{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:77N3NOJV224RPHONVX3WAKFNBR","short_pith_number":"pith:77N3NOJV","canonical_record":{"source":{"id":"2506.00733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:39:48Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"aad40884483502707224659a56882351f8ef32613d39e234c3e6aefd6cf44e17","abstract_canon_sha256":"c06e0d5eb7237b847db5deac0f5d21e71b6b9aedfa7cc11acc95f61ba7103702"},"schema_version":"1.0"},"canonical_sha256":"ffdbb6b935d6b9179dcdadf76028ad0c45afd5221e2b9a373fe38e469c752561","source":{"kind":"arxiv","id":"2506.00733","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00733","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00733v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00733","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"77N3NOJV224R","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"77N3NOJV224RPHON","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"77N3NOJV","created_at":"2026-07-05T11:13:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:77N3NOJV224RPHONVX3WAKFNBR","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00733","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:39:48Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"aad40884483502707224659a56882351f8ef32613d39e234c3e6aefd6cf44e17","abstract_canon_sha256":"c06e0d5eb7237b847db5deac0f5d21e71b6b9aedfa7cc11acc95f61ba7103702"},"schema_version":"1.0"},"canonical_sha256":"ffdbb6b935d6b9179dcdadf76028ad0c45afd5221e2b9a373fe38e469c752561","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:39.536294Z","signature_b64":"7zmTiYw+pXPf+fFp7i8sQhnjWXPQ+9TC/9UbOe1dtjqiAYWnrrPQ6BzHc2cPNJGG1EKSiA+uOidyoPL1f22cDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffdbb6b935d6b9179dcdadf76028ad0c45afd5221e2b9a373fe38e469c752561","last_reissued_at":"2026-07-05T11:13:39.535853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:39.535853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00733","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":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHTjIpngeXt9Bk7FZy9C1ZpxX9g7Qg6c1JYb0uw028S5QiLLjXATs5IGMOoST6+sEsFSZYh+CnVYWc6NhBgOCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:42:28.034229Z"},"content_sha256":"31444d323dd615fc7505fdce9de2bfed13e54bf67aae748cba07ca916d813b3a","schema_version":"1.0","event_id":"sha256:31444d323dd615fc7505fdce9de2bfed13e54bf67aae748cba07ca916d813b3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:77N3NOJV224RPHONVX3WAKFNBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Annie Baker, Aref Farhadipour, Bogdan Pricop, Eleanor Chodroff, Jiachen Ma, Miao Zhang","submitted_at":"2025-05-31T22:39:48Z","abstract_excerpt":"With its crosslinguistic and cross-speaker diversity, the Mozilla Common Voice Corpus (CV) has been a valuable resource for multilingual speech technology and holds tremendous potential for research in crosslinguistic phonetics and speech sciences. Properly accounting for speaker variation is, however, key to the theoretical and statistical bases of speech research. While CV provides a client ID as an approximation to a speaker ID, multiple speakers can contribute under the same ID. This study aims to quantify and reduce heterogeneity in the client ID for a better approximation of a true, thou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00733","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/2506.00733/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":"2026-07-05T11:13:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q/bRTtL//S9i7UEoU1QooO2GtHH7Z8vR9DqhRUER1gLzKTscAq0rlCNMHLjZwfMhHK39azpisQ7uNgAhsoMaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:42:28.034830Z"},"content_sha256":"0072f8af2342457863d2952fc771487eaf4ea3b407f6d196cea58954b8a93834","schema_version":"1.0","event_id":"sha256:0072f8af2342457863d2952fc771487eaf4ea3b407f6d196cea58954b8a93834"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/77N3NOJV224RPHONVX3WAKFNBR/bundle.json","state_url":"https://pith.science/pith/77N3NOJV224RPHONVX3WAKFNBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/77N3NOJV224RPHONVX3WAKFNBR/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":"2026-08-13T19:42:28Z","links":{"resolver":"https://pith.science/pith/77N3NOJV224RPHONVX3WAKFNBR","bundle":"https://pith.science/pith/77N3NOJV224RPHONVX3WAKFNBR/bundle.json","state":"https://pith.science/pith/77N3NOJV224RPHONVX3WAKFNBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/77N3NOJV224RPHONVX3WAKFNBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:77N3NOJV224RPHONVX3WAKFNBR","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":"c06e0d5eb7237b847db5deac0f5d21e71b6b9aedfa7cc11acc95f61ba7103702","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:39:48Z","title_canon_sha256":"aad40884483502707224659a56882351f8ef32613d39e234c3e6aefd6cf44e17"},"schema_version":"1.0","source":{"id":"2506.00733","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00733","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00733v1","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00733","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_12","alias_value":"77N3NOJV224R","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_16","alias_value":"77N3NOJV224RPHON","created_at":"2026-07-05T11:13:39Z"},{"alias_kind":"pith_short_8","alias_value":"77N3NOJV","created_at":"2026-07-05T11:13:39Z"}],"graph_snapshots":[{"event_id":"sha256:0072f8af2342457863d2952fc771487eaf4ea3b407f6d196cea58954b8a93834","target":"graph","created_at":"2026-07-05T11:13:39Z","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/2506.00733/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With its crosslinguistic and cross-speaker diversity, the Mozilla Common Voice Corpus (CV) has been a valuable resource for multilingual speech technology and holds tremendous potential for research in crosslinguistic phonetics and speech sciences. Properly accounting for speaker variation is, however, key to the theoretical and statistical bases of speech research. While CV provides a client ID as an approximation to a speaker ID, multiple speakers can contribute under the same ID. This study aims to quantify and reduce heterogeneity in the client ID for a better approximation of a true, thou","authors_text":"Annie Baker, Aref Farhadipour, Bogdan Pricop, Eleanor Chodroff, Jiachen Ma, Miao Zhang","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:39:48Z","title":"Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00733","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":"sha256:31444d323dd615fc7505fdce9de2bfed13e54bf67aae748cba07ca916d813b3a","target":"record","created_at":"2026-07-05T11:13:39Z","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":"c06e0d5eb7237b847db5deac0f5d21e71b6b9aedfa7cc11acc95f61ba7103702","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-31T22:39:48Z","title_canon_sha256":"aad40884483502707224659a56882351f8ef32613d39e234c3e6aefd6cf44e17"},"schema_version":"1.0","source":{"id":"2506.00733","kind":"arxiv","version":1}},"canonical_sha256":"ffdbb6b935d6b9179dcdadf76028ad0c45afd5221e2b9a373fe38e469c752561","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffdbb6b935d6b9179dcdadf76028ad0c45afd5221e2b9a373fe38e469c752561","first_computed_at":"2026-07-05T11:13:39.535853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:39.535853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7zmTiYw+pXPf+fFp7i8sQhnjWXPQ+9TC/9UbOe1dtjqiAYWnrrPQ6BzHc2cPNJGG1EKSiA+uOidyoPL1f22cDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:39.536294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00733","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31444d323dd615fc7505fdce9de2bfed13e54bf67aae748cba07ca916d813b3a","sha256:0072f8af2342457863d2952fc771487eaf4ea3b407f6d196cea58954b8a93834"],"state_sha256":"7e6963e85d2a2e4205da106401ac519242511d1f53d09ecfc76a523aff02423c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fwela4LEFRS733evwdAdncMqGjvi4pByZpdlAtrpzf+RSOIh+vdeN60gE9dEuavKmkEe3tqQb6VWM+0dogtvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:42:28.041088Z","bundle_sha256":"e583165fd332868d2a18926ee0d5d8a858a3e5ba1780f318db5b3316f9d58ccc"}}