{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:65CXRKWSZYGGB2PS2NCJVJC4YQ","short_pith_number":"pith:65CXRKWS","canonical_record":{"source":{"id":"2607.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:08:28Z","cross_cats_sorted":[],"title_canon_sha256":"368020a695c8cdd970b86000b792ac8acf1ff326532e371235bbd3d38648c7fe","abstract_canon_sha256":"d915330e358c63945846fa57d840fcd116fd8eeaae29c1fed57156660c51a8e4"},"schema_version":"1.0"},"canonical_sha256":"f74578aad2ce0c60e9f2d3449aa45cc42f7fe214946596ea10716ab40db03976","source":{"kind":"arxiv","id":"2607.15209","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:65CXRKWSZYGGB2PS2NCJVJC4YQ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15209","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T17:08:28Z","cross_cats_sorted":[],"title_canon_sha256":"368020a695c8cdd970b86000b792ac8acf1ff326532e371235bbd3d38648c7fe","abstract_canon_sha256":"d915330e358c63945846fa57d840fcd116fd8eeaae29c1fed57156660c51a8e4"},"schema_version":"1.0"},"canonical_sha256":"f74578aad2ce0c60e9f2d3449aa45cc42f7fe214946596ea10716ab40db03976","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:22:14.669698Z","signature_b64":"FqQL04JWN9iTVcPtDE7xz0y+XYZlXnEgTyzx/ae6Na+C9KEj0MEC+2s36XDnD9i7G32x/L6fzme7zVr0twgeCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f74578aad2ce0c60e9f2d3449aa45cc42f7fe214946596ea10716ab40db03976","last_reissued_at":"2026-07-17T01:22:14.668903Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:22:14.668903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15209","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":"2026-07-17T01:22:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pvP5TQPQY/w6O8atX17kF2Z8Om9yeAGmUqVAjzM4v2gNP9Ig+YhCfWwZhfwTGifIgoHtcFDiamGPupYM0vaDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:35:09.351132Z"},"content_sha256":"1f81674de6ec3bc0ce5cd1b662565306633ef942fef28928fdc35c8fb2c67ebe","schema_version":"1.0","event_id":"sha256:1f81674de6ec3bc0ce5cd1b662565306633ef942fef28928fdc35c8fb2c67ebe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:65CXRKWSZYGGB2PS2NCJVJC4YQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Debela Desalegn Yadeta, Hailay Kidu Teklehaymanot, Wolfgang Nejdl","submitted_at":"2026-07-16T17:08:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15209","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/2607.15209/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":"2026-07-17T01:22:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bDzlXRcP6i08XaFyEerpEZPskQoMBcarFT6NXyyHDCCt9r6eEQ0qlE0jpFn/5NSGErcyQF6qlSczXUf28GLeBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:35:09.351888Z"},"content_sha256":"b8a5b43263fcc52518182f3a72b61676587671aed6a079582437ada1702cc848","schema_version":"1.0","event_id":"sha256:b8a5b43263fcc52518182f3a72b61676587671aed6a079582437ada1702cc848"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/bundle.json","state_url":"https://pith.science/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/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":"2026-08-10T08:35:09Z","links":{"resolver":"https://pith.science/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ","bundle":"https://pith.science/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/bundle.json","state":"https://pith.science/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/65CXRKWSZYGGB2PS2NCJVJC4YQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fdg3FErpROnowFznPy28shMcO9o5QTd01e4qxTKfWnyBCSj3SC2kgBQgI2O6EI4bQZ1Ykrc+xU3bgQZvmVtqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:35:09.357007Z","bundle_sha256":"a0170f8e2d9453dbda2698814b13d074decb0a16fc64cb2343c80ed7ef3c0fcc"}}