{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VFPOGT3DULEO2XG6KDY4VAY36X","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":"52c42a0736b31ab270c2132b776b05aa0e2d1a58afefa32a37c5a5c5fe6a7e78","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-15T05:13:19Z","title_canon_sha256":"38027f4d29cfff94331bf69ef9503f20474e64f60b7dff33623af68481df470c"},"schema_version":"1.0","source":{"id":"2406.10507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.10507","created_at":"2026-07-05T08:32:17Z"},{"alias_kind":"arxiv_version","alias_value":"2406.10507v1","created_at":"2026-07-05T08:32:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.10507","created_at":"2026-07-05T08:32:17Z"},{"alias_kind":"pith_short_12","alias_value":"VFPOGT3DULEO","created_at":"2026-07-05T08:32:17Z"},{"alias_kind":"pith_short_16","alias_value":"VFPOGT3DULEO2XG6","created_at":"2026-07-05T08:32:17Z"},{"alias_kind":"pith_short_8","alias_value":"VFPOGT3D","created_at":"2026-07-05T08:32:17Z"}],"graph_snapshots":[{"event_id":"sha256:3fd46c4083520ed7a465a546c98608b35bf00e056c33530310ffe9bc96686f91","target":"graph","created_at":"2026-07-05T08:32:17Z","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/2406.10507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the performance of SFMs for child ASR has not been systematically studied. In addition, there is no benchmark for child ASR with standard evaluations, making the comparisons of novel ideas difficult. In this paper, we initiate and present a comprehensive benchmark on several child speech databases based on various SFMs (Whisper, Wav2vec2.0, HuBERT, and WavLM). Moreover, we investigate finetuning strategies by comparing va","authors_text":"Abeer Alwan, Natarajan Balaji Shankar, Ruchao Fan","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-15T05:13:19Z","title":"Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.10507","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":"sha256:6d94a064046bd4b36a4b7d677c18231a521a2f9f23b390853de1d4a0478f845e","target":"record","created_at":"2026-07-05T08:32:17Z","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":"52c42a0736b31ab270c2132b776b05aa0e2d1a58afefa32a37c5a5c5fe6a7e78","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-15T05:13:19Z","title_canon_sha256":"38027f4d29cfff94331bf69ef9503f20474e64f60b7dff33623af68481df470c"},"schema_version":"1.0","source":{"id":"2406.10507","kind":"arxiv","version":1}},"canonical_sha256":"a95ee34f63a2c8ed5cde50f1ca831bf5c940e29424cd2cf86a6422239bc513cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a95ee34f63a2c8ed5cde50f1ca831bf5c940e29424cd2cf86a6422239bc513cc","first_computed_at":"2026-07-05T08:32:17.582224Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:17.582224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HOeWKMYUyWMKJE1kcQzphATZruo9t1b9PpDNmEq+gAKNHZQyt63R05BwmBsSfvJ7DTrdnE5cEMRz8Bk7m1eHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:17.582729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.10507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d94a064046bd4b36a4b7d677c18231a521a2f9f23b390853de1d4a0478f845e","sha256:3fd46c4083520ed7a465a546c98608b35bf00e056c33530310ffe9bc96686f91"],"state_sha256":"c86c50011dad5d2063aefbfcbb46001f315760b184f1d3475c6fd0c1d94b12bf"}