{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TF3LGZYK33LFUBA2NZLZZ7Q7RP","short_pith_number":"pith:TF3LGZYK","canonical_record":{"source":{"id":"2110.07957","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-15T09:22:34Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f8361aa8bab47ca64f718e37283ca92bbc0cfb84cbabe52b2a753f480dfbacf3","abstract_canon_sha256":"45aed5199c0bce1d282ecb04556afa16510534085dfe9a79e2cd13c6b2a6a729"},"schema_version":"1.0"},"canonical_sha256":"9976b3670aded65a041a6e579cfe1f8bf19ee5fc357f73a840194b091aca08ee","source":{"kind":"arxiv","id":"2110.07957","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07957","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07957v3","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07957","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"TF3LGZYK33LF","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"TF3LGZYK33LFUBA2","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"TF3LGZYK","created_at":"2026-07-05T04:17:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TF3LGZYK33LFUBA2NZLZZ7Q7RP","target":"record","payload":{"canonical_record":{"source":{"id":"2110.07957","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-15T09:22:34Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f8361aa8bab47ca64f718e37283ca92bbc0cfb84cbabe52b2a753f480dfbacf3","abstract_canon_sha256":"45aed5199c0bce1d282ecb04556afa16510534085dfe9a79e2cd13c6b2a6a729"},"schema_version":"1.0"},"canonical_sha256":"9976b3670aded65a041a6e579cfe1f8bf19ee5fc357f73a840194b091aca08ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:17:36.797117Z","signature_b64":"f3wIFCiHJDSlnmg4ZHNpAeoJCyjgyTBZMMN2xWCKdfLpFZNq9k6ndFapI3pRGLiUBWiT6aGKVcKKfBi7TTUwCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9976b3670aded65a041a6e579cfe1f8bf19ee5fc357f73a840194b091aca08ee","last_reissued_at":"2026-07-05T04:17:36.796715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:17:36.796715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.07957","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:17:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RZyJVEHKT+z7v7Hkyw7yry/iHsKvmarKuuDV2+6DobURGJZNtEst6dV/TABXjmQmq5dLsy83dF314imoTNJgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:27:38.713467Z"},"content_sha256":"d1340b778ab0fee65b62658c9b8feaecb595b60ce109e1d0cd1eb06c45e18bcd","schema_version":"1.0","event_id":"sha256:d1340b778ab0fee65b62658c9b8feaecb595b60ce109e1d0cd1eb06c45e18bcd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TF3LGZYK33LFUBA2NZLZZ7Q7RP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't speak too fast: The impact of data bias on self-supervised speech models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andy T. Liu, Hung-yi Lee, Yen Meng, Yi-Hui Chou","submitted_at":"2021-10-15T09:22:34Z","abstract_excerpt":"Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pre-training data affects S3Ms' downstream behavior remains an unexplored issue. In this paper, we study how pre-training data affects S3Ms by pre-training models on biased datasets targeting different factors of speech, including gender, content, and prosody, and evaluate these pre-trained S3Ms on selected downstream tasks in SUPERB Benchmark. Our experiments show that S3Ms have tolerance toward gender bias. Moreover, we find that the content of speech has little impact on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07957","kind":"arxiv","version":3},"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/2110.07957/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":"2026-07-05T04:17:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fUmDnEx3cYVu0AcxuJzvWz2f4GgUgTIgpkGBRMPYdVHR/qs1CtkHpIprJHM59oeNms9yc7HKMH1pLDdRduA7Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T15:27:38.714317Z"},"content_sha256":"02031ee93fef5dadbca71d88fa34155b0bcefa6ca0faa2c1deb9fe0bbd6aec05","schema_version":"1.0","event_id":"sha256:02031ee93fef5dadbca71d88fa34155b0bcefa6ca0faa2c1deb9fe0bbd6aec05"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/bundle.json","state_url":"https://pith.science/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/