbnBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:04.211669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07426","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:866fc148781a32bbba906103517e07917a869f93ae48a29cfb01a2a59be2ecad","sha256:cbb6a2acf4ae5a307fb50611abd8b71d24c09d7d370241b576310f9a919aa401"],"state_sha256":"957629c6cdaa9a5dc58eada64eea3a1d1fb5fb7009699f9979fd98c67225222c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MQtjl3n63p8z+iMlH83vx4MAWAQ4AAn4BcyXznHAfZwt16cugS3YFP4ZppiOOuerRSArbtYdRiKHiZ7bDw0bAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:26:04.223405Z","bundle_sha256":"419b462f820ccf2d907bb199c670e44820d80b213de207395733b904666e3b60"}}