{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:GWXWBCEWYOEUQ73JQJCOCC5SOA","short_pith_number":"pith:GWXWBCEW","canonical_record":{"source":{"id":"2104.04896","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-11T01:57:55Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c7a1a4950af76e6576ba7e41d08004bc0a04a02244cbbae6734e8da938541624","abstract_canon_sha256":"48dc3f475d015e4ba80abbc95b1c48e2376e432cd230f23241d5f2c5a8513cf4"},"schema_version":"1.0"},"canonical_sha256":"35af608896c389487f698244e10bb27015647e721f91eda8ba2aff9ee6641e37","source":{"kind":"arxiv","id":"2104.04896","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04896","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04896v3","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04896","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"GWXWBCEWYOEU","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"GWXWBCEWYOEUQ73J","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"GWXWBCEW","created_at":"2026-07-05T03:46:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:GWXWBCEWYOEUQ73JQJCOCC5SOA","target":"record","payload":{"canonical_record":{"source":{"id":"2104.04896","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-11T01:57:55Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"c7a1a4950af76e6576ba7e41d08004bc0a04a02244cbbae6734e8da938541624","abstract_canon_sha256":"48dc3f475d015e4ba80abbc95b1c48e2376e432cd230f23241d5f2c5a8513cf4"},"schema_version":"1.0"},"canonical_sha256":"35af608896c389487f698244e10bb27015647e721f91eda8ba2aff9ee6641e37","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:33.967080Z","signature_b64":"lwm7DTckvF7Z1AiXCf35IEuPPtnu1TC55825g3OyxVl+IHKXI8PorfpZ9HBNsR6OvSUAE7WsJYSQlSYbMhucAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35af608896c389487f698244e10bb27015647e721f91eda8ba2aff9ee6641e37","last_reissued_at":"2026-07-05T03:46:33.966668Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:33.966668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.04896","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":"2026-07-05T03:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cwgB5tqg+/hrmaez6zjdN+F7k4qXMHIHN1Z4MG9A68l8O2ERhhfj6DQ99W+/UZPYjBoO9j2C+ozMVhbWv1nEBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:32:57.320424Z"},"content_sha256":"a5c6251186509d69c0d5b1f56da8ba6b6c19db210b145d574dd23ecf69a50a4f","schema_version":"1.0","event_id":"sha256:a5c6251186509d69c0d5b1f56da8ba6b6c19db210b145d574dd23ecf69a50a4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:GWXWBCEWYOEUQ73JQJCOCC5SOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Toolbox for Construction and Analysis of Speech Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, Evelina Bakhturina, Vitaly Lavrukhin","submitted_at":"2021-04-11T01:57:55Z","abstract_excerpt":"Automatic Speech Recognition and Text-to-Speech systems are primarily trained in a supervised fashion and require high-quality, accurately labeled speech datasets. In this work, we examine common problems with speech data and introduce a toolbox for the construction and interactive error analysis of speech datasets. The construction tool is based on K\\\"urzinger et al. work, and, to the best of our knowledge, the dataset exploration tool is the world's first open-source tool of this kind. We demonstrate how to apply these tools to create a Russian speech dataset and analyze existing speech data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04896","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/2104.04896/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":"2026-07-05T03:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gT1NacYVqi/ilQucnIJHdlRK09Oyfvx0Lu2MTfMJHqnkGSHN3Wl8w50e1Q6HD4KptvHweOuQZ2LBq7tQp0Z6Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:32:57.321026Z"},"content_sha256":"f36cd7073b282ee922d1152d883f316fe875612dfd994990ef9618088ea04999","schema_version":"1.0","event_id":"sha256:f36cd7073b282ee922d1152d883f316fe875612dfd994990ef9618088ea04999"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/bundle.json","state_url":"https://pith.science/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/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":"2026-08-06T05:32:57Z","links":{"resolver":"https://pith.science/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA","bundle":"https://pith.science/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/bundle.json","state":"https://pith.science/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWXWBCEWYOEUQ73JQJCOCC5SOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GWXWBCEWYOEUQ73JQJCOCC5SOA","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":"48dc3f475d015e4ba80abbc95b1c48e2376e432cd230f23241d5f2c5a8513cf4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-11T01:57:55Z","title_canon_sha256":"c7a1a4950af76e6576ba7e41d08004bc0a04a02244cbbae6734e8da938541624"},"schema_version":"1.0","source":{"id":"2104.04896","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04896","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04896v3","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04896","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"GWXWBCEWYOEU","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"GWXWBCEWYOEUQ73J","created_at":"2026-07-05T03:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"GWXWBCEW","created_at":"2026-07-05T03:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:f36cd7073b282ee922d1152d883f316fe875612dfd994990ef9618088ea04999","target":"graph","created_at":"2026-07-05T03:46:33Z","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/2104.04896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic Speech Recognition and Text-to-Speech systems are primarily trained in a supervised fashion and require high-quality, accurately labeled speech datasets. In this work, we examine common problems with speech data and introduce a toolbox for the construction and interactive error analysis of speech datasets. The construction tool is based on K\\\"urzinger et al. work, and, to the best of our knowledge, the dataset exploration tool is the world's first open-source tool of this kind. We demonstrate how to apply these tools to create a Russian speech dataset and analyze existing speech data","authors_text":"Boris Ginsburg, Evelina Bakhturina, Vitaly Lavrukhin","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-11T01:57:55Z","title":"A Toolbox for Construction and Analysis of Speech Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04896","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:a5c6251186509d69c0d5b1f56da8ba6b6c19db210b145d574dd23ecf69a50a4f","target":"record","created_at":"2026-07-05T03:46:33Z","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":"48dc3f475d015e4ba80abbc95b1c48e2376e432cd230f23241d5f2c5a8513cf4","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-11T01:57:55Z","title_canon_sha256":"c7a1a4950af76e6576ba7e41d08004bc0a04a02244cbbae6734e8da938541624"},"schema_version":"1.0","source":{"id":"2104.04896","kind":"arxiv","version":3}},"canonical_sha256":"35af608896c389487f698244e10bb27015647e721f91eda8ba2aff9ee6641e37","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"35af608896c389487f698244e10bb27015647e721f91eda8ba2aff9ee6641e37","first_computed_at":"2026-07-05T03:46:33.966668Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:33.966668Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lwm7DTckvF7Z1AiXCf35IEuPPtnu1TC55825g3OyxVl+IHKXI8PorfpZ9HBNsR6OvSUAE7WsJYSQlSYbMhucAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:33.967080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04896","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c6251186509d69c0d5b1f56da8ba6b6c19db210b145d574dd23ecf69a50a4f","sha256:f36cd7073b282ee922d1152d883f316fe875612dfd994990ef9618088ea04999"],"state_sha256":"1f20c963d985f3a5c7f3306625805bec1f05c02c00ba11fd5d5cc1a8b9db5f7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bZUI0/oTMIxfDXq86Sz8kW5QE+YUqytBHD+XEfsf24jtaiuDFrLBnTWJqWPkahyCrd5FySdMyJZQPeoYl8FEDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:32:57.324835Z","bundle_sha256":"c2602e344181a233be5354850d392b47e275de6c41d6fea145171aad4dc248b4"}}