{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:R6XP4JN6OGSVNWRODEBQYUBPXC","short_pith_number":"pith:R6XP4JN6","canonical_record":{"source":{"id":"2501.06478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ef4d0c19c48cb45ee77a05e74162244ad3ae533ef00b00ea26e7b06570425047","abstract_canon_sha256":"4ee50354b2ea467b66c4b6a21119f8b19b5a93b98a7894f739be962fb143e016"},"schema_version":"1.0"},"canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","source":{"kind":"arxiv","id":"2501.06478","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06478","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06478v1","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06478","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"R6XP4JN6OGSV","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_16","alias_value":"R6XP4JN6OGSVNWRO","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_8","alias_value":"R6XP4JN6","created_at":"2026-07-05T10:00:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:R6XP4JN6OGSVNWRODEBQYUBPXC","target":"record","payload":{"canonical_record":{"source":{"id":"2501.06478","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"ef4d0c19c48cb45ee77a05e74162244ad3ae533ef00b00ea26e7b06570425047","abstract_canon_sha256":"4ee50354b2ea467b66c4b6a21119f8b19b5a93b98a7894f739be962fb143e016"},"schema_version":"1.0"},"canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:04.072069Z","signature_b64":"jrywIXceDKAKxYq4xmkzc0Xl2R2GVsgiV6EUQtOvdFSnRNpdoXzBbT7+4SRNEIg6Q6fKzYEQ4zeWes/UCP6wCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","last_reissued_at":"2026-07-05T10:00:04.071659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:04.071659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.06478","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":"2026-07-05T10:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X8Hm/+0tZ6i/KOaV3HLyrfOLk2N/asoxED2g2W0l9ugYU7GeO/uDr4uGnS3BVE5FMqWQzic/5ll9w9mG6pkIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:13.766979Z"},"content_sha256":"fdab77ad791aba4b08b68b941cec773ecc2b76746beb0cda796e5c22d3f15156","schema_version":"1.0","event_id":"sha256:fdab77ad791aba4b08b68b941cec773ecc2b76746beb0cda796e5c22d3f15156"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:R6XP4JN6OGSVNWRODEBQYUBPXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Annelien Smith, Christiaan Jacobs, Daleen Klop, Febe de Wet, Herman Kamper, Ond\\v{r}ej Klejch","submitted_at":"2025-01-11T08:11:09Z","abstract_excerpt":"We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06478","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/2501.06478/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":"2026-07-05T10:00:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1mnRsoeC6Z2V81HqgonF3+d5GtGr+KSt3gBH3lLfUxUaGq2QgJysEqvndtn9a0pysAI94u6ZzEusxczqinDvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T10:31:13.767433Z"},"content_sha256":"472ff5cbf29cc55fc1521fe6db0debf4b562774996c508d9267ed7caa0a42bda","schema_version":"1.0","event_id":"sha256:472ff5cbf29cc55fc1521fe6db0debf4b562774996c508d9267ed7caa0a42bda"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/bundle.json","state_url":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/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":"2026-07-06T10:31:13Z","links":{"resolver":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC","bundle":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/bundle.json","state":"https://pith.science/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6XP4JN6OGSVNWRODEBQYUBPXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R6XP4JN6OGSVNWRODEBQYUBPXC","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":"4ee50354b2ea467b66c4b6a21119f8b19b5a93b98a7894f739be962fb143e016","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","title_canon_sha256":"ef4d0c19c48cb45ee77a05e74162244ad3ae533ef00b00ea26e7b06570425047"},"schema_version":"1.0","source":{"id":"2501.06478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.06478","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"arxiv_version","alias_value":"2501.06478v1","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06478","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_12","alias_value":"R6XP4JN6OGSV","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_16","alias_value":"R6XP4JN6OGSVNWRO","created_at":"2026-07-05T10:00:04Z"},{"alias_kind":"pith_short_8","alias_value":"R6XP4JN6","created_at":"2026-07-05T10:00:04Z"}],"graph_snapshots":[{"event_id":"sha256:472ff5cbf29cc55fc1521fe6db0debf4b562774996c508d9267ed7caa0a42bda","target":"graph","created_at":"2026-07-05T10:00:04Z","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/2501.06478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of prior child-speech ASR strategies to determine which is best suited to this unique setting. Using Whisper and only 5 minutes of transcribed in-domain child speech, we find that additional in-domain adult data (adult speech matching the story domain) provides the biggest improvement, especially when coupled with voice conversion. Semi-supervised learning also ","authors_text":"Annelien Smith, Christiaan Jacobs, Daleen Klop, Febe de Wet, Herman Kamper, Ond\\v{r}ej Klejch","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","title":"Speech Recognition for Automatically Assessing Afrikaans and isiXhosa Preschool Oral Narratives"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06478","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:fdab77ad791aba4b08b68b941cec773ecc2b76746beb0cda796e5c22d3f15156","target":"record","created_at":"2026-07-05T10:00:04Z","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":"4ee50354b2ea467b66c4b6a21119f8b19b5a93b98a7894f739be962fb143e016","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-01-11T08:11:09Z","title_canon_sha256":"ef4d0c19c48cb45ee77a05e74162244ad3ae533ef00b00ea26e7b06570425047"},"schema_version":"1.0","source":{"id":"2501.06478","kind":"arxiv","version":1}},"canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8faefe25be71a556da2e19030c502fb8a8ba38c2940b1bb6e3029cdee840139f","first_computed_at":"2026-07-05T10:00:04.071659Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:00:04.071659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jrywIXceDKAKxYq4xmkzc0Xl2R2GVsgiV6EUQtOvdFSnRNpdoXzBbT7+4SRNEIg6Q6fKzYEQ4zeWes/UCP6wCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:00:04.072069Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.06478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fdab77ad791aba4b08b68b941cec773ecc2b76746beb0cda796e5c22d3f15156","sha256:472ff5cbf29cc55fc1521fe6db0debf4b562774996c508d9267ed7caa0a42bda"],"state_sha256":"38b66596307a1a3d43f7358034c4814f08a42099d86fcc4d4158867def706831"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErxwRy4mz2U2KUpXqTpulAWl7E92uSP64isr+pZvo4gLsz4eE/3Q75Iwe4hcO1guLpAbArrk5o6msfA+OgUlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T10:31:13.769452Z","bundle_sha256":"e4f9b701ab81512c6a3769e777d4ed507806f1c07ceb2ad977146a2e91869805"}}