{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SJQEP3XW3EFEXNW3U2GJW2JPN3","short_pith_number":"pith:SJQEP3XW","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"},"canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","source":{"kind":"arxiv","id":"2501.15281","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15281","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15281v1","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15281","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"SJQEP3XW3EFE","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"SJQEP3XW3EFEXNW3","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"SJQEP3XW","created_at":"2026-07-05T10:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SJQEP3XW3EFEXNW3U2GJW2JPN3","target":"record","payload":{"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"},"canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","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"},"source_kind":"arxiv","source_id":"2501.15281","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":"2026-07-05T10:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AUgMzh3nT3+EHDeZJSMN+snw40/viwakLxjoncHl4YHyZN9/Tqe16XX/HTmJtny7Hj5ExuHOlnk/iMQ8b3HUBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:25:33.077392Z"},"content_sha256":"a0180b650a9443c27bfcd3d31c71adaf40646a2afb92635adcbd3917774d9211","schema_version":"1.0","event_id":"sha256:a0180b650a9443c27bfcd3d31c71adaf40646a2afb92635adcbd3917774d9211"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SJQEP3XW3EFEXNW3U2GJW2JPN3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HHO1Qty+SqMvN1YYbHwr7smG77RoE4aC1tcbgChEFNw2s72Q6q6FzIQ8Po+2YSO+NqNFlW3aQXZZygDvAwsCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T16:25:33.077959Z"},"content_sha256":"63ca3b146731e248199c3bd716c54986bcb9738971b9ee1d8428c913aa745a46","schema_version":"1.0","event_id":"sha256:63ca3b146731e248199c3bd716c54986bcb9738971b9ee1d8428c913aa745a46"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/bundle.json","state_url":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/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":"2026-08-15T16:25:33Z","links":{"resolver":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3","bundle":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/bundle.json","state":"https://pith.science/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJQEP3XW3EFEXNW3U2GJW2JPN3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SJQEP3XW3EFEXNW3U2GJW2JPN3","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":"725f2592227e3447c16c5e6805441699f47ef392b225f9b443571d65e0e1b408","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T17:25:06Z","title_canon_sha256":"2bae2ff6df8af3cc8974f2af8ae44ad79e663da27d7891ed528f2f4d3abac62d"},"schema_version":"1.0","source":{"id":"2501.15281","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15281","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15281v1","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15281","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"SJQEP3XW3EFE","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"SJQEP3XW3EFEXNW3","created_at":"2026-07-05T10:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"SJQEP3XW","created_at":"2026-07-05T10:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:63ca3b146731e248199c3bd716c54986bcb9738971b9ee1d8428c913aa745a46","target":"graph","created_at":"2026-07-05T10:05:26Z","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/2501.15281/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Marelie H. Davel, Simon P. Ramalepe, Thipe I. Modipa","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T17:25:06Z","title":"Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15281","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:a0180b650a9443c27bfcd3d31c71adaf40646a2afb92635adcbd3917774d9211","target":"record","created_at":"2026-07-05T10:05:26Z","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":"725f2592227e3447c16c5e6805441699f47ef392b225f9b443571d65e0e1b408","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-25T17:25:06Z","title_canon_sha256":"2bae2ff6df8af3cc8974f2af8ae44ad79e663da27d7891ed528f2f4d3abac62d"},"schema_version":"1.0","source":{"id":"2501.15281","kind":"arxiv","version":1}},"canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"926047eef6d90a4bb6dba68c9b692f6ec2936383d05efd9d198b63802e11fd4b","first_computed_at":"2026-07-05T10:05:26.759842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:26.759842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qNfxzyMt0homRWvF2Skfam+yvZVYtDUVsds9GYhO1alnZCtkrcdx4Jp0uS24XhILlJnK7jb6JFoNeDn8r6S9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:26.760394Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15281","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0180b650a9443c27bfcd3d31c71adaf40646a2afb92635adcbd3917774d9211","sha256:63ca3b146731e248199c3bd716c54986bcb9738971b9ee1d8428c913aa745a46"],"state_sha256":"e2f2b9808459702610a2186601f9c14df4644888f73498a3aa929d16c5c136b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ye8BOmL8trpFeGMBpYf0fVhBDNVZ25Ba03G3bdTc8/k6NMwP2l+Co4lEv8cxvcXBuAHUrGUBHpIONUI5OH2aBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T16:25:33.083321Z","bundle_sha256":"93f9ac205d4f69e8c9fcd4d3ba286e39b7a20223bf240536e1422a58bf794906"}}