{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UEQEWBY6X5GPN4UWN5X7LVHMM5","short_pith_number":"pith:UEQEWBY6","canonical_record":{"source":{"id":"2207.00659","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T21:02:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78d13d8034ced08f61da9c0d471378cbd989eed173f8757704f75122f9620922","abstract_canon_sha256":"11d5a2de39ac3259f76b0ffa1edccd4ab536f1c57cf3471d2a17d1119b5ebef4"},"schema_version":"1.0"},"canonical_sha256":"a1204b071ebf4cf6f2966f6ff5d4ec6749cd129383443ee38d1ea8d7fc0d5f99","source":{"kind":"arxiv","id":"2207.00659","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00659","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00659v1","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00659","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"UEQEWBY6X5GP","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"UEQEWBY6X5GPN4UW","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"UEQEWBY6","created_at":"2026-07-05T04:36:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UEQEWBY6X5GPN4UWN5X7LVHMM5","target":"record","payload":{"canonical_record":{"source":{"id":"2207.00659","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T21:02:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78d13d8034ced08f61da9c0d471378cbd989eed173f8757704f75122f9620922","abstract_canon_sha256":"11d5a2de39ac3259f76b0ffa1edccd4ab536f1c57cf3471d2a17d1119b5ebef4"},"schema_version":"1.0"},"canonical_sha256":"a1204b071ebf4cf6f2966f6ff5d4ec6749cd129383443ee38d1ea8d7fc0d5f99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:50.831787Z","signature_b64":"OFqu3rf/gD2nR7rK63i8qpy4BAOyOU8Cmvtcm9rDjtqQyLnR74sZuWH2mw0LJacnjOIbM1A/hswmwAtvER7xBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1204b071ebf4cf6f2966f6ff5d4ec6749cd129383443ee38d1ea8d7fc0d5f99","last_reissued_at":"2026-07-05T04:36:50.831324Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:50.831324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.00659","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":"2026-07-05T04:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dwHcd9sztowsLkQWoYuyA1D8r1+qAQWwzmeZwqBWY3DOsgKFSvEFbQtvIqjkgWbuVnvjwTdMRqAvpmiGTd66AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:33:45.724009Z"},"content_sha256":"17415b7744bf080914133bcace3e1e1b4c6cf1a6427ace56002240e187318140","schema_version":"1.0","event_id":"sha256:17415b7744bf080914133bcace3e1e1b4c6cf1a6427ace56002240e187318140"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UEQEWBY6X5GPN4UWN5X7LVHMM5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jayadev Billa, Mitchell DeHaven","submitted_at":"2022-07-01T21:02:51Z","abstract_excerpt":"Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based pretrained XLSR-53 model across many languages when fine-tuned with available labeled data. However, the performance from finetuning these models can be dependent on the amount of in-language or similar-to-in-language data included in the pretraining dataset. In this paper we investigate continued pretraining (CoPT) with unlabeled in-language audio data on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00659","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/2207.00659/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":"2026-07-05T04:36:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oBpB0HISKhjfZQ5FSHqtIOeRtXBQbVR6iJtwJzswQhh6tGpuUKjLWJVFtKyiwWMBDV8VmQmd77/zaXsVqP2DBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:33:45.724530Z"},"content_sha256":"6754967a1b7e2269478a4282eb6ccc2c5d6d36478d8f6be73cbb6d5127e26273","schema_version":"1.0","event_id":"sha256:6754967a1b7e2269478a4282eb6ccc2c5d6d36478d8f6be73cbb6d5127e26273"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/bundle.json","state_url":"https://pith.science/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/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":"2026-08-09T18:33:45Z","links":{"resolver":"https://pith.science/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5","bundle":"https://pith.science/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/bundle.json","state":"https://pith.science/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UEQEWBY6X5GPN4UWN5X7LVHMM5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UEQEWBY6X5GPN4UWN5X7LVHMM5","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":"11d5a2de39ac3259f76b0ffa1edccd4ab536f1c57cf3471d2a17d1119b5ebef4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T21:02:51Z","title_canon_sha256":"78d13d8034ced08f61da9c0d471378cbd989eed173f8757704f75122f9620922"},"schema_version":"1.0","source":{"id":"2207.00659","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00659","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00659v1","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00659","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_12","alias_value":"UEQEWBY6X5GP","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_16","alias_value":"UEQEWBY6X5GPN4UW","created_at":"2026-07-05T04:36:50Z"},{"alias_kind":"pith_short_8","alias_value":"UEQEWBY6","created_at":"2026-07-05T04:36:50Z"}],"graph_snapshots":[{"event_id":"sha256:6754967a1b7e2269478a4282eb6ccc2c5d6d36478d8f6be73cbb6d5127e26273","target":"graph","created_at":"2026-07-05T04:36:50Z","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/2207.00659/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised Transformer based models, such as wav2vec 2.0 and HuBERT, have produced significant improvements over existing approaches to automatic speech recognition (ASR). This is evident in the performance of the wav2vec 2.0 based pretrained XLSR-53 model across many languages when fine-tuned with available labeled data. However, the performance from finetuning these models can be dependent on the amount of in-language or similar-to-in-language data included in the pretraining dataset. In this paper we investigate continued pretraining (CoPT) with unlabeled in-language audio data on the ","authors_text":"Jayadev Billa, Mitchell DeHaven","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T21:02:51Z","title":"Improving Low-Resource Speech Recognition with Pretrained Speech Models: Continued Pretraining vs. Semi-Supervised Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00659","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":"sha256:17415b7744bf080914133bcace3e1e1b4c6cf1a6427ace56002240e187318140","target":"record","created_at":"2026-07-05T04:36:50Z","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":"11d5a2de39ac3259f76b0ffa1edccd4ab536f1c57cf3471d2a17d1119b5ebef4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T21:02:51Z","title_canon_sha256":"78d13d8034ced08f61da9c0d471378cbd989eed173f8757704f75122f9620922"},"schema_version":"1.0","source":{"id":"2207.00659","kind":"arxiv","version":1}},"canonical_sha256":"a1204b071ebf4cf6f2966f6ff5d4ec6749cd129383443ee38d1ea8d7fc0d5f99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1204b071ebf4cf6f2966f6ff5d4ec6749cd129383443ee38d1ea8d7fc0d5f99","first_computed_at":"2026-07-05T04:36:50.831324Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:50.831324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OFqu3rf/gD2nR7rK63i8qpy4BAOyOU8Cmvtcm9rDjtqQyLnR74sZuWH2mw0LJacnjOIbM1A/hswmwAtvER7xBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:50.831787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00659","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17415b7744bf080914133bcace3e1e1b4c6cf1a6427ace56002240e187318140","sha256:6754967a1b7e2269478a4282eb6ccc2c5d6d36478d8f6be73cbb6d5127e26273"],"state_sha256":"22997487bc20dc76d5b96ae9c0f5638e74bf584b82faf54a2a9b390c070dcc8a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1j0LG4eo/J5SQ1ifMlGowP1eLI88By2On3Zr4MXkr6DsytHE4NGnYs115yna9lSwbeZSIem0V1yHEm1O61JGAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:33:45.728559Z","bundle_sha256":"ed3fb3a435f90b31fca1a3428d474c839d76e5ede7e7c632fc4386999b406993"}}