{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AJANWMQGBK25QDEB42ZHFCTWXU","short_pith_number":"pith:AJANWMQG","canonical_record":{"source":{"id":"2501.11003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T10:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"3cc8186c95a48cf2d1662d3d44f301e1cb2bd43693ca4ebdb0c60ef9dae653de","abstract_canon_sha256":"7ea47d92b330b491d49399bbd337f4023be797c394adc17ebe9ba88e82d9db65"},"schema_version":"1.0"},"canonical_sha256":"0240db32060ab5d80c81e6b2728a76bd3d02fec176475ef3ea4d9409f76f0f07","source":{"kind":"arxiv","id":"2501.11003","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11003","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11003v1","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11003","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"AJANWMQGBK25","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"AJANWMQGBK25QDEB","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"AJANWMQG","created_at":"2026-07-05T10:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AJANWMQGBK25QDEB42ZHFCTWXU","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11003","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T10:17:21Z","cross_cats_sorted":[],"title_canon_sha256":"3cc8186c95a48cf2d1662d3d44f301e1cb2bd43693ca4ebdb0c60ef9dae653de","abstract_canon_sha256":"7ea47d92b330b491d49399bbd337f4023be797c394adc17ebe9ba88e82d9db65"},"schema_version":"1.0"},"canonical_sha256":"0240db32060ab5d80c81e6b2728a76bd3d02fec176475ef3ea4d9409f76f0f07","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:01.746685Z","signature_b64":"HI1BTJCnRHjo9Q3ssiNT7xmyHXxTJRzm0J56k/3jjAd4mQ/+xMkKQhPPJsOm2ml5YgOGK3XYdbiAkLR9AMHbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0240db32060ab5d80c81e6b2728a76bd3d02fec176475ef3ea4d9409f76f0f07","last_reissued_at":"2026-07-05T10:03:01.746263Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:01.746263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11003","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":"2026-07-05T10:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Pgpg7EGLt2uUIqJFUy1Dof/RT/ZGC01SUMhZBaIzf+mc0oM994iZ+jhEUuCUWx9ra4Ec9NXT1A+iRDFyMtRRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:46:38.416530Z"},"content_sha256":"0327320a8d013ef4418a5499e9fb28d2b37639cf933cca321428478e1b64a6d5","schema_version":"1.0","event_id":"sha256:0327320a8d013ef4418a5499e9fb28d2b37639cf933cca321428478e1b64a6d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AJANWMQGBK25QDEB42ZHFCTWXU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building low-resource African language corpora: A case study of Kidawida, Kalenjin and Dholuo","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Kipkebut, Audrey Mbogho, Lilian Wanzare, Quin Awuor, Vivian Oloo","submitted_at":"2025-01-19T10:17:21Z","abstract_excerpt":"Natural Language Processing is a crucial frontier in artificial intelligence, with broad applications in many areas, including public health, agriculture, education, and commerce. However, due to the lack of substantial linguistic resources, many African languages remain underrepresented in this digital transformation. This paper presents a case study on the development of linguistic corpora for three under-resourced Kenyan languages, Kidaw'ida, Kalenjin, and Dholuo, with the aim of advancing natural language processing and linguistic research in African communities. Our project, which lasted "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11003","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/2501.11003/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":"2026-07-05T10:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DFuE5T6fdOShJcwUMNBsQJaS6dmr1ch3qfR4Cp0qNfZhZC2RcDTDzeUL9Bi5bSF/uFu2EJrWoR+fkHzVS5cGDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T09:46:38.417436Z"},"content_sha256":"00107e42d9471925273d764a1ba2bd27a6ee261867dc09b4cd6a12be5cd8b50d","schema_version":"1.0","event_id":"sha256:00107e42d9471925273d764a1ba2bd27a6ee261867dc09b4cd6a12be5cd8b50d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJANWMQGBK25QDEB42ZHFCTWXU/bundle.json","state_url":"https://pith.science/pith/AJANWMQGBK25QDEB42