{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:DXADP732UEL6Y7WPOYRLLL2XUL","short_pith_number":"pith:DXADP732","canonical_record":{"source":{"id":"2308.11863","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-08-23T01:44:28Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"70c23d1fe5f6d46249851be037e836e1a70b0da4f5f04e085a1bcfd98af00615","abstract_canon_sha256":"5a1fa6efe8dd531eee976d79a7c190c06e970c1728c0dd8eb938e5464839ffec"},"schema_version":"1.0"},"canonical_sha256":"1dc037ff7aa117ec7ecf7622b5af57a2fd6c2177cea62d9df444cd888e99f871","source":{"kind":"arxiv","id":"2308.11863","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11863","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11863v3","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11863","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"DXADP732UEL6","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"DXADP732UEL6Y7WP","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"DXADP732","created_at":"2026-07-05T07:51:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:DXADP732UEL6Y7WPOYRLLL2XUL","target":"record","payload":{"canonical_record":{"source":{"id":"2308.11863","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-08-23T01:44:28Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"70c23d1fe5f6d46249851be037e836e1a70b0da4f5f04e085a1bcfd98af00615","abstract_canon_sha256":"5a1fa6efe8dd531eee976d79a7c190c06e970c1728c0dd8eb938e5464839ffec"},"schema_version":"1.0"},"canonical_sha256":"1dc037ff7aa117ec7ecf7622b5af57a2fd6c2177cea62d9df444cd888e99f871","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:10.031634Z","signature_b64":"OhgQ7kQVdeMnWUZPlRvJ3LJtE0VfwSkIGG7EpRg5W7Vb9edPXyym2lgvFGfixveMNsjihi4ObkW8wPJ+gAjUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1dc037ff7aa117ec7ecf7622b5af57a2fd6c2177cea62d9df444cd888e99f871","last_reissued_at":"2026-07-05T07:51:10.031192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:10.031192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.11863","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":"2026-07-05T07:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qzB4JLgGLWN09y4jzoYeNNztwGFfXV6kbXa/Oez3NM3wQvFHtpIatei7xU0ot767PEM1JNENhQhQozmQ8cRKCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:30:16.342456Z"},"content_sha256":"e2ed973c3f9835fb3f3a8d1b8b6a193c114629c83460a5daec0ccea597ba2b37","schema_version":"1.0","event_id":"sha256:e2ed973c3f9835fb3f3a8d1b8b6a193c114629c83460a5daec0ccea597ba2b37"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:DXADP732UEL6Y7WPOYRLLL2XUL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Antoine Nzeyimana","submitted_at":"2023-08-23T01:44:28Z","abstract_excerpt":"Despite recent availability of large transcribed Kinyarwanda speech data, achieving robust speech recognition for Kinyarwanda is still challenging. In this work, we show that using self-supervised pre-training, following a simple curriculum schedule during fine-tuning and using semi-supervised learning to leverage large unlabelled speech data significantly improve speech recognition performance for Kinyarwanda. Our approach focuses on using public domain data only. A new studio-quality speech dataset is collected from a public website, then used to train a clean baseline model. The clean basel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11863","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/2308.11863/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":"2026-07-05T07:51:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TL0LL9IZJ0H4PbYNoiUr1bCOSevF1sJ2lctOMWeTPEea1qG2GxKlR3eYGUseyo9X/ky8piIB2xi0pDY85922Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:30:16.342840Z"},"content_sha256":"9d8bb1d276266d8912625eb98f73d191f687b0df21832cfd3d0b59c0c8bb4b85","schema_version":"1.0","event_id":"sha256:9d8bb1d276266d8912625eb98f73d191f687b0df21832cfd3d0b59c0c8bb4b85"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DXADP732UEL6Y7WPOYRLLL2XUL/bundle.json","state_url":"https://pith.science/pith/DXADP732UEL6Y7WPOYRLLL2XUL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DXADP732UEL6Y7WPOYRLLL2