{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:65CXRKWSZYGGB2PS2NCJVJC4YQ","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":"d915330e358c63945846fa57d840fcd116fd8eeaae29c1fed57156660c51a8e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:08:28Z","title_canon_sha256":"368020a695c8cdd970b86000b792ac8acf1ff326532e371235bbd3d38648c7fe"},"schema_version":"1.0","source":{"id":"2607.15209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15209","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15209v1","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15209","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_12","alias_value":"65CXRKWSZYGG","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_16","alias_value":"65CXRKWSZYGGB2PS","created_at":"2026-07-17T01:22:14Z"},{"alias_kind":"pith_short_8","alias_value":"65CXRKWS","created_at":"2026-07-17T01:22:14Z"}],"graph_snapshots":[{"event_id":"sha256:b8a5b43263fcc52518182f3a72b61676587671aed6a079582437ada1702cc848","target":"graph","created_at":"2026-07-17T01:22:14Z","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/2607.15209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual pre-trained language models (PLMs) exhibit degraded performance on low-resource, non-Latin-script languages, driven by high out-of-vocabulary (OOV) rates and excessive subword fragmentation that result from Latin-script-centric tokenizer training. We introduce VEXMLM, a vocabulary-extended variant of XLM-R targeting the two highest-resource Ge'ez-script languages, Amharic and Tigrinya, and further evaluated on 17 additional low-resource African languages (19 total). We train a language-specific SentencePiece tokenizer on curated Amharic and Tigrinya monolingual corpora, extend XLM","authors_text":"Debela Desalegn Yadeta, Hailay Kidu Teklehaymanot, Wolfgang Nejdl","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:08:28Z","title":"Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15209","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":"sha256:1f81674de6ec3bc0ce5cd1b662565306633ef942fef28928fdc35c8fb2c67ebe","target":"record","created_at":"2026-07-17T01:22:14Z","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":"d915330e358c63945846fa57d840fcd116fd8eeaae29c1fed57156660c51a8e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:08:28Z","title_canon_sha256":"368020a695c8cdd970b86000b792ac8acf1ff326532e371235bbd3d38648c7fe"},"schema_version":"1.0","source":{"id":"2607.15209","kind":"arxiv","version":1}},"canonical_sha256":"f74578aad2ce0c60e9f2d3449aa45cc42f7fe214946596ea10716ab40db03976","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f74578aad2ce0c60e9f2d3449aa45cc42f7fe214946596ea10716ab40db03976","first_computed_at":"2026-07-17T01:22:14.668903Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-17T01:22:14.668903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqQL04JWN9iTVcPtDE7xz0y+XYZlXnEgTyzx/ae6Na+C9KEj0MEC+2s36XDnD9i7G32x/L6fzme7zVr0twgeCQ==","signature_status":"signed_v1","signed_at":"2026-07-17T01:22:14.669698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f81674de6ec3bc0ce5cd1b662565306633ef942fef28928fdc35c8fb2c67ebe","sha256:b8a5b43263fcc52518182f3a72b61676587671aed6a079582437ada1702cc848"],"state_sha256":"5beff463083d75a61a02950b0fe042f66768265060a41eccbcaaaffd77c13260"}