{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GCY27VB4DFOBVHEUDD74BB6DOI","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":"697ef804c099421e87befd9afeb97412a5f7df8272c822d1186e37524d7131c0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-22T06:02:09Z","title_canon_sha256":"65bfae7533f19a41115dc65396ce425c146b8bbb2e2243cf304d6a6314478f05"},"schema_version":"1.0","source":{"id":"2605.23261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23261","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23261v1","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23261","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_12","alias_value":"GCY27VB4DFOB","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_16","alias_value":"GCY27VB4DFOBVHEU","created_at":"2026-05-25T02:01:46Z"},{"alias_kind":"pith_short_8","alias_value":"GCY27VB4","created_at":"2026-05-25T02:01:46Z"}],"graph_snapshots":[{"event_id":"sha256:1d72fb95647ae45d14da9c5bed0455bfa4b40af99482e5c0c3148e4986ff467f","target":"graph","created_at":"2026-05-25T02:01:46Z","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/2605.23261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating speech generation still relies heavily on human judgments, such as Mean Opinion Score (MOS), which are expensive, subjective, and difficult to reproduce at scale. While a few recent studies have begun to explore AudioLLM-based judge models, existing efforts typically target only a narrow set of scenarios (e.g., utterance-level quality or single-turn dialogue) and provide limited coverage of diverse speech generation tasks and evaluation dimensions. In this work, we propose UniSRM, a unified speech reward model that can support multi-dimensional, interpretable reward signals with rel","authors_text":"Dongchao Yang, Helen Meng, Xixin Wu, Yayue Deng, Yiwen Guo, Yuanyuan Wang, Zhiyong Wu","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-22T06:02:09Z","title":"UniSRM: A Unified Speech Reward Model for Reasoning-Based Fine-grained Assessment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23261","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:e882f145b803fa8634be773157e483e83fbcbe68b33345f2d0afc6af340a350d","target":"record","created_at":"2026-05-25T02:01:46Z","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":"697ef804c099421e87befd9afeb97412a5f7df8272c822d1186e37524d7131c0","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-22T06:02:09Z","title_canon_sha256":"65bfae7533f19a41115dc65396ce425c146b8bbb2e2243cf304d6a6314478f05"},"schema_version":"1.0","source":{"id":"2605.23261","kind":"arxiv","version":1}},"canonical_sha256":"30b1afd43c195c1a9c9418ffc087c3722a64cc7457d1cb3974769c80b9e848fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b1afd43c195c1a9c9418ffc087c3722a64cc7457d1cb3974769c80b9e848fa","first_computed_at":"2026-05-25T02:01:46.210059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:46.210059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tL97BU3bBqHJhVj2EdtoqQhz8BN/s51xWfP7jGzc/6knvVK2EiIbjWPrn8MWZ3CI5/0NMJ6JL83E1if+vO8dAQ==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:46.210708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e882f145b803fa8634be773157e483e83fbcbe68b33345f2d0afc6af340a350d","sha256:1d72fb95647ae45d14da9c5bed0455bfa4b40af99482e5c0c3148e4986ff467f"],"state_sha256":"2dae2095e21e648b190b331c46d7be7222c13b45493bf9b2d12bfd5657f6c2b4"}