{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:43YS2VMUK6Y7ZB5IVPERHMEGGW","short_pith_number":"pith:43YS2VMU","schema_version":"1.0","canonical_sha256":"e6f12d559457b1fc87a8abc913b08635a2fc88c5d0a02503ab80a30b35458b64","source":{"kind":"arxiv","id":"2501.17202","version":2},"attestation_state":"computed","paper":{"title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao-Han Huck Yang, Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Siyin Wang, Yuchen Hu, Zhehuai Chen","submitted_at":"2025-01-27T22:47:51Z","abstract_excerpt":"An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs remain unaware of the quality of the speech they process. This limitation arises because speech quality evaluation is typically excluded from multi-task training due to the lack of suitable datasets. To address this, we introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. In addition to the overall Mean"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.17202","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T22:47:51Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"95ca63f6ae19217c17ad118285e8d124f15c4302f907f4e184eb6bfce864ae5b","abstract_canon_sha256":"98378a89ec122c86939d5c0790fe01620d4877004fad9bd5655cc24bdec4322e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:33.195018Z","signature_b64":"lD5+95HPmdV0VMeVcQKJVNK3h3XskpkMWHrf+sW25sCtBDfJoUTcVZg7iS3cXGljQgicshq3j96CbiRNvlpWAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6f12d559457b1fc87a8abc913b08635a2fc88c5d0a02503ab80a30b35458b64","last_reissued_at":"2026-07-05T10:29:33.194485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:33.194485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chao-Han Huck Yang, Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Siyin Wang, Yuchen Hu, Zhehuai Chen","submitted_at":"2025-01-27T22:47:51Z","abstract_excerpt":"An ideal multimodal agent should be aware of the quality of its input modalities. Recent advances have enabled large language models (LLMs) to incorporate auditory systems for handling various speech-related tasks. However, most audio LLMs remain unaware of the quality of the speech they process. This limitation arises because speech quality evaluation is typically excluded from multi-task training due to the lack of suitable datasets. To address this, we introduce the first natural language-based speech evaluation corpus, generated from authentic human ratings. In addition to the overall Mean"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17202","kind":"arxiv","version":2},"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/2501.17202/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.17202","created_at":"2026-07-05T10:29:33.194548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.17202v2","created_at":"2026-07-05T10:29:33.194548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17202","created_at":"2026-07-05T10:29:33.194548+00:00"},{"alias_kind":"pith_short_12","alias_value":"43YS2VMUK6Y7","created_at":"2026-07-05T10:29:33.194548+00:00"},{"alias_kind":"pith_short_16","alias_value":"43YS2VMUK6Y7ZB5I","created_at":"2026-07-05T10:29:33.194548+00:00"},{"alias_kind":"pith_short_8","alias_value":"43YS2VMU","created_at":"2026-07-05T10:29:33.194548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24648","citing_title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13507","citing_title":"Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04505","citing_title":"JASTIN: Aligning LLMs for Zero-Shot Audio and Speech Evaluation via Natural Language Instructions","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13804","citing_title":"Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW","json":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW.json","graph_json":"https://pith.science/api/pith-number/43YS2VMUK6Y7ZB5IVPERHMEGGW/graph.json","events_json":"https://pith.science/api/pith-number/43YS2VMUK6Y7ZB5IVPERHMEGGW/events.json","paper":"https://pith.science/paper/43YS2VMU"},"agent_actions":{"view_html":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW","download_json":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW.json","view_paper":"https://pith.science/paper/43YS2VMU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.17202&json=true","fetch_graph":"https://pith.science/api/pith-number/43YS2VMUK6Y7ZB5IVPERHMEGGW/graph.json","fetch_events":"https://pith.science/api/pith-number/43YS2VMUK6Y7ZB5IVPERHMEGGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW/action/storage_attestation","attest_author":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW/action/author_attestation","sign_citation":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW/action/citation_signature","submit_replication":"https://pith.science/pith/43YS2VMUK6Y7ZB5IVPERHMEGGW/action/replication_record"}},"created_at":"2026-07-05T10:29:33.194548+00:00","updated_at":"2026-07-05T10:29:33.194548+00:00"}