{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GHMNPLYTTSOTJ4I3GKUOB5YCHJ","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":"744d3f89032ca1712553e77f58d6a993b5dbdb663e0b3c1ffadc8662e6fc4889","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:06:51Z","title_canon_sha256":"406719dd507f08357aa5ae6c3a332c77c1a618516f655fb5ba1ea79f98e170a0"},"schema_version":"1.0","source":{"id":"2104.00767","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00767","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00767v1","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00767","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_12","alias_value":"GHMNPLYTTSOT","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_16","alias_value":"GHMNPLYTTSOTJ4I3","created_at":"2026-07-05T02:28:35Z"},{"alias_kind":"pith_short_8","alias_value":"GHMNPLYT","created_at":"2026-07-05T02:28:35Z"}],"graph_snapshots":[{"event_id":"sha256:341c42be5f81309d03e24c8a5875e457b2fd5f7a1831f6fe7935f16900b1303f","target":"graph","created_at":"2026-07-05T02:28:35Z","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/2104.00767/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aaron Daniels, Jan Buys, Sheldon Reay, Tumi Moeng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:06:51Z","title":"Canonical and Surface Morphological Segmentation for Nguni Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00767","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:ffc1e97cb39bcf34d35d46408ee6fd9b7718c8e068a8898ca80a32dc8dfd2167","target":"record","created_at":"2026-07-05T02:28:35Z","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":"744d3f89032ca1712553e77f58d6a993b5dbdb663e0b3c1ffadc8662e6fc4889","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-01T21:06:51Z","title_canon_sha256":"406719dd507f08357aa5ae6c3a332c77c1a618516f655fb5ba1ea79f98e170a0"},"schema_version":"1.0","source":{"id":"2104.00767","kind":"arxiv","version":1}},"canonical_sha256":"31d8d7af139c9d34f11b32a8e0f7023a5c98bc60e09cb2740e7ca86507519843","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31d8d7af139c9d34f11b32a8e0f7023a5c98bc60e09cb2740e7ca86507519843","first_computed_at":"2026-07-05T02:28:35.647831Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:28:35.647831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"318jT0CQNvRPZlD7aNXduX9U6+uSkaE5YWMpJF+Ty0VmafGMkDqLsNILLar9cYO5KHGA/fIPgGUSGHDE0bhRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:28:35.648352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00767","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffc1e97cb39bcf34d35d46408ee6fd9b7718c8e068a8898ca80a32dc8dfd2167","sha256:341c42be5f81309d03e24c8a5875e457b2fd5f7a1831f6fe7935f16900b1303f"],"state_sha256":"656f06f9bebc0f7505fca3c322b940b5c5ee3af278f237b8790edb19f5516b27"}