{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I77BEQYTMFGGLZLEHPFKP5Y5U7","short_pith_number":"pith:I77BEQYT","canonical_record":{"source":{"id":"2512.02201","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T20:49:10Z","cross_cats_sorted":[],"title_canon_sha256":"509d7741e3d439d1af88683307faa572e164a74842e0906a5692cf9ce19abfaf","abstract_canon_sha256":"7ead61e9c8622ffa610851b32b4661c5a1d03bf8f087af46525fb65cb994ddcf"},"schema_version":"1.0"},"canonical_sha256":"47fe124313614c65e5643bcaa7f71da7f208f190c3c5448f332a7c680d36e53c","source":{"kind":"arxiv","id":"2512.02201","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02201","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02201v3","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02201","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"I77BEQYTMFGG","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"I77BEQYTMFGGLZLE","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"I77BEQYT","created_at":"2026-06-10T01:09:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I77BEQYTMFGGLZLEHPFKP5Y5U7","target":"record","payload":{"canonical_record":{"source":{"id":"2512.02201","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T20:49:10Z","cross_cats_sorted":[],"title_canon_sha256":"509d7741e3d439d1af88683307faa572e164a74842e0906a5692cf9ce19abfaf","abstract_canon_sha256":"7ead61e9c8622ffa610851b32b4661c5a1d03bf8f087af46525fb65cb994ddcf"},"schema_version":"1.0"},"canonical_sha256":"47fe124313614c65e5643bcaa7f71da7f208f190c3c5448f332a7c680d36e53c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:48.213771Z","signature_b64":"JOJF2d98uMGHZV20H5T1ts6zpB6DFC1qpQoT5He9xV9K8ZpBNgFEiyxpjECTm3TV0FWQdU5S0pk1EPRtrfk1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47fe124313614c65e5643bcaa7f71da7f208f190c3c5448f332a7c680d36e53c","last_reissued_at":"2026-06-10T01:09:48.212676Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:48.212676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2512.02201","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-10T01:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"74mw1XVxk9IRa1wJoepinEBiuwqJcOl719rRwzCcgO0RsEbmXTbfSQpGoJb8+ybwQ3iP7q5RZohFCgVjr+/8BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:26:41.540568Z"},"content_sha256":"44c8bac0be73f2403b5ce34cf711671777a4b5f0e82d4a1729aed54c670f8288","schema_version":"1.0","event_id":"sha256:44c8bac0be73f2403b5ce34cf711671777a4b5f0e82d4a1729aed54c670f8288"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I77BEQYTMFGGLZLEHPFKP5Y5U7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andinda Bakainga, Andiswa Bukula, and Seani Rananga, Chijioke Okorie, Dale Dunbar, Francois Smit, Graham Morrissey, Idris Abdulmumin, Kayode Olaleye, Kesego Mokgosi, Mahmooda Milanzie, Nia Zion Van Wyk, Respect Mlambo, Rooweither Mabuya, Sitwala Mundia, Tebogo Macucwa, Thapelo Sindane, Tsholofelo Hope Mogale, Tsosheletso Chidi, Unarine Netshifhefhe, Vukosi Marivate, Zainab Abdulrasaq","submitted_at":"2025-12-01T20:49:10Z","abstract_excerpt":"This paper introduces Swivuriso, a 3000-hour multilingual speech dataset developed as part of the African Next Voices project, to support the development and benchmarking of automatic speech recognition (ASR) technologies in seven South African languages. Covering agriculture, healthcare, and general domain topics, Swivuriso addresses significant gaps in existing ASR datasets. We describe the design principles, ethical considerations, and data collection procedures that guided the dataset creation. We present baseline results of training/finetuning ASR models with this data and compare to othe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02201","kind":"arxiv","version":3},"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/2512.02201/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":"2026-06-10T01:09:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bWGTMhsMidofTjrbknm2K0Du5Jii8ucLIUMsi997XUHIA9fnwVDeeqfCaR4PnPRyduJHR0RFIKMcgGVs4+04CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:26:41.540963Z"},"content_sha256":"4dbb9487cc5b788df1c4c1b39b8611bd6d3f19f6289ecaa71b381f348fdcbe83","schema_version":"1.0","event_id":"sha256:4dbb9487cc5b788df1c4c1b39b8611bd6d3f19f6289ecaa71b381f348fdcbe83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/bundle.json","state_url":"https://pith.science/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/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