{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Y3YPCS6WNDDF5JMBXWUH73ZX2K","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":"4bf46bd4dc2bb3bee1956afb2168e22af1bfb9c20f68ad5104ba2e5ea753c49c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T12:47:36Z","title_canon_sha256":"e21a99a85821a6eeedfe5787d9c230b1b74a35fcaa77b1dbe6e08c708025fda5"},"schema_version":"1.0","source":{"id":"2502.00421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00421","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00421v1","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00421","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_12","alias_value":"Y3YPCS6WNDDF","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_16","alias_value":"Y3YPCS6WNDDF5JMB","created_at":"2026-07-05T10:08:33Z"},{"alias_kind":"pith_short_8","alias_value":"Y3YPCS6W","created_at":"2026-07-05T10:08:33Z"}],"graph_snapshots":[{"event_id":"sha256:1f32c82793913d69c41399c934f99701b8608a91992a6e74101b8c1f825975e2","target":"graph","created_at":"2026-07-05T10:08:33Z","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/2502.00421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a novel Automatic Speech Recognition (ASR) dataset for the Oromo language, a widely spoken language in Ethiopia and neighboring regions. The dataset was collected through a crowd-sourcing initiative, encompassing a diverse range of speakers and phonetic variations. It consists of 100 hours of real-world audio recordings paired with transcriptions, covering read speech in both clean and noisy environments. This dataset addresses the critical need for ASR resources for the Oromo language which is underrepresented. To show its applicability for the ASR task, we conducted experiments us","authors_text":"Dong Wang, Thomas Fang Zheng, Turi Abu, Ying Shi","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T12:47:36Z","title":"Sagalee: an Open Source Automatic Speech Recognition Dataset for Oromo Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00421","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":"sha256:35693812f7d2e1b0f930df04ce8fd6b7eb1e165a9ea7298e41e0ef446769d0e6","target":"record","created_at":"2026-07-05T10:08:33Z","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":"4bf46bd4dc2bb3bee1956afb2168e22af1bfb9c20f68ad5104ba2e5ea753c49c","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T12:47:36Z","title_canon_sha256":"e21a99a85821a6eeedfe5787d9c230b1b74a35fcaa77b1dbe6e08c708025fda5"},"schema_version":"1.0","source":{"id":"2502.00421","kind":"arxiv","version":1}},"canonical_sha256":"c6f0f14bd668c65ea581bda87fef37d291ef7e771177d2a38bc8458124e02e65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6f0f14bd668c65ea581bda87fef37d291ef7e771177d2a38bc8458124e02e65","first_computed_at":"2026-07-05T10:08:33.470784Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:33.470784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yawDGPzwrZmaWotei11wIKZBlobab+X4cd8HgAyC4Lox5Km53LvF+oMyj/pcZLXmTamlPJ+YutCyBBIRFehmBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:33.471211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:35693812f7d2e1b0f930df04ce8fd6b7eb1e165a9ea7298e41e0ef446769d0e6","sha256:1f32c82793913d69c41399c934f99701b8608a91992a6e74101b8c1f825975e2"],"state_sha256":"ef2514134cf7ca19a85bf5f3805b129e1db3bf63a9141fb29352d250bc3725a6"}