{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:G3C7DYDOGUNB4PBQGPOENU3QNZ","short_pith_number":"pith:G3C7DYDO","canonical_record":{"source":{"id":"2003.10564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-23T22:07:15Z","cross_cats_sorted":[],"title_canon_sha256":"49c62fe07f7c51a05cbc151b343c9b7c11f1199af2aa39dc6ce3daf891c1e76b","abstract_canon_sha256":"62604daf3bc822d93f10b34df56c4f324972f9d9fcdfc03119fb9232ed3e26fc"},"schema_version":"1.0"},"canonical_sha256":"36c5f1e06e351a1e3c3033dc46d3706e79e9dbf6adc07d9a91d531640bd8cb58","source":{"kind":"arxiv","id":"2003.10564","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10564","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10564v1","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10564","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"G3C7DYDOGUNB","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"G3C7DYDOGUNB4PBQ","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"G3C7DYDO","created_at":"2026-07-05T00:50:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:G3C7DYDOGUNB4PBQGPOENU3QNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2003.10564","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-23T22:07:15Z","cross_cats_sorted":[],"title_canon_sha256":"49c62fe07f7c51a05cbc151b343c9b7c11f1199af2aa39dc6ce3daf891c1e76b","abstract_canon_sha256":"62604daf3bc822d93f10b34df56c4f324972f9d9fcdfc03119fb9232ed3e26fc"},"schema_version":"1.0"},"canonical_sha256":"36c5f1e06e351a1e3c3033dc46d3706e79e9dbf6adc07d9a91d531640bd8cb58","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:50:18.559405Z","signature_b64":"FBlJExhELJn5R8Mbqhz/IpoTApg8sHDbuYczuIAxEWYjAHIavpX3YhN5f6E0/6MS3tt/MzPA5ahZX6P3yV5EAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36c5f1e06e351a1e3c3033dc46d3706e79e9dbf6adc07d9a91d531640bd8cb58","last_reissued_at":"2026-07-05T00:50:18.558988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:50:18.558988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.10564","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":"2026-07-05T00:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SOvudl4YuNxOP4EhedZ6QJd3Iu4uQXoLEANUzOkp/WclbGyNg+OByZRXesPCOmjwq4jtxW49iE5nscChxQkTCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:38:04.834951Z"},"content_sha256":"f0afb65ffd509a20c06ca5a024ce68e40dd54dfcb681320aa369be4b4f3ff8a1","schema_version":"1.0","event_id":"sha256:f0afb65ffd509a20c06ca5a024ce68e40dd54dfcb681320aa369be4b4f3ff8a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:G3C7DYDOGUNB4PBQGPOENU3QNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Yor\\`ub\\'a Diacritic Restoration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David I. Adelani, Iroro Orife, Kola Tubosun, Olamilekan Wahab, Timi Fasubaa, Victor Williamson, Wuraola Fisayo Oyewusi","submitted_at":"2020-03-23T22:07:15Z","abstract_excerpt":"Yor\\`ub\\'a is a widely spoken West African language with a writing system rich in orthographic and tonal diacritics. They provide morphological information, are crucial for lexical disambiguation, pronunciation and are vital for any computational Speech or Natural Language Processing tasks. However diacritic marks are commonly excluded from electronic texts due to limited device and application support as well as general education on proper usage. We report on recent efforts at dataset cultivation. By aggregating and improving disparate texts from the web and various personal libraries, we wer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10564","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/2003.10564/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":"2026-07-05T00:50:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ea1VVsQ+dOW0iT1KZNvcfvwf0NlhvTG5JlPjF/iOVTJACXqfXc7STK+0Ptiy2o56SkYmLajgX5f1o+3yAmI3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T10:38:04.835913Z"},"content_sha256":"9e0a6e4dcbc4625eb67ce6b4da4ca586f594cafef19bbd8b5b199cde3645ee54","schema_version":"1.0","event_id":"sha256:9e0a6e4dcbc4625eb67ce6b4da4ca586f594cafef19bbd8b5b199cde3645ee54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/bundle.json","state_url":"https://pith.science/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