{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:42245LDJN32NHVDRNG3L524IQL","short_pith_number":"pith:42245LDJ","canonical_record":{"source":{"id":"2507.00297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64363b17ba53b409de1052a8464c915b1bc9c0e503bfce6461b643469334b2b0","abstract_canon_sha256":"35f90930e6732a1d9b4c856a007f106d4dc9b365d7382367c540a66cdaec296c"},"schema_version":"1.0"},"canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","source":{"kind":"arxiv","id":"2507.00297","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00297","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00297v1","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00297","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_12","alias_value":"42245LDJN32N","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_16","alias_value":"42245LDJN32NHVDR","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_8","alias_value":"42245LDJ","created_at":"2026-07-05T11:30:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:42245LDJN32NHVDRNG3L524IQL","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00297","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"64363b17ba53b409de1052a8464c915b1bc9c0e503bfce6461b643469334b2b0","abstract_canon_sha256":"35f90930e6732a1d9b4c856a007f106d4dc9b365d7382367c540a66cdaec296c"},"schema_version":"1.0"},"canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:05.722767Z","signature_b64":"Px8slc+ulo8CFyoYeYpSTP7nwdqOh5g5agwjyJQt2aRQmIvrhE/9ecVr0nB64Cr6yIoX61h/ATrdR7dUZPbICw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","last_reissued_at":"2026-07-05T11:30:05.722394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:05.722394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00297","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":"2026-07-05T11:30:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8NYOEObvo6xxlHyltk7i71ez7rioqkT2IBjO/49KKVTDjWqhvpYXtDBoiI5ueL/Db8xVKx3irIbqmscX+tSXCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:45.217017Z"},"content_sha256":"6b6a4576d1ada65b3dcb65fc68b97f99682cf72f9a95d58aea2ce4350ff8d41b","schema_version":"1.0","event_id":"sha256:6b6a4576d1ada65b3dcb65fc68b97f99682cf72f9a95d58aea2ce4350ff8d41b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:42245LDJN32NHVDRNG3L524IQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural language processing for African languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"David Ifeoluwa Adelani","submitted_at":"2025-06-30T22:26:36Z","abstract_excerpt":"Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the indigenous languages in this region can be regarded as low-resourced in terms of the availability of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00297","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/2507.00297/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":"2026-07-05T11:30:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1xRWx1YSX9uCMKRlySveJpthv2Cf7CVJIgEfw/ZKfdBGZqEkhvJRfTriL9LEgrpVPuVwm9cjD+D1bvOLXNf9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T08:32:45.217523Z"},"content_sha256":"60151a2fb30aa60b35602b76d4df930e6d8b253e39a35898c4988c21269c766a","schema_version":"1.0","event_id":"sha256:60151a2fb30aa60b35602b76d4df930e6d8b253e39a35898c4988c21269c766a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/bundle.json","state_url":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42245LDJN32NHVDRNG3L524IQL/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":"2026-08-08T08:32:45Z","links":{"resolver":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL","bundle":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/bundle.json","state":"https://pith.science/pith/42245LDJN32NHVDRNG3L524IQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42245LDJN32NHVDRNG3L524IQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:42245LDJN32NHVDRNG3L524IQL","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":"35f90930e6732a1d9b4c856a007f106d4dc9b365d7382367c540a66cdaec296c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","title_canon_sha256":"64363b17ba53b409de1052a8464c915b1bc9c0e503bfce6461b643469334b2b0"},"schema_version":"1.0","source":{"id":"2507.00297","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00297","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00297v1","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00297","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_12","alias_value":"42245LDJN32N","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_16","alias_value":"42245LDJN32NHVDR","created_at":"2026-07-05T11:30:05Z"},{"alias_kind":"pith_short_8","alias_value":"42245LDJ","created_at":"2026-07-05T11:30:05Z"}],"graph_snapshots":[{"event_id":"sha256:60151a2fb30aa60b35602b76d4df930e6d8b253e39a35898c4988c21269c766a","target":"graph","created_at":"2026-07-05T11:30:05Z","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/2507.00297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in word embeddings and language models use large-scale, unlabelled data and self-supervised learning to boost NLP performance. Multilingual models, often trained on web-sourced data like Wikipedia, face challenges: few low-resource languages are included, their data is often noisy, and lack of labeled datasets makes it hard to evaluate performance outside high-resource languages like English. In this dissertation, we focus on languages spoken in Sub-Saharan Africa where all the indigenous languages in this region can be regarded as low-resourced in terms of the availability of ","authors_text":"David Ifeoluwa Adelani","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","title":"Natural language processing for African languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00297","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":"sha256:6b6a4576d1ada65b3dcb65fc68b97f99682cf72f9a95d58aea2ce4350ff8d41b","target":"record","created_at":"2026-07-05T11:30:05Z","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":"35f90930e6732a1d9b4c856a007f106d4dc9b365d7382367c540a66cdaec296c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-30T22:26:36Z","title_canon_sha256":"64363b17ba53b409de1052a8464c915b1bc9c0e503bfce6461b643469334b2b0"},"schema_version":"1.0","source":{"id":"2507.00297","kind":"arxiv","version":1}},"canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6b5ceac696ef4d3d47169b6beeb8882e0f2307b0abe4143703e7f35941768ed","first_computed_at":"2026-07-05T11:30:05.722394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:30:05.722394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Px8slc+ulo8CFyoYeYpSTP7nwdqOh5g5agwjyJQt2aRQmIvrhE/9ecVr0nB64Cr6yIoX61h/ATrdR7dUZPbICw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:30:05.722767Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00297","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b6a4576d1ada65b3dcb65fc68b97f99682cf72f9a95d58aea2ce4350ff8d41b","sha256:60151a2fb30aa60b35602b76d4df930e6d8b253e39a35898c4988c21269c766a"],"state_sha256":"02a703d8ed818ed69c44b31d360442129ed419d128a6b312af25e74def21d6dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oW5R0micktfMZL9cRFoCwrQybJNmKve20zP83oR07KgM2myiFGdFwHVG2qUMUmilF7MOCykCiv14uvhbxPeZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T08:32:45.222327Z","bundle_sha256":"ebad810201893f8d44f3301063d1e9a919a69a51414a7eddd13cb1b3cfacb6f2"}}