{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SJQEP3XW3EFEXNW3U2GJW2JPN3","short_pith_number":"pith:SJQEP3XW","schema_version":"1.0","canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","source":{"kind":"arxiv","id":"2501.15281","version":1},"attestation_state":"computed","paper":{"title":"Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Marelie H. Davel, Simon P. Ramalepe, Thipe I. Modipa","submitted_at":"2025-01-25T17:25:06Z","abstract_excerpt":"Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.15281","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T17:25:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2bae2ff6df8af3cc8974f2af8ae44ad79e663da27d7891ed528f2f4d3abac62d","abstract_canon_sha256":"725f2592227e3447c16c5e6805441699f47ef392b225f9b443571d65e0e1b408"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:26.760394Z","signature_b64":"qNfxzyMt0homRWvF2Skfam+yvZVYtDUVsds9GYhO1alnZCtkrcdx4Jp0uS24XhILlJnK7jb6JFoNeDn8r6S9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","last_reissued_at":"2026-07-05T10:05:26.759842Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:26.759842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Marelie H. Davel, Simon P. Ramalepe, Thipe I. Modipa","submitted_at":"2025-01-25T17:25:06Z","abstract_excerpt":"Due to the scarcity of data in low-resourced languages, the development of language models for these languages has been very slow. Currently, pre-trained language models have gained popularity in natural language processing, especially, in developing domain-specific models for low-resourced languages. In this study, we experiment with the impact of using occlusion-based techniques when training a language model for a text generation task. We curate 2 new datasets, the Sepedi monolingual (SepMono) dataset from several South African resources and the Sepedi radio news (SepNews) dataset from the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15281","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/2501.15281/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.15281","created_at":"2026-07-05T10:05:26.759903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15281v1","created_at":"2026-07-05T10:05:26.759903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15281","created_at":"2026-07-05T10:05:26.759903+00:00"},{"alias_kind":"pith_short_12","alias_value":"SJQEP3XW3EFE","created_at":"2026-07-05T10:05:26.759903+00:00"},{"alias_kind":"pith_short_16","alias_value":"SJQEP3XW3EFEXNW3","created_at":"2026-07-05T10:05:26.759903+00:00"},{"alias_kind":"pith_short_8","alias_value":"SJQEP3XW","created_at":"2026-07-05T10:05:26.759903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3","json":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3.json","graph_json":"https://pith.science/api/pith-number/SJQEP3XW3EFEXNW3U2GJW2JPN3/graph.json","events_json":"https://pith.science/api/pith-number/SJQEP3XW3EFEXNW3U2GJW2JPN3/events.json","paper":"https://pith.science/paper/SJQEP3XW"},"agent_actions":{"view_html":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3","download_json":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3.json","view_paper":"https://pith.science/paper/SJQEP3XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15281&json=true","fetch_graph":"https://pith.science/api/pith-number/SJQEP3XW3EFEXNW3U2GJW2JPN3/graph.json","fetch_events":"https://pith.science/api/pith-number/SJQEP3XW3EFEXNW3U2GJW2JPN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/action/storage_attestation","attest_author":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/action/author_attestation","sign_citation":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/action/citation_signature","submit_replication":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/action/replication_record"}},"created_at":"2026-07-05T10:05:26.759903+00:00","updated_at":"2026-07-05T10:05:26.759903+00:00"}