{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DFCVVV2PAZ3MNH6S6NKEHFYDMW","short_pith_number":"pith:DFCVVV2P","canonical_record":{"source":{"id":"2607.21540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","cross_cats_sorted":[],"title_canon_sha256":"fb326466f3ce1f1103397c1b2a9781382fb81a8c5166e592cc1994c59377e62d","abstract_canon_sha256":"7a8509a30bd3d5a8dadb881b3bdbcb1e0d4047925839720570707fbb2cdcf44c"},"schema_version":"1.0"},"canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","source":{"kind":"arxiv","id":"2607.21540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21540","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21540v1","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21540","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"DFCVVV2PAZ3M","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"DFCVVV2PAZ3MNH6S","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"DFCVVV2P","created_at":"2026-07-24T01:24:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DFCVVV2PAZ3MNH6S6NKEHFYDMW","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21540","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","cross_cats_sorted":[],"title_canon_sha256":"fb326466f3ce1f1103397c1b2a9781382fb81a8c5166e592cc1994c59377e62d","abstract_canon_sha256":"7a8509a30bd3d5a8dadb881b3bdbcb1e0d4047925839720570707fbb2cdcf44c"},"schema_version":"1.0"},"canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:24:38.466111Z","signature_b64":"uLVY8accPMpARFt5p5V3z4XaKiPTdqus4J5Mrv/+W4TMc0DKuLXJtC5nSa+GsFFQgU8JCt1mIr0nvyXSHnQeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","last_reissued_at":"2026-07-24T01:24:38.465253Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:24:38.465253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21540","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":"2026-07-24T01:24:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jRIuoDzONq0XH89pMh+Awq81lqfRwzPxPSh2knzKJa74jMZoZ8bnQbRBC2hXIEH7f7I0lmekUMLrSc5nGoVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:19:57.416367Z"},"content_sha256":"64d7dd6d72bd98f2d0bb5fbe719cce5fc9c41291465444642f7344bdd76c4c5b","schema_version":"1.0","event_id":"sha256:64d7dd6d72bd98f2d0bb5fbe719cce5fc9c41291465444642f7344bdd76c4c5b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DFCVVV2PAZ3MNH6S6NKEHFYDMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Paul Azunre","submitted_at":"2026-07-23T17:25:08Z","abstract_excerpt":"We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21540","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/2607.21540/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":"2026-07-24T01:24:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k99B8zr6ejgkzjxLjB4OdkhSjVPjTZPTg/TW1M9h+PKGf/Hst1WFIei5uvwn+Srxr6SfCPoGykyvqKypeM07DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:19:57.419209Z"},"content_sha256":"561597a6fe5fc4e74cd35e5bdd434df6f57c64f093eb02af2624bbb918ed5795","schema_version":"1.0","event_id":"sha256:561597a6fe5fc4e74cd35e5bdd434df6f57c64f093eb02af2624bbb918ed5795"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/bundle.json","state_url":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/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":"2026-08-05T15:19:57Z","links":{"resolver":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW","bundle":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/bundle.json","state":"https://pith.science/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DFCVVV2PAZ3MNH6S6NKEHFYDMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DFCVVV2PAZ3MNH6S6NKEHFYDMW","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":"7a8509a30bd3d5a8dadb881b3bdbcb1e0d4047925839720570707fbb2cdcf44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","title_canon_sha256":"fb326466f3ce1f1103397c1b2a9781382fb81a8c5166e592cc1994c59377e62d"},"schema_version":"1.0","source":{"id":"2607.21540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21540","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21540v1","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21540","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_12","alias_value":"DFCVVV2PAZ3M","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_16","alias_value":"DFCVVV2PAZ3MNH6S","created_at":"2026-07-24T01:24:38Z"},{"alias_kind":"pith_short_8","alias_value":"DFCVVV2P","created_at":"2026-07-24T01:24:38Z"}],"graph_snapshots":[{"event_id":"sha256:561597a6fe5fc4e74cd35e5bdd434df6f57c64f093eb02af2624bbb918ed5795","target":"graph","created_at":"2026-07-24T01:24:38Z","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/2607.21540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DONDO, a family of open, permissively licensed automatic speech recognition (ASR) base models for African languages, built on the w2v-BERT 2.0 self-supervised speech encoder. DONDO comprises twenty-one monolingual models and five multilingual models spanning twenty-seven language varieties across Ghana, Sierra Leone, Nigeria, Senegal, Kenya and Zimbabwe. Models are fine-tuned primarily on read speech drawn from religious texts, which offer broad, license-clear and orthographically consistent coverage for languages that otherwise lack transcribed audio. We describe a two-step (and, f","authors_text":"Paul Azunre","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","title":"DONDO: Open w2v-BERT Speech-Recognition Base Models for African Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21540","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":"sha256:64d7dd6d72bd98f2d0bb5fbe719cce5fc9c41291465444642f7344bdd76c4c5b","target":"record","created_at":"2026-07-24T01:24:38Z","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":"7a8509a30bd3d5a8dadb881b3bdbcb1e0d4047925839720570707fbb2cdcf44c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-23T17:25:08Z","title_canon_sha256":"fb326466f3ce1f1103397c1b2a9781382fb81a8c5166e592cc1994c59377e62d"},"schema_version":"1.0","source":{"id":"2607.21540","kind":"arxiv","version":1}},"canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19455ad74f0676c69fd2f35443970365b380f7588495020dd7606bb82f39df9c","first_computed_at":"2026-07-24T01:24:38.465253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:24:38.465253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uLVY8accPMpARFt5p5V3z4XaKiPTdqus4J5Mrv/+W4TMc0DKuLXJtC5nSa+GsFFQgU8JCt1mIr0nvyXSHnQeBw==","signature_status":"signed_v1","signed_at":"2026-07-24T01:24:38.466111Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64d7dd6d72bd98f2d0bb5fbe719cce5fc9c41291465444642f7344bdd76c4c5b","sha256:561597a6fe5fc4e74cd35e5bdd434df6f57c64f093eb02af2624bbb918ed5795"],"state_sha256":"63cb234f99082b1bc435b7338646eca18a7e9e50dfee101a60318c52fc093f16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FARSODWpkkrx/5q9l1+dytfIq6w38yCfMHpLKyLLwIuMfdWLZFaHTJ34vmk1z3TTDM0hoLcgnjlfwopYuuqHBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:19:57.436789Z","bundle_sha256":"e2360fa186884225c5ff6c154cc6bedb42fcda974f4dafc69c954d492461f97f"}}