{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GUVSMPMUAXN4YZYQJQLPUMY66Q","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":"0304df33df02bf9afb4fba246faa89e79b79af2efc0a37fe0b30d66f58f6871c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T11:28:03Z","title_canon_sha256":"8b2dee07f87c5c8173ab53669e2d4e44749877d8a3a251332101ad7af65cebaa"},"schema_version":"1.0","source":{"id":"2605.18232","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18232","created_at":"2026-05-20T00:05:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18232v1","created_at":"2026-05-20T00:05:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18232","created_at":"2026-05-20T00:05:51Z"},{"alias_kind":"pith_short_12","alias_value":"GUVSMPMUAXN4","created_at":"2026-05-20T00:05:51Z"},{"alias_kind":"pith_short_16","alias_value":"GUVSMPMUAXN4YZYQ","created_at":"2026-05-20T00:05:51Z"},{"alias_kind":"pith_short_8","alias_value":"GUVSMPMU","created_at":"2026-05-20T00:05:51Z"}],"graph_snapshots":[{"event_id":"sha256:84cf0e51e9c5339174cb1e1cf6ebbea7a3b565f6714acaca2f5c1864da7bbfe1","target":"graph","created_at":"2026-05-20T00:05:51Z","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":[{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:41:58.930162Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.290686Z","status":"skipped","version":"1.0.0"}],"endpoint":"/pith/2605.18232/integrity.json","findings":[],"snapshot_sha256":"484438621b66639615ded5226ca02e7a3120172ce31ad756c3af87c3086619d2","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Somali is a Cushitic language of the Horn of Africa with ~25 million speakers, yet no documented dedicated Somali pretraining corpus with a companion tokenizer and language-identification benchmark has been publicly released. Existing Somali text appears either inside multilingual distributions (HPLT v2, CC100, MADLAD-400, OSCAR, mC4) or in small, undocumented Somali-only uploads on Hugging Face. We introduce SomaliWeb v1, a quality-filtered Somali corpus of 819,322 documents (~303M tokens) built from three upstream sources (HPLT v2, CC100, Somali Wikipedia) through a six-stage reproducible pi","authors_text":"Khalid Yusuf Dahir","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T11:28:03Z","title":"SomaliWeb v1: A Quality-Filtered Somali Web Corpus with a Matched Tokenizer and a Public Language-Identification Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18232","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:e661ad11d32e91b5e0aa902325b06a7d054d8cea08ccf8cd76e7169535e9ab07","target":"record","created_at":"2026-05-20T00:05:51Z","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":"0304df33df02bf9afb4fba246faa89e79b79af2efc0a37fe0b30d66f58f6871c","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T11:28:03Z","title_canon_sha256":"8b2dee07f87c5c8173ab53669e2d4e44749877d8a3a251332101ad7af65cebaa"},"schema_version":"1.0","source":{"id":"2605.18232","kind":"arxiv","version":1}},"canonical_sha256":"352b263d9405dbcc67104c16fa331ef411468f8709f9ff5d5cdaab5dc3984132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"352b263d9405dbcc67104c16fa331ef411468f8709f9ff5d5cdaab5dc3984132","first_computed_at":"2026-05-20T00:05:51.538529Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:51.538529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"odYbX2UObQNgyG26VhALvbE8BFiIwN5wkAHHymAPQfwGuxFnwrF1900nMP1zv1zdWHwIzIG7AvFnCqnD+MkqDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:51.539124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18232","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e661ad11d32e91b5e0aa902325b06a7d054d8cea08ccf8cd76e7169535e9ab07","sha256:84cf0e51e9c5339174cb1e1cf6ebbea7a3b565f6714acaca2f5c1864da7bbfe1"],"state_sha256":"c8e5269f279cc8890c634d11c57c38b044b6a7bef14691b15bff27789b0734c3"}