/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":"2026-08-18T10:38:04Z","links":{"resolver":"https://pith.science/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ","bundle":"https://pith.science/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/bundle.json","state":"https://pith.science/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/G3C7DYDOGUNB4PBQGPOENU3QNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:G3C7DYDOGUNB4PBQGPOENU3QNZ","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":"62604daf3bc822d93f10b34df56c4f324972f9d9fcdfc03119fb9232ed3e26fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-23T22:07:15Z","title_canon_sha256":"49c62fe07f7c51a05cbc151b343c9b7c11f1199af2aa39dc6ce3daf891c1e76b"},"schema_version":"1.0","source":{"id":"2003.10564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.10564","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"arxiv_version","alias_value":"2003.10564v1","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.10564","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_12","alias_value":"G3C7DYDOGUNB","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_16","alias_value":"G3C7DYDOGUNB4PBQ","created_at":"2026-07-05T00:50:18Z"},{"alias_kind":"pith_short_8","alias_value":"G3C7DYDO","created_at":"2026-07-05T00:50:18Z"}],"graph_snapshots":[{"event_id":"sha256:9e0a6e4dcbc4625eb67ce6b4da4ca586f594cafef19bbd8b5b199cde3645ee54","target":"graph","created_at":"2026-07-05T00:50:18Z","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/2003.10564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Yor\\`ub\\'a is a widely spoken West African language with a writing system rich in orthographic and tonal diacritics. They provide morphological information, are crucial for lexical disambiguation, pronunciation and are vital for any computational Speech or Natural Language Processing tasks. However diacritic marks are commonly excluded from electronic texts due to limited device and application support as well as general education on proper usage. We report on recent efforts at dataset cultivation. By aggregating and improving disparate texts from the web and various personal libraries, we wer","authors_text":"David I. Adelani, Iroro Orife, Kola Tubosun, Olamilekan Wahab, Timi Fasubaa, Victor Williamson, Wuraola Fisayo Oyewusi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-23T22:07:15Z","title":"Improving Yor\\`ub\\'a Diacritic Restoration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.10564","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:f0afb65ffd509a20c06ca5a024ce68e40dd54dfcb681320aa369be4b4f3ff8a1","target":"record","created_at":"2026-07-05T00:50:18Z","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":"62604daf3bc822d93f10b34df56c4f324972f9d9fcdfc03119fb9232ed3e26fc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-23T22:07:15Z","title_canon_sha256":"49c62fe07f7c51a05cbc151b343c9b7c11f1199af2aa39dc6ce3daf891c1e76b"},"schema_version":"1.0","source":{"id":"2003.10564","kind":"arxiv","version":1}},"canonical_sha256":"36c5f1e06e351a1e3c3033dc46d3706e79e9dbf6adc07d9a91d531640bd8cb58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"36c5f1e06e351a1e3c3033dc46d3706e79e9dbf6adc07d9a91d531640bd8cb58","first_computed_at":"2026-07-05T00:50:18.558988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:50:18.558988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FBlJExhELJn5R8Mbqhz/IpoTApg8sHDbuYczuIAxEWYjAHIavpX3YhN5f6E0/6MS3tt/MzPA5ahZX6P3yV5EAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:50:18.559405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.10564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0afb65ffd509a20c06ca5a024ce68e40dd54dfcb681320aa369be4b4f3ff8a1","sha256:9e0a6e4dcbc4625eb67ce6b4da4ca586f594cafef19bbd8b5b199cde3645ee54"],"state_sha256":"e23dd9b1dc4823c281bf8194866ffbb40e92c9c57b68e2dede1f0058e8a800ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EBfZc/OO+cIMElT9ieYC6LCNrIZxJrCeBV9HqDLHz1HQnLXrC4rDBvECtzp+q2Fcbv3f7Qm0cXwAPwyx3ipfDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T10:38:04.844334Z","bundle_sha256":"a8a106586f0985f060fb1564ff72d8fe8c0506e3eaf885b50511162b605dcd00"}}