{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:JF4NGGZYLSXJJZLFKH6U7C5YBR","short_pith_number":"pith:JF4NGGZY","canonical_record":{"source":{"id":"2409.16644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T05:44:44Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"985620c16454fadecfb38f097ce19d3d20f736b368e520a92658c9c0021922c4","abstract_canon_sha256":"7e94103f438400901d6c9039af941d0623ded8a9faf4d9e15863087bbd6daf18"},"schema_version":"1.0"},"canonical_sha256":"4978d31b385cae94e56551fd4f8bb80c77e84e13156b20512c33a1899d66b7d6","source":{"kind":"arxiv","id":"2409.16644","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16644","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16644v3","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16644","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"JF4NGGZYLSXJ","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"JF4NGGZYLSXJJZLF","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"JF4NGGZY","created_at":"2026-07-05T10:42:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:JF4NGGZYLSXJJZLFKH6U7C5YBR","target":"record","payload":{"canonical_record":{"source":{"id":"2409.16644","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T05:44:44Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"985620c16454fadecfb38f097ce19d3d20f736b368e520a92658c9c0021922c4","abstract_canon_sha256":"7e94103f438400901d6c9039af941d0623ded8a9faf4d9e15863087bbd6daf18"},"schema_version":"1.0"},"canonical_sha256":"4978d31b385cae94e56551fd4f8bb80c77e84e13156b20512c33a1899d66b7d6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:37.635665Z","signature_b64":"A8LVLMjGYGYpbHNjeAwEqTTSytSUi5Ywf3T8F2vkExYE/R7SfpSuBtu9l0QyVbipZxnYWy2Fk0ImM83BTqZbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4978d31b385cae94e56551fd4f8bb80c77e84e13156b20512c33a1899d66b7d6","last_reissued_at":"2026-07-05T10:42:37.635163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:37.635163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.16644","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":"2026-07-05T10:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5UFe6esSof1fOukSnQd7AAsRL/HnKylhvuiy2RQkE+0y6z3rcYY9MGn8bxPE5AURZmvgwCg0SF+GxhMet1fDDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:56:15.269139Z"},"content_sha256":"9e469793d55d8ddb92a265a4c4d73b1b73fb79d205ba5104dbc61df72ea8947a","schema_version":"1.0","event_id":"sha256:9e469793d55d8ddb92a265a4c4d73b1b73fb79d205ba5104dbc61df72ea8947a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:JF4NGGZYLSXJJZLFKH6U7C5YBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Jun Zhang, Lu Lu, Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Yixuan Li, Yudong Yang, Yuxuan Wang","submitted_at":"2024-09-25T05:44:44Z","abstract_excerpt":"Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \\etc., which can be challenging to cover using one small model designed for a single task. In this paper, we propose leveraging recently introduced auditory large language models (LLMs) for automatic speech quality assessment. By employing task-specific prompts, auditory LLMs are finetuned to predict MOS, SIM and A/B testing results, which are commonly used for evaluating text-to-speech systems. Additionally, the finetuned auditory LLM is able to ge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16644","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/2409.16644/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":"2026-07-05T10:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Np0cQftWLZ8QugSKfEX5vPjBFefQ+EPMvEN+6vNVT12zKBcG0CKihe5G7HeYaNfS7czP0K4tUclSpTOoNr5jAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:56:15.269656Z"},"content_sha256":"1c3d8b9d83f74795753cb4e24205f459426c154e1ce413c7ab1d558e7b461744","schema_version":"1.0","event_id":"sha256:1c3d8b9d83f74795753cb4e24205f459426c154e1ce413c7ab1d558e7b461744"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/bundle.json","state_url":"https://pith.science/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/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":"2026-08-18T06:56:15Z","links":{"resolver":"https://pith.science/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR","bundle":"https://pith.science/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/bundle.json","state":"https://pith.science/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JF4NGGZYLSXJJZLFKH6U7C5YBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JF4NGGZYLSXJJZLFKH6U7C5YBR","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":"7e94103f438400901d6c9039af941d0623ded8a9faf4d9e15863087bbd6daf18","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T05:44:44Z","title_canon_sha256":"985620c16454fadecfb38f097ce19d3d20f736b368e520a92658c9c0021922c4"},"schema_version":"1.0","source":{"id":"2409.16644","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.16644","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"2409.16644v3","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16644","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"JF4NGGZYLSXJ","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_16","alias_value":"JF4NGGZYLSXJJZLF","created_at":"2026-07-05T10:42:37Z"},{"alias_kind":"pith_short_8","alias_value":"JF4NGGZY","created_at":"2026-07-05T10:42:37Z"}],"graph_snapshots":[{"event_id":"sha256:1c3d8b9d83f74795753cb4e24205f459426c154e1ce413c7ab1d558e7b461744","target":"graph","created_at":"2026-07-05T10:42:37Z","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/2409.16644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech quality assessment typically requires evaluating audio from multiple aspects, such as mean opinion score (MOS) and speaker similarity (SIM) \\etc., which can be challenging to cover using one small model designed for a single task. In this paper, we propose leveraging recently introduced auditory large language models (LLMs) for automatic speech quality assessment. By employing task-specific prompts, auditory LLMs are finetuned to predict MOS, SIM and A/B testing results, which are commonly used for evaluating text-to-speech systems. Additionally, the finetuned auditory LLM is able to ge","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jimin Zhuang, Jun Zhang, Lu Lu, Siyin Wang, Wenyi Yu, Xianzhao Chen, Xiaohai Tian, Yixuan Li, Yudong Yang, Yuxuan Wang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T05:44:44Z","title":"Enabling Auditory Large Language Models for Automatic Speech Quality Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16644","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":"sha256:9e469793d55d8ddb92a265a4c4d73b1b73fb79d205ba5104dbc61df72ea8947a","target":"record","created_at":"2026-07-05T10:42:37Z","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":"7e94103f438400901d6c9039af941d0623ded8a9faf4d9e15863087bbd6daf18","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-25T05:44:44Z","title_canon_sha256":"985620c16454fadecfb38f097ce19d3d20f736b368e520a92658c9c0021922c4"},"schema_version":"1.0","source":{"id":"2409.16644","kind":"arxiv","version":3}},"canonical_sha256":"4978d31b385cae94e56551fd4f8bb80c77e84e13156b20512c33a1899d66b7d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4978d31b385cae94e56551fd4f8bb80c77e84e13156b20512c33a1899d66b7d6","first_computed_at":"2026-07-05T10:42:37.635163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:42:37.635163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A8LVLMjGYGYpbHNjeAwEqTTSytSUi5Ywf3T8F2vkExYE/R7SfpSuBtu9l0QyVbipZxnYWy2Fk0ImM83BTqZbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:42:37.635665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.16644","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e469793d55d8ddb92a265a4c4d73b1b73fb79d205ba5104dbc61df72ea8947a","sha256:1c3d8b9d83f74795753cb4e24205f459426c154e1ce413c7ab1d558e7b461744"],"state_sha256":"db435497ee57cc288104e845db2bb89304c3a6aa344e1f5843f9a462f3b03183"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZY/MQMmplJt3yZc6SCgUwNmXbmM8GxCjugUXCH9wL+ITyNNEdyoRPfgNpkLXSslr+2aiexUDy1BA3udD/dcIDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:56:15.274028Z","bundle_sha256":"f8271085fe04e47028bb699bbfd4742c97f5e922e49ef126d27d0167fa8c148a"}}