{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XC7ETD65D27KMKJL62GTXDH4AJ","short_pith_number":"pith:XC7ETD65","canonical_record":{"source":{"id":"2108.01280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b770f7091f173d393a3b5e06f5787f5406512f831ded265d5a335770ead287a0","abstract_canon_sha256":"8f1cf8dca89c5dc11c07235337395d71d77515effb1b5890cf38f36906392b9e"},"schema_version":"1.0"},"canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","source":{"kind":"arxiv","id":"2108.01280","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01280","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01280v1","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01280","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"XC7ETD65D27K","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"XC7ETD65D27KMKJL","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"XC7ETD65","created_at":"2026-07-05T03:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XC7ETD65D27KMKJL62GTXDH4AJ","target":"record","payload":{"canonical_record":{"source":{"id":"2108.01280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b770f7091f173d393a3b5e06f5787f5406512f831ded265d5a335770ead287a0","abstract_canon_sha256":"8f1cf8dca89c5dc11c07235337395d71d77515effb1b5890cf38f36906392b9e"},"schema_version":"1.0"},"canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:01.072126Z","signature_b64":"Eo8+kcgNoZqfbr91jienYdfyYeVRNgcwEtY7BC+LR7JB3EEOZaNz0Rp5bp3JPea7Z5giEd5kg5GgYsR5swGBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","last_reissued_at":"2026-07-05T03:03:01.071665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:01.071665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.01280","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":"2026-07-05T03:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Vq1y1GrBIot4/3/zbgMBa2eZEofr0PZFOphiqsroswF7oNvQ38DR5DxQnugzjBRUiICW3U7jqZt6YwV9n7tDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:02:06.431449Z"},"content_sha256":"026379fbdf97c18bb44b5e2113b54cbfe6d49724c4133318c3198bd6b9fc2abf","schema_version":"1.0","event_id":"sha256:026379fbdf97c18bb44b5e2113b54cbfe6d49724c4133318c3198bd6b9fc2abf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XC7ETD65D27KMKJL62GTXDH4AJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","submitted_at":"2021-08-03T04:04:01Z","abstract_excerpt":"We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer networks and then perform an extensive assessment on the aforementioned languages. We also compare two variants of output grapheme set construction: combined and independent. Furthermore, we evaluate the impact of LMs and data augmentation techniques on the recognition performance of the multilingual E2E ASR. In addition, we present several datasets for training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01280","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/2108.01280/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":"2026-07-05T03:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2cJjl+pMNrlBohf+rR6TNCw1tO3cozg0xOCo242CfCz0oXwjxXXncm2YBQcERBU6UPn2KVH7KjiB9Nf/ij2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:02:06.431841Z"},"content_sha256":"557cb5c00224353ba828d0ab3fce20b874afac5ee8c370c83e03987535f12299","schema_version":"1.0","event_id":"sha256:557cb5c00224353ba828d0ab3fce20b874afac5ee8c370c83e03987535f12299"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/bundle.json","state_url":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XC7ETD65D27KMKJL62GTXDH4AJ/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":"2026-08-13T19:02:06Z","links":{"resolver":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ","bundle":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/bundle.json","state":"https://pith.science/pith/XC7ETD65D27KMKJL62GTXDH4AJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XC7ETD65D27KMKJL62GTXDH4AJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XC7ETD65D27KMKJL62GTXDH4AJ","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":"8f1cf8dca89c5dc11c07235337395d71d77515effb1b5890cf38f36906392b9e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","title_canon_sha256":"b770f7091f173d393a3b5e06f5787f5406512f831ded265d5a335770ead287a0"},"schema_version":"1.0","source":{"id":"2108.01280","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01280","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01280v1","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01280","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"XC7ETD65D27K","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"XC7ETD65D27KMKJL","created_at":"2026-07-05T03:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"XC7ETD65","created_at":"2026-07-05T03:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:557cb5c00224353ba828d0ab3fce20b874afac5ee8c370c83e03987535f12299","target":"graph","created_at":"2026-07-05T03:03:01Z","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/2108.01280/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study training a single end-to-end (E2E) automatic speech recognition (ASR) model for three languages used in Kazakhstan: Kazakh, Russian, and English. We first describe the development of multilingual E2E ASR based on Transformer networks and then perform an extensive assessment on the aforementioned languages. We also compare two variants of output grapheme set construction: combined and independent. Furthermore, we evaluate the impact of LMs and data augmentation techniques on the recognition performance of the multilingual E2E ASR. In addition, we present several datasets for training a","authors_text":"Huseyin Atakan Varol, Saida Mussakhojayeva, Yerbolat Khassanov","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","title":"A Study of Multilingual End-to-End Speech Recognition for Kazakh, Russian, and English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01280","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":"sha256:026379fbdf97c18bb44b5e2113b54cbfe6d49724c4133318c3198bd6b9fc2abf","target":"record","created_at":"2026-07-05T03:03:01Z","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":"8f1cf8dca89c5dc11c07235337395d71d77515effb1b5890cf38f36906392b9e","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-08-03T04:04:01Z","title_canon_sha256":"b770f7091f173d393a3b5e06f5787f5406512f831ded265d5a335770ead287a0"},"schema_version":"1.0","source":{"id":"2108.01280","kind":"arxiv","version":1}},"canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8be498fdd1ebea6292bf68d3b8cfc027948fca95e50bcf737028636f282cec5","first_computed_at":"2026-07-05T03:03:01.071665Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:01.071665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Eo8+kcgNoZqfbr91jienYdfyYeVRNgcwEtY7BC+LR7JB3EEOZaNz0Rp5bp3JPea7Z5giEd5kg5GgYsR5swGBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:01.072126Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01280","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:026379fbdf97c18bb44b5e2113b54cbfe6d49724c4133318c3198bd6b9fc2abf","sha256:557cb5c00224353ba828d0ab3fce20b874afac5ee8c370c83e03987535f12299"],"state_sha256":"cd68d2fc3e15f35346373b8f290c60e6673f10bb073cb092fa8a82773f423295"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HTkVW3H5jFStM0+GKFHcgRydCxG8hUeGsJ/KjtdRktIJYRtwWkHVV79j508dnUK7TThD2VZbq4AWgdXDWE8EDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:02:06.435412Z","bundle_sha256":"f8b242fc657fca2b97637a419812c7c91bee54f534541493c12584089d6c3e9b"}}