{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YQHFISXUQC7AYAWRTHNAFUOZV7","short_pith_number":"pith:YQHFISXU","canonical_record":{"source":{"id":"2506.17525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T00:34:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29c9f3097de426a9d0923fc7fb5471db5ace145cb05ec825ecac14f261d91526","abstract_canon_sha256":"f31198fa2c6e7afab5e3c6fcad8682ce297d5fe7e22293954c871a5f3ce41c63"},"schema_version":"1.0"},"canonical_sha256":"c40e544af480be0c02d199da02d1d9afc330c882a8b9d3b1786c6ffe0496e512","source":{"kind":"arxiv","id":"2506.17525","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17525","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17525v2","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17525","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"YQHFISXUQC7A","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"YQHFISXUQC7AYAWR","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"YQHFISXU","created_at":"2026-07-05T11:28:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YQHFISXUQC7AYAWRTHNAFUOZV7","target":"record","payload":{"canonical_record":{"source":{"id":"2506.17525","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T00:34:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"29c9f3097de426a9d0923fc7fb5471db5ace145cb05ec825ecac14f261d91526","abstract_canon_sha256":"f31198fa2c6e7afab5e3c6fcad8682ce297d5fe7e22293954c871a5f3ce41c63"},"schema_version":"1.0"},"canonical_sha256":"c40e544af480be0c02d199da02d1d9afc330c882a8b9d3b1786c6ffe0496e512","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:37.874122Z","signature_b64":"JbAPJ7lUwLobqdau68eAarw7yHd8UzJ2N/XILraTD5T2y3FlIUIEsm4kyVj56yqAZTz/48HHjlwWqBx66A1SCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40e544af480be0c02d199da02d1d9afc330c882a8b9d3b1786c6ffe0496e512","last_reissued_at":"2026-07-05T11:28:37.873689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:37.873689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.17525","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qmx2ecFVHH1QmB4Ado9cVJNbUHoj6sweanhU4CoUSanIeVWXfX77CKbCxHvcYuscnE/mq4MPoruCQw61DZexAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:33:14.076527Z"},"content_sha256":"444a6565e59b017adce837bf667ef2eb4cd53d127510f4c3065853b57f6f4c9d","schema_version":"1.0","event_id":"sha256:444a6565e59b017adce837bf667ef2eb4cd53d127510f4c3065853b57f6f4c9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YQHFISXUQC7AYAWRTHNAFUOZV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mingfei Lau, Pavel Golik, Qian Chen, Tingting Xu, Tongzhou Chen, Yeming Fang","submitted_at":"2025-06-21T00:34:18Z","abstract_excerpt":"Our quality audit for three widely used public multilingual speech datasets - Mozilla Common Voice 17.0, FLEURS, and Vox Populi - shows that in some languages, these datasets suffer from significant quality issues, which may obfuscate downstream evaluation results while creating an illusion of success. We divide these quality issues into two categories: micro-level and macro-level. We find that macro-level issues are more prevalent in less institutionalized, often under-resourced languages. We provide a case analysis of Taiwanese Southern Min (nan_tw) that highlights the need for proactive lan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17525","kind":"arxiv","version":2},"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/2506.17525/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":"2026-07-05T11:28:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CyF5aTL8bQ4DG1AGjFXoC2UGehr6SypqJYEsOu1O8dFfJj5cJy7kqcvw+hdHUCUmGdtWcvHnMtosly1fqk+bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:33:14.077059Z"},"content_sha256":"bb1061adb1e2d21cb6820560a1f046e3cff724eb069479f6488e3852febb8274","schema_version":"1.0","event_id":"sha256:bb1061adb1e2d21cb6820560a1f046e3cff724eb069479f6488e3852febb8274"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/bundle.json","state_url":"https://pith.science/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/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":"2026-08-09T10:33:14Z","links":{"