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":"2026-08-18T15:27:38Z","links":{"resolver":"https://pith.science/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP","bundle":"https://pith.science/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/bundle.json","state":"https://pith.science/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TF3LGZYK33LFUBA2NZLZZ7Q7RP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TF3LGZYK33LFUBA2NZLZZ7Q7RP","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":"45aed5199c0bce1d282ecb04556afa16510534085dfe9a79e2cd13c6b2a6a729","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-15T09:22:34Z","title_canon_sha256":"f8361aa8bab47ca64f718e37283ca92bbc0cfb84cbabe52b2a753f480dfbacf3"},"schema_version":"1.0","source":{"id":"2110.07957","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.07957","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"arxiv_version","alias_value":"2110.07957v3","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.07957","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_12","alias_value":"TF3LGZYK33LF","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_16","alias_value":"TF3LGZYK33LFUBA2","created_at":"2026-07-05T04:17:36Z"},{"alias_kind":"pith_short_8","alias_value":"TF3LGZYK","created_at":"2026-07-05T04:17:36Z"}],"graph_snapshots":[{"event_id":"sha256:02031ee93fef5dadbca71d88fa34155b0bcefa6ca0faa2c1deb9fe0bbd6aec05","target":"graph","created_at":"2026-07-05T04:17:36Z","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/2110.07957/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised Speech Models (S3Ms) have been proven successful in many speech downstream tasks, like ASR. However, how pre-training data affects S3Ms' downstream behavior remains an unexplored issue. In this paper, we study how pre-training data affects S3Ms by pre-training models on biased datasets targeting different factors of speech, including gender, content, and prosody, and evaluate these pre-trained S3Ms on selected downstream tasks in SUPERB Benchmark. Our experiments show that S3Ms have tolerance toward gender bias. Moreover, we find that the content of speech has little impact on ","authors_text":"Andy T. Liu, Hung-yi Lee, Yen Meng, Yi-Hui Chou","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-15T09:22:34Z","title":"Don't speak too fast: The impact of data bias on self-supervised speech models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.07957","kind":"arxiv","version":3},"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:d1340b778ab0fee65b62658c9b8feaecb595b60ce109e1d0cd1eb06c45e18bcd","target":"record","created_at":"2026-07-05T04:17:36Z","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":"45aed5199c0bce1d282ecb04556afa16510534085dfe9a79e2cd13c6b2a6a729","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-10-15T09:22:34Z","title_canon_sha256":"f8361aa8bab47ca64f718e37283ca92bbc0cfb84cbabe52b2a753f480dfbacf3"},"schema_version":"1.0","source":{"id":"2110.07957","kind":"arxiv","version":3}},"canonical_sha256":"9976b3670aded65a041a6e579cfe1f8bf19ee5fc357f73a840194b091aca08ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9976b3670aded65a041a6e579cfe1f8bf19ee5fc357f73a840194b091aca08ee","first_computed_at":"2026-07-05T04:17:36.796715Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:36.796715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f3wIFCiHJDSlnmg4ZHNpAeoJCyjgyTBZMMN2xWCKdfLpFZNq9k6ndFapI3pRGLiUBWiT6aGKVcKKfBi7TTUwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:36.797117Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.07957","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d1340b778ab0fee65b62658c9b8feaecb595b60ce109e1d0cd1eb06c45e18bcd","sha256:02031ee93fef5dadbca71d88fa34155b0bcefa6ca0faa2c1deb9fe0bbd6aec05"],"state_sha256":"5a00b8d7a4cfcdea9fcc407bcf539c10cc0f6f9da23a31fc4a86dd7bc2c3bdc0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XXFwV5yqBRFWuMAwHKkn9N3anyLGgnFWTZFSOt9TUGx1xxwL8cON0JdlDG3HksGqhhQu4MvdF/9p6Ca16hClCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T15:27:38.720091Z","bundle_sha256":"448b93a204797bbbc9b4d182b41616a0786e779792171a0ce9a04a13620ddd02"}}