{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5A32OCF5KRMPQVCOX7B5F33FH6","short_pith_number":"pith:5A32OCF5","canonical_record":{"source":{"id":"2104.00772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"4fa021da28478d0bc44968d0872f858fc24fd69b5c58f843726596edb4727597","abstract_canon_sha256":"2d1d785e4696a4974377b15cf28e22f0bcf5642bd18990e8c4a0a4809f680d3f"},"schema_version":"1.0"},"canonical_sha256":"e837a708bd5458f8544ebfc3d2ef653fa34e61ec6720195004618d5b0b0b1b72","source":{"kind":"arxiv","id":"2104.00772","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00772","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00772v1","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00772","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_12","alias_value":"5A32OCF5KRMP","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"5A32OCF5KRMPQVCO","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"5A32OCF5","created_at":"2026-07-05T02:28:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5A32OCF5KRMPQVCOX7B5F33FH6","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00772","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"4fa021da28478d0bc44968d0872f858fc24fd69b5c58f843726596edb4727597","abstract_canon_sha256":"2d1d785e4696a4974377b15cf28e22f0bcf5642bd18990e8c4a0a4809f680d3f"},"schema_version":"1.0"},"canonical_sha256":"e837a708bd5458f8544ebfc3d2ef653fa34e61ec6720195004618d5b0b0b1b72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:35.674608Z","signature_b64":"FmE797XgVyWqoDhEuP5OVs+VbxTvmNmnHRpfXpWmgLGIE3+tPpQNfsDBJ4SA2mjc8/ailu0RELvUUMj94vYKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e837a708bd5458f8544ebfc3d2ef653fa34e61ec6720195004618d5b0b0b1b72","last_reissued_at":"2026-07-05T02:28:35.674265Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:35.674265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00772","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":"2026-07-05T02:28:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vubPLYvw+pXmi3yKg8rddm9aKIzMIwKDu6t9UQSVTlxNRzdBazqQxdHV0fCbX5o1Ip/ur1r2DwL8WOhbRTmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:06:09.133975Z"},"content_sha256":"e8bbcb3a7dc075421aac07a5cf14de08e224b87b794ff9505ff44d8be90aa05f","schema_version":"1.0","event_id":"sha256:e8bbcb3a7dc075421aac07a5cf14de08e224b87b794ff9505ff44d8be90aa05f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5A32OCF5KRMPQVCOX7B5F33FH6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Low-Resource Language Modelling of South African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jan Buys, Jared Shapiro, Luc Hayward, Stuart Mesham","submitted_at":"2021-04-01T21:27:27Z","abstract_excerpt":"Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited, which is made more challenging by the lack of large or standardised training and evaluation sets that exist for English and other high-resource languages. In this paper, we evaluate the performance of open-vocabulary language models on low-resource South African languages, using byte-pair encoding to handle the rich morphology of these languages. We evaluate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00772","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/2104.00772/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":"2026-07-05T02:28:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nMqih/IbDRZDQnOY16z/gpAhSqoFKN6dyRAjXSUYh1yqK5bqUNv3J6/Asjom6Lrx3kwgO8aXdppLicogcWH9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T04:06:09.134824Z"},"content_sha256":"10044a27fc0362275b30497031db074f03e0b137499dfebf48173174b89576ab","schema_version":"1.0","event_id":"sha256:10044a27fc0362275b30497031db074f03e0b137499dfebf48173174b89576ab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5A32OCF5KRMPQVCOX7B5F33FH6/bundle.json","state_url":"https://pith.science/pith/5A32OCF5KRMPQVCOX7B5F33FH6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5A32OCF5KRMPQVCOX7B5F33FH6/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":"2026-08-04T04:06:09Z","links":{"resolver":"https://pith.science/pith/5A32OCF5KRMPQVCOX7B5F33FH6","bundle":"https://pith.science/pith/5A32OCF5KRMPQVCOX7B5F33FH6/bundle.json","state":"https://pith.science/pith/5A32OCF5KRMPQVCOX7B5F33FH6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5A32OCF5KRMPQVCOX7B5F33FH6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5A32OCF5KRMPQVCOX7B5F33FH6","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":"2d1d785e4696a4974377b15cf28e22f0bcf5642bd18990e8c4a0a4809f680d3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:27:27Z","title_canon_sha256":"4fa021da28478d0bc44968d0872f858fc24fd69b5c58f843726596edb4727597"},"schema_version":"1.0","source":{"id":"2104.00772","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00772","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00772v1","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00772","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_12","alias_value":"5A32OCF5KRMP","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"5A32OCF5KRMPQVCO","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"5A32OCF5","created_at":"2026-07-05T02:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:10044a27fc0362275b30497031db074f03e0b137499dfebf48173174b89576ab","target":"graph","created_at":"2026-07-05T02:28:35Z","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/2104.00772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are the foundation of current neural network-based models for natural language understanding and generation. However, research on the intrinsic performance of language models on African languages has been extremely limited, which is made more challenging by the lack of large or standardised training and evaluation sets that exist for English and other high-resource languages. In this paper, we evaluate the performance of open-vocabulary language models on low-resource South African languages, using byte-pair encoding to handle the rich morphology of these languages. We evaluate","authors_text":"Jan Buys, Jared Shapiro, Luc Hayward, Stuart Mesham","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:27:27Z","title":"Low-Resource Language Modelling of South African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00772","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:e8bbcb3a7dc075421aac07a5cf14de08e224b87b794ff9505ff44d8be90aa05f","target":"record","created_at":"2026-07-05T02:28:35Z","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":"2d1d785e4696a4974377b15cf28e22f0bcf5642bd18990e8c4a0a4809f680d3f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:27:27Z","title_canon_sha256":"4fa021da28478d0bc44968d0872f858fc24fd69b5c58f843726596edb4727597"},"schema_version":"1.0","source":{"id":"2104.00772","kind":"arxiv","version":1}},"canonical_sha256":"e837a708bd5458f8544ebfc3d2ef653fa34e61ec6720195004618d5b0b0b1b72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e837a708bd5458f8544ebfc3d2ef653fa34e61ec6720195004618d5b0b0b1b72","first_computed_at":"2026-07-05T02:28:35.674265Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:35.674265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FmE797XgVyWqoDhEuP5OVs+VbxTvmNmnHRpfXpWmgLGIE3+tPpQNfsDBJ4SA2mjc8/ailu0RELvUUMj94vYKAg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:35.674608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00772","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8bbcb3a7dc075421aac07a5cf14de08e224b87b794ff9505ff44d8be90aa05f","sha256:10044a27fc0362275b30497031db074f03e0b137499dfebf48173174b89576ab"],"state_sha256":"6b16a5903b516058aa458c7035f64b20699e5203ad6fceea11f9781716adee8e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0QPdCaC8oqrDwZzdrraPXa/gx62+4z+aP/bMN//RvcsA3yt3nADBRgVp0pOGDQVLo/KUouLMLtb6pHkqq118CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T04:06:09.140489Z","bundle_sha256":"03f2c092aa7cb9fb9eca03bd5787d9a7f2770bbedf14d69e161fa8a99a08cb6b"}}