{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YIWXZV2NF4UVJS53Q74YHZZIW6","short_pith_number":"pith:YIWXZV2N","canonical_record":{"source":{"id":"2304.12155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T17:32:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5639334e9379cd19024cfebb4b0300df41e668c602f9d8203e7d090979dfed0f","abstract_canon_sha256":"d820d042b105720426373c895fda35a5bb2c2f1395c46476b2a6c0c39bec0b08"},"schema_version":"1.0"},"canonical_sha256":"c22d7cd74d2f2954cbbb87f983e728b7b7874e7892319a9a1568dea5ea6f3e20","source":{"kind":"arxiv","id":"2304.12155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12155","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12155v1","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12155","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"YIWXZV2NF4UV","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"YIWXZV2NF4UVJS53","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"YIWXZV2N","created_at":"2026-07-05T06:03:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YIWXZV2NF4UVJS53Q74YHZZIW6","target":"record","payload":{"canonical_record":{"source":{"id":"2304.12155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T17:32:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5639334e9379cd19024cfebb4b0300df41e668c602f9d8203e7d090979dfed0f","abstract_canon_sha256":"d820d042b105720426373c895fda35a5bb2c2f1395c46476b2a6c0c39bec0b08"},"schema_version":"1.0"},"canonical_sha256":"c22d7cd74d2f2954cbbb87f983e728b7b7874e7892319a9a1568dea5ea6f3e20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:48.428526Z","signature_b64":"P7t/Mlvpva1Zik7G5aozHFM7qYX5PquI9U2+LJekwr+F951BVFtWU0j/GqtnBOHxy75CRUNtkjfH4W1JlaQFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22d7cd74d2f2954cbbb87f983e728b7b7874e7892319a9a1568dea5ea6f3e20","last_reissued_at":"2026-07-05T06:03:48.428089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:48.428089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.12155","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":"2026-07-05T06:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3+yzVIjfQZc8+ke9G3+pCXWaRp4NlGQdN0gWUzwBTcZaFQ+H+lwr/dFtqXDrV6RAucT8NRN9TQhJWcnNhxApBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:33:37.600187Z"},"content_sha256":"a8a919c551b6ec287638796abcf62260bc35c76b7a9bc6e6ff44411783a2cf5f","schema_version":"1.0","event_id":"sha256:a8a919c551b6ec287638796abcf62260bc35c76b7a9bc6e6ff44411783a2cf5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YIWXZV2NF4UVJS53Q74YHZZIW6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The African Stopwords project: curating stopwords for African languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Atnafu Lambebo Tonja, Benjamin Ajibade, Bonaventure F.P. Dossou, Chiamaka Chukwuneke, Chris Emezue, Cynthia Thinwa, Davis David, Emeka Onwuegbuzia, Handel Emezue, Hellina Nigatu, Helper Zhou, Idris Abdulmumin, Ifeoluwatayo A. Ige, Kaosarat Aina, Lerato Louis, Mbonu Chinedu Emmanuel, Naome A. Etori, Olanrewaju Samuel, Oreen Yousuf, Oviawe Joshua, Samuel Oyerinde, Shamsuddeen Muhammad","submitted_at":"2023-03-21T17:32:01Z","abstract_excerpt":"Stopwords are fundamental in Natural Language Processing (NLP) techniques for information retrieval. One of the common tasks in preprocessing of text data is the removal of stopwords. Currently, while high-resource languages like English benefit from the availability of several stopwords, low-resource languages, such as those found in the African continent, have none that are standardized and available for use in NLP packages. Stopwords in the context of African languages are understudied and can reveal information about the crossover between languages. The \\textit{African Stopwords} project a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12155","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/2304.12155/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":"2026-07-05T06:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtkrIitr1IP5nP5E/7Dg7cgGg+fWAnXl3zjLEhq4Ui7pViWbRX/lLaEUaenwyhd1zlyW7lR+P+XJXij1t07tAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:33:37.600690Z"},"content_sha256":"acbcbf130ad5c28405b46deb3dd34020f6248238d490cc7e644e98658aa6db81","schema_version":"1.0","event_id":"sha256:acbcbf130ad5c28405b46deb3dd34020f6248238d490cc7e644e98658aa6db81"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/bundle.json","state_url":"https://pith.