{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PBRP37DBEFZAGGGMEGPW336ZOZ","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":"1e09e03f797fb1eb14f882d9bc46d7c78cd1bfc69b28ad316d696825cd8841a3","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-18T14:10:35Z","title_canon_sha256":"d371837806aae971c5e0135a0d82fed6385b5aa34fd82ed6aeb665328bbb7cb9"},"schema_version":"1.0","source":{"id":"2408.09491","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.09491","created_at":"2026-07-05T08:56:33Z"},{"alias_kind":"arxiv_version","alias_value":"2408.09491v1","created_at":"2026-07-05T08:56:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.09491","created_at":"2026-07-05T08:56:33Z"},{"alias_kind":"pith_short_12","alias_value":"PBRP37DBEFZA","created_at":"2026-07-05T08:56:33Z"},{"alias_kind":"pith_short_16","alias_value":"PBRP37DBEFZAGGGM","created_at":"2026-07-05T08:56:33Z"},{"alias_kind":"pith_short_8","alias_value":"PBRP37DB","created_at":"2026-07-05T08:56:33Z"}],"graph_snapshots":[{"event_id":"sha256:360276c04bea18681a4378b2d43bcb031935fa43d08a27a5744766857a8cff1f","target":"graph","created_at":"2026-07-05T08:56:33Z","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/2408.09491/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-LLM introduces audio modality into a large language model (LLM) to enable a powerful LLM to recognize, understand, and generate audio. However, during speech recognition in noisy environments, we observed the presence of illusions and repetition issues in audio-LLM, leading to substitution and insertion errors. This paper proposes a transcription prompt-based audio-LLM by introducing an ASR expert as a transcription tokenizer and a hybrid Autoregressive (AR) Non-autoregressive (NAR) decoding approach to solve the above problems. Experiments on 10k-hour WenetSpeech Mandarin corpus show th","authors_text":"Lei Xie, Long Ma, Songjun Cao, Xiong Wang, Yangze Li, Yike Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-18T14:10:35Z","title":"A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.09491","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":"sha256:40c11a6da82175aa96ba6ae0025392b5ed144980ef9e6eb4c761b7ef7b25c485","target":"record","created_at":"2026-07-05T08:56:33Z","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":"1e09e03f797fb1eb14f882d9bc46d7c78cd1bfc69b28ad316d696825cd8841a3","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-08-18T14:10:35Z","title_canon_sha256":"d371837806aae971c5e0135a0d82fed6385b5aa34fd82ed6aeb665328bbb7cb9"},"schema_version":"1.0","source":{"id":"2408.09491","kind":"arxiv","version":1}},"canonical_sha256":"7862fdfc6121720318cc219f6defd97674bf806815f27deff5934baa85613f78","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7862fdfc6121720318cc219f6defd97674bf806815f27deff5934baa85613f78","first_computed_at":"2026-07-05T08:56:33.310628Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:33.310628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DizVPMDZyY7tnDBHsOB1mmJM1+xE47XJj6SbEp9e4FR+VPbBWuvhoMYjmpQDyeFymTvflWQaPECGIgDz7ob4Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:33.311112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.09491","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40c11a6da82175aa96ba6ae0025392b5ed144980ef9e6eb4c761b7ef7b25c485","sha256:360276c04bea18681a4378b2d43bcb031935fa43d08a27a5744766857a8cff1f"],"state_sha256":"d937874fa2309af179df86fb5135c18a0e01c106d1e5594a6e652ccc2495d748"}