XUL/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":"2026-07-07T04:30:16Z","links":{"resolver":"https://pith.science/pith/DXADP732UEL6Y7WPOYRLLL2XUL","bundle":"https://pith.science/pith/DXADP732UEL6Y7WPOYRLLL2XUL/bundle.json","state":"https://pith.science/pith/DXADP732UEL6Y7WPOYRLLL2XUL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DXADP732UEL6Y7WPOYRLLL2XUL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:DXADP732UEL6Y7WPOYRLLL2XUL","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":"5a1fa6efe8dd531eee976d79a7c190c06e970c1728c0dd8eb938e5464839ffec","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-08-23T01:44:28Z","title_canon_sha256":"70c23d1fe5f6d46249851be037e836e1a70b0da4f5f04e085a1bcfd98af00615"},"schema_version":"1.0","source":{"id":"2308.11863","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.11863","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"arxiv_version","alias_value":"2308.11863v3","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.11863","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_12","alias_value":"DXADP732UEL6","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_16","alias_value":"DXADP732UEL6Y7WP","created_at":"2026-07-05T07:51:10Z"},{"alias_kind":"pith_short_8","alias_value":"DXADP732","created_at":"2026-07-05T07:51:10Z"}],"graph_snapshots":[{"event_id":"sha256:9d8bb1d276266d8912625eb98f73d191f687b0df21832cfd3d0b59c0c8bb4b85","target":"graph","created_at":"2026-07-05T07:51:10Z","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/2308.11863/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent availability of large transcribed Kinyarwanda speech data, achieving robust speech recognition for Kinyarwanda is still challenging. In this work, we show that using self-supervised pre-training, following a simple curriculum schedule during fine-tuning and using semi-supervised learning to leverage large unlabelled speech data significantly improve speech recognition performance for Kinyarwanda. Our approach focuses on using public domain data only. A new studio-quality speech dataset is collected from a public website, then used to train a clean baseline model. The clean basel","authors_text":"Antoine Nzeyimana","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-08-23T01:44:28Z","title":"KinSPEAK: Improving speech recognition for Kinyarwanda via semi-supervised learning methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.11863","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:e2ed973c3f9835fb3f3a8d1b8b6a193c114629c83460a5daec0ccea597ba2b37","target":"record","created_at":"2026-07-05T07:51:10Z","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":"5a1fa6efe8dd531eee976d79a7c190c06e970c1728c0dd8eb938e5464839ffec","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-08-23T01:44:28Z","title_canon_sha256":"70c23d1fe5f6d46249851be037e836e1a70b0da4f5f04e085a1bcfd98af00615"},"schema_version":"1.0","source":{"id":"2308.11863","kind":"arxiv","version":3}},"canonical_sha256":"1dc037ff7aa117ec7ecf7622b5af57a2fd6c2177cea62d9df444cd888e99f871","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1dc037ff7aa117ec7ecf7622b5af57a2fd6c2177cea62d9df444cd888e99f871","first_computed_at":"2026-07-05T07:51:10.031192Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:51:10.031192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OhgQ7kQVdeMnWUZPlRvJ3LJtE0VfwSkIGG7EpRg5W7Vb9edPXyym2lgvFGfixveMNsjihi4ObkW8wPJ+gAjUAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:51:10.031634Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.11863","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e2ed973c3f9835fb3f3a8d1b8b6a193c114629c83460a5daec0ccea597ba2b37","sha256:9d8bb1d276266d8912625eb98f73d191f687b0df21832cfd3d0b59c0c8bb4b85"],"state_sha256":"c79a62fdcf5c0b0f9df60b6190ba5fbac6b6802ee9fcbbb2c37fc7d70a75ffbc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/W820oBisVpiWw1XXiUwH/arNcTdFdrFDWx9EXnagpwXIOOS/ab0+f48AMlss193PgfXmrLZmaAZMQVEoVt9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:30:16.344749Z","bundle_sha256":"7cdbea33fdcd88121849e3c345a10cf2f78fc2e3d8dbaa25e2405cdc7b0fd790"}}