{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:7ERFKDCKTZG5DEDPLCK7ODL2JQ","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":"1e0df04866ba4838ef78da2d6908f8b06c190d6766fb080c0ef294f7f430ce49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T08:36:14Z","title_canon_sha256":"92ea51e97ff0cd055ba7fb690957d27a8176290994d5e3eb17ddeb38691c0fec"},"schema_version":"1.0","source":{"id":"2203.08459","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.08459","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"arxiv_version","alias_value":"2203.08459v2","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08459","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_12","alias_value":"7ERFKDCKTZG5","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_16","alias_value":"7ERFKDCKTZG5DEDP","created_at":"2026-07-05T06:03:53Z"},{"alias_kind":"pith_short_8","alias_value":"7ERFKDCK","created_at":"2026-07-05T06:03:53Z"}],"graph_snapshots":[{"event_id":"sha256:895946c88714d93164bbd88f63c3fc31984883d3854c5abbd43b409cacac05e1","target":"graph","created_at":"2026-07-05T06:03:53Z","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/2203.08459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained language models such as BERT have been successful at tackling many natural language processing tasks. However, the unsupervised sub-word tokenization methods commonly used in these models (e.g., byte-pair encoding - BPE) are sub-optimal at handling morphologically rich languages. Even given a morphological analyzer, naive sequencing of morphemes into a standard BERT architecture is inefficient at capturing morphological compositionality and expressing word-relative syntactic regularities. We address these challenges by proposing a simple yet effective two-tier BERT architecture tha","authors_text":"Andre Niyongabo Rubungo, Antoine Nzeyimana","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T08:36:14Z","title":"KinyaBERT: a Morphology-aware Kinyarwanda Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08459","kind":"arxiv","version":2},"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":"sha256:49d56d7f3f71dd6649c1963fe06a40c7cd374bd0cb2545557e1d08a8f6e92dae","target":"record","created_at":"2026-07-05T06:03:53Z","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":"1e0df04866ba4838ef78da2d6908f8b06c190d6766fb080c0ef294f7f430ce49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-16T08:36:14Z","title_canon_sha256":"92ea51e97ff0cd055ba7fb690957d27a8176290994d5e3eb17ddeb38691c0fec"},"schema_version":"1.0","source":{"id":"2203.08459","kind":"arxiv","version":2}},"canonical_sha256":"f922550c4a9e4dd1906f5895f70d7a4c3f81437422c169505f5a26d6a8a41a74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f922550c4a9e4dd1906f5895f70d7a4c3f81437422c169505f5a26d6a8a41a74","first_computed_at":"2026-07-05T06:03:53.397331Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:53.397331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sqVJRTg7JmDTnmn442DIyDwDg+DJ6C2Nh+kpt22DEhIZUAWnjCuV82mGTlN1ZphXpI3ItoMaIgMHc55nCo5kBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:53.397770Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.08459","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49d56d7f3f71dd6649c1963fe06a40c7cd374bd0cb2545557e1d08a8f6e92dae","sha256:895946c88714d93164bbd88f63c3fc31984883d3854c5abbd43b409cacac05e1"],"state_sha256":"866dc68f3bed165c4a037e709a4608cecbcf995e34f0ace7c97bcd2d2a9fb97b"}