{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XZO3VWJAPZQ7GWT7IIWDB5MWZE","short_pith_number":"pith:XZO3VWJA","canonical_record":{"source":{"id":"2408.05554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-10T13:39:13Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"e85702edbe9283d3b65b85af4ebc0a6c0874e977a0955563350f06f694b73166","abstract_canon_sha256":"b5d980e06ad9c10471b2310be21330319ba19089a37d20c34c06c64ae0e92455"},"schema_version":"1.0"},"canonical_sha256":"be5dbad9207e61f35a7f422c30f596c936416248f804f4c671f120fea336d76c","source":{"kind":"arxiv","id":"2408.05554","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05554","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05554v1","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05554","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"XZO3VWJAPZQ7","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"XZO3VWJAPZQ7GWT7","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"XZO3VWJA","created_at":"2026-07-05T10:59:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XZO3VWJAPZQ7GWT7IIWDB5MWZE","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-10T13:39:13Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"e85702edbe9283d3b65b85af4ebc0a6c0874e977a0955563350f06f694b73166","abstract_canon_sha256":"b5d980e06ad9c10471b2310be21330319ba19089a37d20c34c06c64ae0e92455"},"schema_version":"1.0"},"canonical_sha256":"be5dbad9207e61f35a7f422c30f596c936416248f804f4c671f120fea336d76c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:24.507334Z","signature_b64":"AgP81FGRepfdZjktyFEDyNCKZofcD6ggvx1mxpEZdjkRfKjgdw1P/z6W9kRtzZDx0VTU0HyM9al81PcKmEELAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be5dbad9207e61f35a7f422c30f596c936416248f804f4c671f120fea336d76c","last_reissued_at":"2026-07-05T10:59:24.506809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:24.506809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05554","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":"2026-07-05T10:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kQtknmMV+nUv1mE8gN+UfC5B6BulVFP63t4HgiDoSYZ6Bug68xPdqxo8aLMcb2JkBbrMjUx/UL8milkSxGg7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:09:32.674381Z"},"content_sha256":"50823adeaa3dbc2586c2cb5659d5751b75e5a0e2f7f708c5f8ee4150f75c949f","schema_version":"1.0","event_id":"sha256:50823adeaa3dbc2586c2cb5659d5751b75e5a0e2f7f708c5f8ee4150f75c949f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XZO3VWJAPZQ7GWT7IIWDB5MWZE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jinpeng Li, Qi Sun, Wei-Qiang Zhang, Yu Pu","submitted_at":"2024-08-10T13:39:13Z","abstract_excerpt":"Whisper and other large-scale automatic speech recognition models have made significant progress in performance. However, their performance on many low-resource languages, such as Kazakh, is not satisfactory. It is worth researching how to utilize low-cost data to improve the performance of Whisper on under-represented languages. In this study, we utilized easily accessible unpaired speech and text data and combined the language model GPT with Whisper on Kazakh. We implemented end of transcript (EOT) judgment modification and hallucination penalty to improve the performance of speech recogniti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05554","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/2408.05554/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":"2026-07-05T10:59:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nuT7sGmA/4Dh+zgo0qCeHwWVw3IKXGSc0HvGN/3llJSWYePIqbYEMecrm9xYppdrtYICnIGpRURYu+DBjL9uBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T12:09:32.675465Z"},"content_sha256":"906e7e29feebd27ae94ab1ae3eaf8c44dfd14ecbcd791b9abfd8b13be5dad517","schema_version":"1.0","event_id":"sha256:906e7e29feebd27ae94ab1ae3eaf8c44dfd14ecbcd791b9abfd8b13be5dad517"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/bundle.json","state_url":"https://pith.science/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/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":"2026-08-16T12:09:32Z","links":{"resolver":"https://pith.science/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE","bundle":"https://pith.science/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/bundle.json","state":"https://pith.science/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XZO3VWJAPZQ7GWT7IIWDB5MWZE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XZO3VWJAPZQ7GWT7IIWDB5MWZE","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":"b5d980e06ad9c10471b2310be21330319ba19089a37d20c34c06c64ae0e92455","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-10T13:39:13Z","title_canon_sha256":"e85702edbe9283d3b65b85af4ebc0a6c0874e977a0955563350f06f694b73166"},"schema_version":"1.0","source":{"id":"2408.05554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05554","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05554v1","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05554","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_12","alias_value":"XZO3VWJAPZQ7","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_16","alias_value":"XZO3VWJAPZQ7GWT7","created_at":"2026-07-05T10:59:24Z"},{"alias_kind":"pith_short_8","alias_value":"XZO3VWJA","created_at":"2026-07-05T10:59:24Z"}],"graph_snapshots":[{"event_id":"sha256:906e7e29feebd27ae94ab1ae3eaf8c44dfd14ecbcd791b9abfd8b13be5dad517","target":"graph","created_at":"2026-07-05T10:59:24Z","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/2408.05554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whisper and other large-scale automatic speech recognition models have made significant progress in performance. However, their performance on many low-resource languages, such as Kazakh, is not satisfactory. It is worth researching how to utilize low-cost data to improve the performance of Whisper on under-represented languages. In this study, we utilized easily accessible unpaired speech and text data and combined the language model GPT with Whisper on Kazakh. We implemented end of transcript (EOT) judgment modification and hallucination penalty to improve the performance of speech recogniti","authors_text":"Jinpeng Li, Qi Sun, Wei-Qiang Zhang, Yu Pu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-10T13:39:13Z","title":"Improving Whisper's Recognition Performance for Under-Represented Language Kazakh Leveraging Unpaired Speech and Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05554","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":"sha256:50823adeaa3dbc2586c2cb5659d5751b75e5a0e2f7f708c5f8ee4150f75c949f","target":"record","created_at":"2026-07-05T10:59:24Z","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":"b5d980e06ad9c10471b2310be21330319ba19089a37d20c34c06c64ae0e92455","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-08-10T13:39:13Z","title_canon_sha256":"e85702edbe9283d3b65b85af4ebc0a6c0874e977a0955563350f06f694b73166"},"schema_version":"1.0","source":{"id":"2408.05554","kind":"arxiv","version":1}},"canonical_sha256":"be5dbad9207e61f35a7f422c30f596c936416248f804f4c671f120fea336d76c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be5dbad9207e61f35a7f422c30f596c936416248f804f4c671f120fea336d76c","first_computed_at":"2026-07-05T10:59:24.506809Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:24.506809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AgP81FGRepfdZjktyFEDyNCKZofcD6ggvx1mxpEZdjkRfKjgdw1P/z6W9kRtzZDx0VTU0HyM9al81PcKmEELAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:24.507334Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50823adeaa3dbc2586c2cb5659d5751b75e5a0e2f7f708c5f8ee4150f75c949f","sha256:906e7e29feebd27ae94ab1ae3eaf8c44dfd14ecbcd791b9abfd8b13be5dad517"],"state_sha256":"ed55fa1c6b8ebcd591054c44b8f03cc0dad13e7354b22416580c82caf5a0bfd0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TBrHVYPJGPfqc8AqhLXI2PnTEKYrfU3vd/50HZArk6GRCdteaa5ON0RSjUAPBSGsWGy8PeySSuZQ/KsiG2QqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T12:09:32.681410Z","bundle_sha256":"f66eedb4fb4fb3c01827c2bded7eca1fdea53137d969858a49eba03202c564f3"}}