{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ANFJDLW7JUORCBP3BVAKG2QGBJ","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":"0451a43494676273232e59ca78bba81e56c57abd06c94ac2bd55329f79fb8859","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:32:42Z","title_canon_sha256":"03edfe5332c065ce42a92ab72632a5721a62707aa9cdcadb9294829df8b47bd7"},"schema_version":"1.0","source":{"id":"2406.06371","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.06371","created_at":"2026-07-05T09:38:26Z"},{"alias_kind":"arxiv_version","alias_value":"2406.06371v5","created_at":"2026-07-05T09:38:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.06371","created_at":"2026-07-05T09:38:26Z"},{"alias_kind":"pith_short_12","alias_value":"ANFJDLW7JUOR","created_at":"2026-07-05T09:38:26Z"},{"alias_kind":"pith_short_16","alias_value":"ANFJDLW7JUORCBP3","created_at":"2026-07-05T09:38:26Z"},{"alias_kind":"pith_short_8","alias_value":"ANFJDLW7","created_at":"2026-07-05T09:38:26Z"}],"graph_snapshots":[{"event_id":"sha256:528ff1b6af6705ba97e08b886a465a4389b82192e359411797f15c78ead56194","target":"graph","created_at":"2026-07-05T09:38:26Z","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/2406.06371/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present mHuBERT-147, the first general-purpose massively multilingual HuBERT speech representation model trained on 90K hours of clean, open-license data. To scale up the multi-iteration HuBERT approach, we use faiss-based clustering, achieving 5.2x faster label assignment than the original method. We also apply a new multilingual batching up-sampling strategy, leveraging both language and dataset diversity. After 3 training iterations, our compact 95M parameter mHuBERT-147 outperforms larger models trained on substantially more data. We rank second and first on the ML-SUPERB 10min and 1h l","authors_text":"Ioan Calapodescu, Laurent Besacier, Marcely Zanon Boito, Nikolaos Lagos, Vivek Iyer","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:32:42Z","title":"mHuBERT-147: A Compact Multilingual HuBERT Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.06371","kind":"arxiv","version":5},"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":"sha256:423b0d22e3472e6b163078eace19809ac616435d58dea3ff9b9311d65f26e54a","target":"record","created_at":"2026-07-05T09:38:26Z","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":"0451a43494676273232e59ca78bba81e56c57abd06c94ac2bd55329f79fb8859","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-10T15:32:42Z","title_canon_sha256":"03edfe5332c065ce42a92ab72632a5721a62707aa9cdcadb9294829df8b47bd7"},"schema_version":"1.0","source":{"id":"2406.06371","kind":"arxiv","version":5}},"canonical_sha256":"034a91aedf4d1d1105fb0d40a36a060a452904869bb8e76884f6bde141d5ca3e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"034a91aedf4d1d1105fb0d40a36a060a452904869bb8e76884f6bde141d5ca3e","first_computed_at":"2026-07-05T09:38:26.957397Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:26.957397Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ipnARQClmMtSwWL1tmcOlX+fAG9EqOxTkNYB+IsZN/dxH6ddeUYy3z8alhUrJKAvMOYnD44bAh1s8R5BQauTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:26.957823Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.06371","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:423b0d22e3472e6b163078eace19809ac616435d58dea3ff9b9311d65f26e54a","sha256:528ff1b6af6705ba97e08b886a465a4389b82192e359411797f15c78ead56194"],"state_sha256":"0b59e0e2dca3f6bbbb530d17e19656dc20016936a99ac3ca083f324b689262a7"}