{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GHMNPLYTTSOTJ4I3GKUOB5YCHJ","short_pith_number":"pith:GHMNPLYT","schema_version":"1.0","canonical_sha256":"31d8d7af139c9d34f11b32a8e0f7023a5c98bc60e09cb2740e7ca86507519843","source":{"kind":"arxiv","id":"2104.00767","version":1},"attestation_state":"computed","paper":{"title":"Canonical and Surface Morphological Segmentation for Nguni Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Daniels, Jan Buys, Sheldon Reay, Tumi Moeng","submitted_at":"2021-04-01T21:06:51Z","abstract_excerpt":"Morphological Segmentation involves decomposing words into morphemes, the smallest meaning-bearing units of language. This is an important NLP task for morphologically-rich agglutinative languages such as the Southern African Nguni language group. In this paper, we investigate supervised and unsupervised models for two variants of morphological segmentation: canonical and surface segmentation. We train sequence-to-sequence models for canonical segmentation, where the underlying morphemes may not be equal to the surface form of the word, and Conditional Random Fields (CRF) for surface segmentat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2104.00767","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:06:51Z","cross_cats_sorted":[],"title_canon_sha256":"406719dd507f08357aa5ae6c3a332c77c1a618516f655fb5ba1ea79f98e170a0","abstract_canon_sha256":"744d3f89032ca1712553e77f58d6a993b5dbdb663e0b3c1ffadc8662e6fc4889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:28:35.648352Z","signature_b64":"318jT0CQNvRPZlD7aNXduX9U6+uSkaE5YWMpJF+Ty0VmafGMkDqLsNILLar9cYO5KHGA/fIPgGUSGHDE0bhRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d8d7af139c9d34f11b32a8e0f7023a5c98bc60e09cb2740e7ca86507519843","last_reissued_at":"2026-07-05T02:28:35.647831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:28:35.647831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Canonical and Surface Morphological Segmentation for Nguni Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aaron Daniels, Jan Buys, Sheldon Reay, Tumi Moeng","submitted_at":"2021-04-01T21:06:51Z","abstract_excerpt":"Morphological Segmentation involves decomposing words into morphemes, the smallest meaning-bearing units of language. This is an important NLP task for morphologically-rich agglutinative languages such as the Southern African Nguni language group. In this paper, we investigate supervised and unsupervised models for two variants of morphological segmentation: canonical and surface segmentation. We train sequence-to-sequence models for canonical segmentation, where the underlying morphemes may not be equal to the surface form of the word, and Conditional Random Fields (CRF) for surface segmentat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00767","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/2104.00767/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2104.00767","created_at":"2026-07-05T02:28:35.647903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.00767v1","created_at":"2026-07-05T02:28:35.647903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00767","created_at":"2026-07-05T02:28:35.647903+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHMNPLYTTSOT","created_at":"2026-07-05T02:28:35.647903+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHMNPLYTTSOTJ4I3","created_at":"2026-07-05T02:28:35.647903+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHMNPLYT","created_at":"2026-07-05T02:28:35.647903+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ","json":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ.json","graph_json":"https://pith.science/api/pith-number/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/graph.json","events_json":"https://pith.science/api/pith-number/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/events.json","paper":"https://pith.science/paper/GHMNPLYT"},"agent_actions":{"view_html":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ","download_json":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ.json","view_paper":"https://pith.science/paper/GHMNPLYT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.00767&json=true","fetch_graph":"https://pith.science/api/pith-number/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/action/storage_attestation","attest_author":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/action/author_attestation","sign_citation":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/action/citation_signature","submit_replication":"https://pith.science/pith/GHMNPLYTTSOTJ4I3GKUOB5YCHJ/action/replication_record"}},"created_at":"2026-07-05T02:28:35.647903+00:00","updated_at":"2026-07-05T02:28:35.647903+00:00"}