":"2026-06-29T19:26:41Z","links":{"resolver":"https://pith.science/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7","bundle":"https://pith.science/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/bundle.json","state":"https://pith.science/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I77BEQYTMFGGLZLEHPFKP5Y5U7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I77BEQYTMFGGLZLEHPFKP5Y5U7","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":"7ead61e9c8622ffa610851b32b4661c5a1d03bf8f087af46525fb65cb994ddcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T20:49:10Z","title_canon_sha256":"509d7741e3d439d1af88683307faa572e164a74842e0906a5692cf9ce19abfaf"},"schema_version":"1.0","source":{"id":"2512.02201","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.02201","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"arxiv_version","alias_value":"2512.02201v3","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.02201","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_12","alias_value":"I77BEQYTMFGG","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_16","alias_value":"I77BEQYTMFGGLZLE","created_at":"2026-06-10T01:09:48Z"},{"alias_kind":"pith_short_8","alias_value":"I77BEQYT","created_at":"2026-06-10T01:09:48Z"}],"graph_snapshots":[{"event_id":"sha256:4dbb9487cc5b788df1c4c1b39b8611bd6d3f19f6289ecaa71b381f348fdcbe83","target":"graph","created_at":"2026-06-10T01:09:48Z","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/2512.02201/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces Swivuriso, a 3000-hour multilingual speech dataset developed as part of the African Next Voices project, to support the development and benchmarking of automatic speech recognition (ASR) technologies in seven South African languages. Covering agriculture, healthcare, and general domain topics, Swivuriso addresses significant gaps in existing ASR datasets. We describe the design principles, ethical considerations, and data collection procedures that guided the dataset creation. We present baseline results of training/finetuning ASR models with this data and compare to othe","authors_text":"Andinda Bakainga, Andiswa Bukula, and Seani Rananga, Chijioke Okorie, Dale Dunbar, Francois Smit, Graham Morrissey, Idris Abdulmumin, Kayode Olaleye, Kesego Mokgosi, Mahmooda Milanzie, Nia Zion Van Wyk, Respect Mlambo, Rooweither Mabuya, Sitwala Mundia, Tebogo Macucwa, Thapelo Sindane, Tsholofelo Hope Mogale, Tsosheletso Chidi, Unarine Netshifhefhe, Vukosi Marivate, Zainab Abdulrasaq","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T20:49:10Z","title":"Swivuriso: The South African Next Voices Multilingual Speech Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.02201","kind":"arxiv","version":3},"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":"sha256:44c8bac0be73f2403b5ce34cf711671777a4b5f0e82d4a1729aed54c670f8288","target":"record","created_at":"2026-06-10T01:09:48Z","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":"7ead61e9c8622ffa610851b32b4661c5a1d03bf8f087af46525fb65cb994ddcf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-01T20:49:10Z","title_canon_sha256":"509d7741e3d439d1af88683307faa572e164a74842e0906a5692cf9ce19abfaf"},"schema_version":"1.0","source":{"id":"2512.02201","kind":"arxiv","version":3}},"canonical_sha256":"47fe124313614c65e5643bcaa7f71da7f208f190c3c5448f332a7c680d36e53c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47fe124313614c65e5643bcaa7f71da7f208f190c3c5448f332a7c680d36e53c","first_computed_at":"2026-06-10T01:09:48.212676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:48.212676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JOJF2d98uMGHZV20H5T1ts6zpB6DFC1qpQoT5He9xV9K8ZpBNgFEiyxpjECTm3TV0FWQdU5S0pk1EPRtrfk1Dg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:48.213771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.02201","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44c8bac0be73f2403b5ce34cf711671777a4b5f0e82d4a1729aed54c670f8288","sha256:4dbb9487cc5b788df1c4c1b39b8611bd6d3f19f6289ecaa71b381f348fdcbe83"],"state_sha256":"afea9158f13e945e27115edf7ef941ff53e41f3e532363d366441a4fe7c9c41e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y4ZPXIHvbpCijLzJCxsk/BSsbxu93NBHpM6qLQab8eOGnU87Dr5jr4/jv25XP1H97iXl2TLD227nXi93X0q9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:26:41.542942Z","bundle_sha256":"9545f280d48939c1d11827ef7f5771d7ba538669afdf736c9eb58ebb351c4ccf"}}