ZHFCTWXU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJANWMQGBK25QDEB42ZHFCTWXU/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":"2026-08-21T09:46:38Z","links":{"resolver":"https://pith.science/pith/AJANWMQGBK25QDEB42ZHFCTWXU","bundle":"https://pith.science/pith/AJANWMQGBK25QDEB42ZHFCTWXU/bundle.json","state":"https://pith.science/pith/AJANWMQGBK25QDEB42ZHFCTWXU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJANWMQGBK25QDEB42ZHFCTWXU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AJANWMQGBK25QDEB42ZHFCTWXU","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":"7ea47d92b330b491d49399bbd337f4023be797c394adc17ebe9ba88e82d9db65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T10:17:21Z","title_canon_sha256":"3cc8186c95a48cf2d1662d3d44f301e1cb2bd43693ca4ebdb0c60ef9dae653de"},"schema_version":"1.0","source":{"id":"2501.11003","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11003","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11003v1","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11003","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"AJANWMQGBK25","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"AJANWMQGBK25QDEB","created_at":"2026-07-05T10:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"AJANWMQG","created_at":"2026-07-05T10:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:00107e42d9471925273d764a1ba2bd27a6ee261867dc09b4cd6a12be5cd8b50d","target":"graph","created_at":"2026-07-05T10:03:01Z","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/2501.11003/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural Language Processing is a crucial frontier in artificial intelligence, with broad applications in many areas, including public health, agriculture, education, and commerce. However, due to the lack of substantial linguistic resources, many African languages remain underrepresented in this digital transformation. This paper presents a case study on the development of linguistic corpora for three under-resourced Kenyan languages, Kidaw'ida, Kalenjin, and Dholuo, with the aim of advancing natural language processing and linguistic research in African communities. Our project, which lasted ","authors_text":"Andrew Kipkebut, Audrey Mbogho, Lilian Wanzare, Quin Awuor, Vivian Oloo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T10:17:21Z","title":"Building low-resource African language corpora: A case study of Kidawida, Kalenjin and Dholuo"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11003","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":"sha256:0327320a8d013ef4418a5499e9fb28d2b37639cf933cca321428478e1b64a6d5","target":"record","created_at":"2026-07-05T10:03:01Z","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":"7ea47d92b330b491d49399bbd337f4023be797c394adc17ebe9ba88e82d9db65","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T10:17:21Z","title_canon_sha256":"3cc8186c95a48cf2d1662d3d44f301e1cb2bd43693ca4ebdb0c60ef9dae653de"},"schema_version":"1.0","source":{"id":"2501.11003","kind":"arxiv","version":1}},"canonical_sha256":"0240db32060ab5d80c81e6b2728a76bd3d02fec176475ef3ea4d9409f76f0f07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0240db32060ab5d80c81e6b2728a76bd3d02fec176475ef3ea4d9409f76f0f07","first_computed_at":"2026-07-05T10:03:01.746263Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:01.746263Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HI1BTJCnRHjo9Q3ssiNT7xmyHXxTJRzm0J56k/3jjAd4mQ/+xMkKQhPPJsOm2ml5YgOGK3XYdbiAkLR9AMHbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:01.746685Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11003","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0327320a8d013ef4418a5499e9fb28d2b37639cf933cca321428478e1b64a6d5","sha256:00107e42d9471925273d764a1ba2bd27a6ee261867dc09b4cd6a12be5cd8b50d"],"state_sha256":"464357abbe73a82cf695d1a393e52ef5c4372e04f44f1bbc50998f5f6bc7d320"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AfEuy/5plXorCRIV8bE/+4U3Q8IEQbNgEtjg99O+ctCHf6HYKdKxIzKmUpH6bZ45KliWv2pFFoLZstURQz5tBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T09:46:38.423361Z","bundle_sha256":"056761d271a6f3d7805736afaedfaf2522b890578c65b4d920d7316df8967f9a"}}