{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WMOSC22K2O5XTHSCWTFWRU22G2","short_pith_number":"pith:WMOSC22K","canonical_record":{"source":{"id":"2401.13398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T11:52:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04cd3529b1ec9bee7af14e0e6349e39837089264aadabc92bf7e2d614bad1071","abstract_canon_sha256":"f428dbea0309a9b0a1044864722157c495e228568a30378e68a7077769f397fb"},"schema_version":"1.0"},"canonical_sha256":"b31d216b4ad3bb799e42b4cb68d35a36b729b89205779d7f2a90684c8560091b","source":{"kind":"arxiv","id":"2401.13398","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13398","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13398v1","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13398","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"WMOSC22K2O5X","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"WMOSC22K2O5XTHSC","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"WMOSC22K","created_at":"2026-07-05T07:37:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WMOSC22K2O5XTHSCWTFWRU22G2","target":"record","payload":{"canonical_record":{"source":{"id":"2401.13398","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T11:52:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04cd3529b1ec9bee7af14e0e6349e39837089264aadabc92bf7e2d614bad1071","abstract_canon_sha256":"f428dbea0309a9b0a1044864722157c495e228568a30378e68a7077769f397fb"},"schema_version":"1.0"},"canonical_sha256":"b31d216b4ad3bb799e42b4cb68d35a36b729b89205779d7f2a90684c8560091b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:04.989361Z","signature_b64":"h90n6zj9cQl4UrdTcq06SVNiS10/ONy9GTycDY0oYWcN5n+9aLAgZ6uIHTW36B04Es1wl4af75fCXIA5QLf+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31d216b4ad3bb799e42b4cb68d35a36b729b89205779d7f2a90684c8560091b","last_reissued_at":"2026-07-05T07:37:04.988942Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:04.988942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.13398","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":"2026-07-05T07:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jq+RdWN5q05XEXBMTj+7HnPDcC3mNtBW/JYyTZMqGlrD4XkRkX39n6ZP/D9PznqoGFMLvVOX2m2AsZ/HuGPIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T08:58:24.960037Z"},"content_sha256":"fafdcef31ebcd473fd94c20945392aba267d89578ab39720d6bc167eab6b1842","schema_version":"1.0","event_id":"sha256:fafdcef31ebcd473fd94c20945392aba267d89578ab39720d6bc167eab6b1842"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WMOSC22K2O5XTHSCWTFWRU22G2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Text Categorization Can Enhance Domain-Agnostic Stopword Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdul-Hakeem Omotayo, Ayodele Awokoya, Chris Chinenye Emezue, Doreen Nixdorf, Falalu Ibrahim Lawan, Houcemeddine Turki, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha, Naome A. Etori","submitted_at":"2024-01-24T11:52:05Z","abstract_excerpt":"This paper investigates the role of text categorization in streamlining stopword extraction in natural language processing (NLP), specifically focusing on nine African languages alongside French. By leveraging the MasakhaNEWS, African Stopwords Project, and MasakhaPOS datasets, our findings emphasize that text categorization effectively identifies domain-agnostic stopwords with over 80% detection success rate for most examined languages. Nevertheless, linguistic variances result in lower detection rates for certain languages. Interestingly, we find that while over 40% of stopwords are common a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13398","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/2401.13398/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":"2026-07-05T07:37:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVMHKjsDfpjOHjkFd5v3gT4OsAzXYenRx45ReKeFXu/c5QROrHBhZUFGrKU75n3e0jTFRM05q2NcIcLonP+DBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T08:58:24.960440Z"},"content_sha256":"c631df4e80aa0e42406aadad687d089d957d78ca51b41a2e133dc0b9194f7880","schema_version":"1.0","event_id":"sha256:c631df4e80aa0e42406aadad687d089d957d78ca51b41a2e133dc0b9194f7880"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMOSC22K2O5XTHSCWTFWRU22G2/bundle.json","state_url":"https://pith.science/pith/WMOSC22K2O5XTHSCWTFWRU22G2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMOSC22K2O5XTHSCWTFWRU22G2/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":"2026-07-10T08:58:24Z","links":{"resolver":"https://pith.science/pith/WMOSC22K2O5XTHSCWTFWRU22G2","bundle":"https://pith.science/pith/WMOSC22K2O5XTHSCWTFWRU22G2/bundle.json","state":"https://pith.science/pith/WMOSC22K2O5XTHSCWTFWRU22G2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMOSC22K2O5XTHSCWTFWRU22G2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WMOSC22K2O5XTHSCWTFWRU22G2","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":"f428dbea0309a9b0a1044864722157c495e228568a30378e68a7077769f397fb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T11:52:05Z","title_canon_sha256":"04cd3529b1ec9bee7af14e0e6349e39837089264aadabc92bf7e2d614bad1071"},"schema_version":"1.0","source":{"id":"2401.13398","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.13398","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"arxiv_version","alias_value":"2401.13398v1","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13398","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_12","alias_value":"WMOSC22K2O5X","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_16","alias_value":"WMOSC22K2O5XTHSC","created_at":"2026-07-05T07:37:04Z"},{"alias_kind":"pith_short_8","alias_value":"WMOSC22K","created_at":"2026-07-05T07:37:04Z"}],"graph_snapshots":[{"event_id":"sha256:c631df4e80aa0e42406aadad687d089d957d78ca51b41a2e133dc0b9194f7880","target":"graph","created_at":"2026-07-05T07:37:04Z","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/2401.13398/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates the role of text categorization in streamlining stopword extraction in natural language processing (NLP), specifically focusing on nine African languages alongside French. By leveraging the MasakhaNEWS, African Stopwords Project, and MasakhaPOS datasets, our findings emphasize that text categorization effectively identifies domain-agnostic stopwords with over 80% detection success rate for most examined languages. Nevertheless, linguistic variances result in lower detection rates for certain languages. Interestingly, we find that while over 40% of stopwords are common a","authors_text":"Abdul-Hakeem Omotayo, Ayodele Awokoya, Chris Chinenye Emezue, Doreen Nixdorf, Falalu Ibrahim Lawan, Houcemeddine Turki, Mohamed Ali Hadj Taieb, Mohamed Ben Aouicha, Naome A. Etori","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T11:52:05Z","title":"Text Categorization Can Enhance Domain-Agnostic Stopword Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13398","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:fafdcef31ebcd473fd94c20945392aba267d89578ab39720d6bc167eab6b1842","target":"record","created_at":"2026-07-05T07:37:04Z","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":"f428dbea0309a9b0a1044864722157c495e228568a30378e68a7077769f397fb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T11:52:05Z","title_canon_sha256":"04cd3529b1ec9bee7af14e0e6349e39837089264aadabc92bf7e2d614bad1071"},"schema_version":"1.0","source":{"id":"2401.13398","kind":"arxiv","version":1}},"canonical_sha256":"b31d216b4ad3bb799e42b4cb68d35a36b729b89205779d7f2a90684c8560091b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b31d216b4ad3bb799e42b4cb68d35a36b729b89205779d7f2a90684c8560091b","first_computed_at":"2026-07-05T07:37:04.988942Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:04.988942Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h90n6zj9cQl4UrdTcq06SVNiS10/ONy9GTycDY0oYWcN5n+9aLAgZ6uIHTW36B04Es1wl4af75fCXIA5QLf+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:04.989361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.13398","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fafdcef31ebcd473fd94c20945392aba267d89578ab39720d6bc167eab6b1842","sha256:c631df4e80aa0e42406aadad687d089d957d78ca51b41a2e133dc0b9194f7880"],"state_sha256":"615523547054b3504b7e1302a0475b868514c741d5f08109fb232572b5148861"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qwu3LcdR0ADerAqoZbPXMyPJ9Po9wzdi5ETMrybKAIY4tdGzp3nZ2lBDmnF/LEJu+0H/YltIzvDTMD5aNXllAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T08:58:24.962655Z","bundle_sha256":"e56c7d5230b6d4c38ecb74c241cf2edd083c12b823a5cf12dbf215d7bcdb9cd9"}}