{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EYKAFT7V45DB4WV3L7MMQKNCLU","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":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121"},"schema_version":"1.0","source":{"id":"2402.02302","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"2402.02302v1","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.02302","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"EYKAFT7V45DB","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"EYKAFT7V45DB4WV3","created_at":"2026-07-05T07:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"EYKAFT7V","created_at":"2026-07-05T07:41:13Z"}],"graph_snapshots":[{"event_id":"sha256:4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7","target":"graph","created_at":"2026-07-05T07:41:13Z","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/2402.02302/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While massively multilingual speech models like wav2vec 2.0 XLSR-128 can be directly fine-tuned for automatic speech recognition (ASR), downstream performance can still be relatively poor on languages that are under-represented in the pre-training data. Continued pre-training on 70-200 hours of untranscribed speech in these languages can help -- but what about languages without that much recorded data? For such cases, we show that supplementing the target language with data from a similar, higher-resource 'donor' language can help. For example, continued pre-training on only 10 hours of low-re","authors_text":"Aryaman Arora, Dan Jurafsky, Georgios Paraskevopoulos, Nay San, Oliver Adams, Prabhjot Kaur, Xiluo He","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title":"Predicting positive transfer for improved low-resource speech recognition using acoustic pseudo-tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.02302","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":"sha256:2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d","target":"record","created_at":"2026-07-05T07:41:13Z","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":"b7aef93bfc2b03607e84904822787c571824b36358771fe93ce3d05198df233c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-03T23:54:03Z","title_canon_sha256":"9d4abcf8cdeb0e06d14de33d9e03c40f181f0c8d9ca3c2ade553fc0890f33121"},"schema_version":"1.0","source":{"id":"2402.02302","kind":"arxiv","version":1}},"canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"261402cff5e7461e5abb5fd8c829a25d2883aa52197b04a57912048463feb782","first_computed_at":"2026-07-05T07:41:13.182051Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:41:13.182051Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VHBXymMyhcUjJkugGolEnv5Mpjda0HO7tush2zP3AVKjaV/tEcSr9IRuXP++MCVljAWTqypmdcN8/LnPKjB0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:41:13.182488Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.02302","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2515e464c6f3fcb65d2c99dbde7d3ae82e704f57a2974c466752d5c0329fcf0d","sha256:4e8d090f78a62ddab8a31872b2bc537c9f6fbe531f079c8489d0cf0a755a10c7"],"state_sha256":"d934fa1ae6aa029b9980cd7385fec7e4d86c76dd893b0b09522b3b7c47752bbb"}