resolver":"https://pith.science/pith/YQHFISXUQC7AYAWRTHNAFUOZV7","bundle":"https://pith.science/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/bundle.json","state":"https://pith.science/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQHFISXUQC7AYAWRTHNAFUOZV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YQHFISXUQC7AYAWRTHNAFUOZV7","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":"f31198fa2c6e7afab5e3c6fcad8682ce297d5fe7e22293954c871a5f3ce41c63","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T00:34:18Z","title_canon_sha256":"29c9f3097de426a9d0923fc7fb5471db5ace145cb05ec825ecac14f261d91526"},"schema_version":"1.0","source":{"id":"2506.17525","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.17525","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"arxiv_version","alias_value":"2506.17525v2","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17525","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_12","alias_value":"YQHFISXUQC7A","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_16","alias_value":"YQHFISXUQC7AYAWR","created_at":"2026-07-05T11:28:37Z"},{"alias_kind":"pith_short_8","alias_value":"YQHFISXU","created_at":"2026-07-05T11:28:37Z"}],"graph_snapshots":[{"event_id":"sha256:bb1061adb1e2d21cb6820560a1f046e3cff724eb069479f6488e3852febb8274","target":"graph","created_at":"2026-07-05T11:28:37Z","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/2506.17525/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Our quality audit for three widely used public multilingual speech datasets - Mozilla Common Voice 17.0, FLEURS, and Vox Populi - shows that in some languages, these datasets suffer from significant quality issues, which may obfuscate downstream evaluation results while creating an illusion of success. We divide these quality issues into two categories: micro-level and macro-level. We find that macro-level issues are more prevalent in less institutionalized, often under-resourced languages. We provide a case analysis of Taiwanese Southern Min (nan_tw) that highlights the need for proactive lan","authors_text":"Mingfei Lau, Pavel Golik, Qian Chen, Tingting Xu, Tongzhou Chen, Yeming Fang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T00:34:18Z","title":"Data Quality Issues in Multilingual Speech Datasets: The Need for Sociolinguistic Awareness and Proactive Language Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17525","kind":"arxiv","version":2},"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":"sha256:444a6565e59b017adce837bf667ef2eb4cd53d127510f4c3065853b57f6f4c9d","target":"record","created_at":"2026-07-05T11:28:37Z","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":"f31198fa2c6e7afab5e3c6fcad8682ce297d5fe7e22293954c871a5f3ce41c63","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T00:34:18Z","title_canon_sha256":"29c9f3097de426a9d0923fc7fb5471db5ace145cb05ec825ecac14f261d91526"},"schema_version":"1.0","source":{"id":"2506.17525","kind":"arxiv","version":2}},"canonical_sha256":"c40e544af480be0c02d199da02d1d9afc330c882a8b9d3b1786c6ffe0496e512","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40e544af480be0c02d199da02d1d9afc330c882a8b9d3b1786c6ffe0496e512","first_computed_at":"2026-07-05T11:28:37.873689Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:37.873689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JbAPJ7lUwLobqdau68eAarw7yHd8UzJ2N/XILraTD5T2y3FlIUIEsm4kyVj56yqAZTz/48HHjlwWqBx66A1SCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:37.874122Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.17525","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:444a6565e59b017adce837bf667ef2eb4cd53d127510f4c3065853b57f6f4c9d","sha256:bb1061adb1e2d21cb6820560a1f046e3cff724eb069479f6488e3852febb8274"],"state_sha256":"3244c54b3b71ae80dc8db90a58945758c9c83a216ab8fb559350ff7b8feffc00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JlAbBuJLi+8u1RsL23qkDpYg8VDBy6PXKLo1CAAjekN487ol5/jsiqvoz4QMrI9y2+2YdqIy96x3UI6ESQa7Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:33:14.081324Z","bundle_sha256":"eea4444cc6ea6090efa42d686a94aa94692426c8a5108bc13d4d3ba4ff21e0fc"}}