science/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/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":"2026-08-20T09:33:37Z","links":{"resolver":"https://pith.science/pith/YIWXZV2NF4UVJS53Q74YHZZIW6","bundle":"https://pith.science/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/bundle.json","state":"https://pith.science/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YIWXZV2NF4UVJS53Q74YHZZIW6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YIWXZV2NF4UVJS53Q74YHZZIW6","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":"d820d042b105720426373c895fda35a5bb2c2f1395c46476b2a6c0c39bec0b08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T17:32:01Z","title_canon_sha256":"5639334e9379cd19024cfebb4b0300df41e668c602f9d8203e7d090979dfed0f"},"schema_version":"1.0","source":{"id":"2304.12155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.12155","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2304.12155v1","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.12155","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"YIWXZV2NF4UV","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"YIWXZV2NF4UVJS53","created_at":"2026-07-05T06:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"YIWXZV2N","created_at":"2026-07-05T06:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:acbcbf130ad5c28405b46deb3dd34020f6248238d490cc7e644e98658aa6db81","target":"graph","created_at":"2026-07-05T06:03:48Z","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/2304.12155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stopwords are fundamental in Natural Language Processing (NLP) techniques for information retrieval. One of the common tasks in preprocessing of text data is the removal of stopwords. Currently, while high-resource languages like English benefit from the availability of several stopwords, low-resource languages, such as those found in the African continent, have none that are standardized and available for use in NLP packages. Stopwords in the context of African languages are understudied and can reveal information about the crossover between languages. The \\textit{African Stopwords} project a","authors_text":"Atnafu Lambebo Tonja, Benjamin Ajibade, Bonaventure F.P. Dossou, Chiamaka Chukwuneke, Chris Emezue, Cynthia Thinwa, Davis David, Emeka Onwuegbuzia, Handel Emezue, Hellina Nigatu, Helper Zhou, Idris Abdulmumin, Ifeoluwatayo A. Ige, Kaosarat Aina, Lerato Louis, Mbonu Chinedu Emmanuel, Naome A. Etori, Olanrewaju Samuel, Oreen Yousuf, Oviawe Joshua, Samuel Oyerinde, Shamsuddeen Muhammad","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T17:32:01Z","title":"The African Stopwords project: curating stopwords for African languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.12155","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:a8a919c551b6ec287638796abcf62260bc35c76b7a9bc6e6ff44411783a2cf5f","target":"record","created_at":"2026-07-05T06:03:48Z","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":"d820d042b105720426373c895fda35a5bb2c2f1395c46476b2a6c0c39bec0b08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-21T17:32:01Z","title_canon_sha256":"5639334e9379cd19024cfebb4b0300df41e668c602f9d8203e7d090979dfed0f"},"schema_version":"1.0","source":{"id":"2304.12155","kind":"arxiv","version":1}},"canonical_sha256":"c22d7cd74d2f2954cbbb87f983e728b7b7874e7892319a9a1568dea5ea6f3e20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22d7cd74d2f2954cbbb87f983e728b7b7874e7892319a9a1568dea5ea6f3e20","first_computed_at":"2026-07-05T06:03:48.428089Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:48.428089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P7t/Mlvpva1Zik7G5aozHFM7qYX5PquI9U2+LJekwr+F951BVFtWU0j/GqtnBOHxy75CRUNtkjfH4W1JlaQFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:48.428526Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.12155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8a919c551b6ec287638796abcf62260bc35c76b7a9bc6e6ff44411783a2cf5f","sha256:acbcbf130ad5c28405b46deb3dd34020f6248238d490cc7e644e98658aa6db81"],"state_sha256":"a9478eebaf3969edd83fa9bfca2763ff8ffa2ce78bbf710f5fe9afeb75e7a91c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RmoxdoPcdhwlyv3pbM3BzG8rAY5mpOa4EEwIHenW9WDb22b2Fhnz8bdUNn/WpGORQWQXDNma09yhp6QvHbGHAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T09:33:37.605396Z","bundle_sha256":"55547b11ca70a45b7b867c6c0697ce39b05762b5dbe87b7d0fb2132e16cd81b0"}}