{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ISXX2GXN2OLIEBWPVZ5YKQBJTP","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":"ca5c14e069ae72408c5e601f3264c01511a0a9b54809395ddb2c73eb903f1280","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T14:43:43Z","title_canon_sha256":"01dab2483cb72bf11ee5ec1d3aebba1fa2c9f69a1a40d16e39edbade6723ce7e"},"schema_version":"1.0","source":{"id":"2606.24648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24648","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24648v1","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24648","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_12","alias_value":"ISXX2GXN2OLI","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_16","alias_value":"ISXX2GXN2OLIEBWP","created_at":"2026-06-24T01:15:38Z"},{"alias_kind":"pith_short_8","alias_value":"ISXX2GXN","created_at":"2026-06-24T01:15:38Z"}],"graph_snapshots":[{"event_id":"sha256:e9a3554b0681e225b18a44c809e34dc6be62ee6efefc20e41493e132a5d9bd43","target":"graph","created_at":"2026-06-24T01:15:38Z","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/2606.24648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio-Language Models (LALMs) have been widely used as judge models for the automatic evaluation of generated speech. However, prior approaches predominantly focus on holistic naturalness, leaving fine-grained paralinguistic distinctions underexplored. We introduce ParaPairAudioBench, a pairwise benchmark of 5,175 audio pairs across five paralinguistic dimensions: Style, Rate, Emphasis, Age, and Gender. Our experiments show that current LALM judges still lag behind human judgments by 32%p on average and exhibit severe calibration failures, particularly in Tie cases where the correct deci","authors_text":"Hwiyeol Jo, Jeonghoon Kim, Jinhyeon Kim, Jisu Jeon, Jonghyun Choi, Joosung Lee, Seungyeon Jwa, Soyoon Kim, WooJin Chung","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T14:43:43Z","title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24648","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":"sha256:7bce23296376d937be3da88a09a4190f8f32ac908961f07672881bcd4ddb15ec","target":"record","created_at":"2026-06-24T01:15:38Z","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":"ca5c14e069ae72408c5e601f3264c01511a0a9b54809395ddb2c73eb903f1280","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T14:43:43Z","title_canon_sha256":"01dab2483cb72bf11ee5ec1d3aebba1fa2c9f69a1a40d16e39edbade6723ce7e"},"schema_version":"1.0","source":{"id":"2606.24648","kind":"arxiv","version":1}},"canonical_sha256":"44af7d1aedd3968206cfae7b8540299be010d339da2eff43ef6f44123cb16c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"44af7d1aedd3968206cfae7b8540299be010d339da2eff43ef6f44123cb16c20","first_computed_at":"2026-06-24T01:15:38.105213Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:38.105213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U4HBMb74rOpTuN6TvYJbW23X1RQ0SUcmtB/SUdEUSiqCTxnM+NeRp6Ggfw0q31TdQ4+jIjiA4fLQJEMGD4AJDg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:38.105697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7bce23296376d937be3da88a09a4190f8f32ac908961f07672881bcd4ddb15ec","sha256:e9a3554b0681e225b18a44c809e34dc6be62ee6efefc20e41493e132a5d9bd43"],"state_sha256":"a3555ed2294a44515f83f981a09198a3ddb157bc71393f8cb1e54d7bc62f8746"}