{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","short_pith_number":"pith:ZJUTJGQT","canonical_record":{"source":{"id":"2102.04889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","cross_cats_sorted":[],"title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8","abstract_canon_sha256":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959"},"schema_version":"1.0"},"canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","source":{"kind":"arxiv","id":"2102.04889","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04889v1","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZJUTJGQTYYFZ","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZJUTJGQTYYFZNNR3","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZJUTJGQT","created_at":"2026-07-05T02:14:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","target":"record","payload":{"canonical_record":{"source":{"id":"2102.04889","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","cross_cats_sorted":[],"title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8","abstract_canon_sha256":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959"},"schema_version":"1.0"},"canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:05.936001Z","signature_b64":"L2frtNH54z2vGJAT1fgIfP8QC1VJfrdh9ezkAEyzOXh9EIfC4qr7t94NUcb9xr2EkjHEJEEVxzuIg+lL1aYvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","last_reissued_at":"2026-07-05T02:14:05.935576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:05.935576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.04889","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":"2026-07-05T02:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NnzFmT0a7Umm3QgWKe6DuCRQtae9Ttm0pzEbHijmQChiTCifh3GBg/ecXBXCRebjJXlkFUfXEMsyX/MRp6RRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T12:16:41.815542Z"},"content_sha256":"502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3","schema_version":"1.0","event_id":"sha256:502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, Claytone Sikasote","submitted_at":"2021-02-09T15:42:00Z","abstract_excerpt":"We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04889","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/2102.04889/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":"2026-07-05T02:14:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBN2EpF0UTNCxeekR4SjEo4Q2iAZPu7XJMKofV8pbnP1+Ps0r/f/N7Sju4fa8Z+iDIMptQwNYkTq8+CncmQZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T12:16:41.815938Z"},"content_sha256":"afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9","schema_version":"1.0","event_id":"sha256:afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/bundle.json","state_url":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/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":"2026-07-17T12:16:41Z","links":{"resolver":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE","bundle":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/bundle.json","state":"https://pith.science/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZJUTJGQTYYFZNNR3BLOOKL74ZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZJUTJGQTYYFZNNR3BLOOKL74ZE","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":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8"},"schema_version":"1.0","source":{"id":"2102.04889","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"arxiv_version","alias_value":"2102.04889v1","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.04889","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_12","alias_value":"ZJUTJGQTYYFZ","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_16","alias_value":"ZJUTJGQTYYFZNNR3","created_at":"2026-07-05T02:14:05Z"},{"alias_kind":"pith_short_8","alias_value":"ZJUTJGQT","created_at":"2026-07-05T02:14:05Z"}],"graph_snapshots":[{"event_id":"sha256:afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9","target":"graph","created_at":"2026-07-05T02:14:05Z","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/2102.04889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a preprocessed, ready-to-use automatic speech recognition corpus, BembaSpeech, consisting over 24 hours of read speech in the Bemba language, a written but low-resourced language spoken by over 30% of the population in Zambia. To assess its usefulness for training and testing ASR systems for Bemba, we train an end-to-end Bemba ASR system by fine-tuning a pre-trained DeepSpeech English model on the training portion of the BembaSpeech corpus. Our best model achieves a word error rate (WER) of 54.78%. The results show that the corpus can be used for building ASR systems for Bemba. The ","authors_text":"Antonios Anastasopoulos, Claytone Sikasote","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title":"BembaSpeech: A Speech Recognition Corpus for the Bemba Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.04889","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":"sha256:502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3","target":"record","created_at":"2026-07-05T02:14:05Z","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":"2d57d5c36f30e61444875158a8b7a041525d77edd44e00d4d8938cac80311959","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-09T15:42:00Z","title_canon_sha256":"4419b455f234e4778004d149ae7b69115a9ecf96b27a6d5e003e45ad024999a8"},"schema_version":"1.0","source":{"id":"2102.04889","kind":"arxiv","version":1}},"canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca69349a13c60b96b63b0adce52ffcc92b2dd71e0fdcf497138c64ae1175eacd","first_computed_at":"2026-07-05T02:14:05.935576Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:05.935576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L2frtNH54z2vGJAT1fgIfP8QC1VJfrdh9ezkAEyzOXh9EIfC4qr7t94NUcb9xr2EkjHEJEEVxzuIg+lL1aYvDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:05.936001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.04889","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:502be78b7b08eb5755366dcd5024a1dad5a26a736fdb6ecfc807df22d12bafc3","sha256:afc412356bbd4f650cebdb2ec6e71fcf6ef558d7043222248459bbdac043c5a9"],"state_sha256":"f238015d44504ed953a659c1aa011e038a2bc906254fb13fd6caad75506b352c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9qr+5nVYVfcj+BoU4gzStSsvahpSAiTbADCaGnmSWEpCZqXBDfH8j3TAsbY+RporkvrEiFWAXInOgTAf9kFADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T12:16:41.818218Z","bundle_sha256":"768f57606a07618103e7a132c0b1e2ec9a32e2a70de99d28ce3a79ebaef40593"}}