{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:43YS2VMUK6Y7ZB5IVPERHMEGGW","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":"98378a89ec122c86939d5c0790fe01620d4877004fad9bd5655cc24bdec4322e","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T22:47:51Z","title_canon_sha256":"95ca63f6ae19217c17ad118285e8d124f15c4302f907f4e184eb6bfce864ae5b"},"schema_version":"1.0","source":{"id":"2501.17202","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.17202","created_at":"2026-07-05T10:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2501.17202v2","created_at":"2026-07-05T10:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.17202","created_at":"2026-07-05T10:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"43YS2VMUK6Y7","created_at":"2026-07-05T10:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"43YS2VMUK6Y7ZB5I","created_at":"2026-07-05T10:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"43YS2VMU","created_at":"2026-07-05T10:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:36cd1b3d329ef1d52cb99e2e7f25ee89745c8147185312919c6c0746c36c79db","target":"graph","created_at":"2026-07-05T10:29:33Z","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/2501.17202/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao-Han Huck Yang, Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Siyin Wang, Yuchen Hu, Zhehuai Chen","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T22:47:51Z","title":"Audio Large Language Models Can Be Descriptive Speech Quality Evaluators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.17202","kind":"arxiv","version":2},"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":"sha256:4661f1a0d4832256d39d6ff572dcc86df3367fe896c1732c98cd66170fd17ea3","target":"record","created_at":"2026-07-05T10:29:33Z","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":"98378a89ec122c86939d5c0790fe01620d4877004fad9bd5655cc24bdec4322e","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-27T22:47:51Z","title_canon_sha256":"95ca63f6ae19217c17ad118285e8d124f15c4302f907f4e184eb6bfce864ae5b"},"schema_version":"1.0","source":{"id":"2501.17202","kind":"arxiv","version":2}},"canonical_sha256":"e6f12d559457b1fc87a8abc913b08635a2fc88c5d0a02503ab80a30b35458b64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6f12d559457b1fc87a8abc913b08635a2fc88c5d0a02503ab80a30b35458b64","first_computed_at":"2026-07-05T10:29:33.194485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:33.194485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lD5+95HPmdV0VMeVcQKJVNK3h3XskpkMWHrf+sW25sCtBDfJoUTcVZg7iS3cXGljQgicshq3j96CbiRNvlpWAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:33.195018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.17202","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4661f1a0d4832256d39d6ff572dcc86df3367fe896c1732c98cd66170fd17ea3","sha256:36cd1b3d329ef1d52cb99e2e7f25ee89745c8147185312919c6c0746c36c79db"],"state_sha256":"46077fa3c267ef81b4f7ee12b5016c18780395808a2bdfcdbb65d92156ceb00f"}