{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ISXX2GXN2OLIEBWPVZ5YKQBJTP","short_pith_number":"pith:ISXX2GXN","schema_version":"1.0","canonical_sha256":"44af7d1aedd3968206cfae7b8540299be010d339da2eff43ef6f44123cb16c20","source":{"kind":"arxiv","id":"2606.24648","version":1},"attestation_state":"computed","paper":{"title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hwiyeol Jo, Jeonghoon Kim, Jinhyeon Kim, Jisu Jeon, Jonghyun Choi, Joosung Lee, Seungyeon Jwa, Soyoon Kim, WooJin Chung","submitted_at":"2026-06-23T14:43:43Z","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"},"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":"2606.24648","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T14:43:43Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"01dab2483cb72bf11ee5ec1d3aebba1fa2c9f69a1a40d16e39edbade6723ce7e","abstract_canon_sha256":"ca5c14e069ae72408c5e601f3264c01511a0a9b54809395ddb2c73eb903f1280"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:38.105697Z","signature_b64":"U4HBMb74rOpTuN6TvYJbW23X1RQ0SUcmtB/SUdEUSiqCTxnM+NeRp6Ggfw0q31TdQ4+jIjiA4fLQJEMGD4AJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"44af7d1aedd3968206cfae7b8540299be010d339da2eff43ef6f44123cb16c20","last_reissued_at":"2026-06-24T01:15:38.105213Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:38.105213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Hwiyeol Jo, Jeonghoon Kim, Jinhyeon Kim, Jisu Jeon, Jonghyun Choi, Joosung Lee, Seungyeon Jwa, Soyoon Kim, WooJin Chung","submitted_at":"2026-06-23T14:43:43Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24648","kind":"arxiv","version":1},"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/2606.24648/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":"2606.24648","created_at":"2026-06-24T01:15:38.105300+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24648v1","created_at":"2026-06-24T01:15:38.105300+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24648","created_at":"2026-06-24T01:15:38.105300+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISXX2GXN2OLI","created_at":"2026-06-24T01:15:38.105300+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISXX2GXN2OLIEBWP","created_at":"2026-06-24T01:15:38.105300+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISXX2GXN","created_at":"2026-06-24T01:15:38.105300+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP","json":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP.json","graph_json":"https://pith.science/api/pith-number/ISXX2GXN2OLIEBWPVZ5YKQBJTP/graph.json","events_json":"https://pith.science/api/pith-number/ISXX2GXN2OLIEBWPVZ5YKQBJTP/events.json","paper":"https://pith.science/paper/ISXX2GXN"},"agent_actions":{"view_html":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP","download_json":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP.json","view_paper":"https://pith.science/paper/ISXX2GXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24648&json=true","fetch_graph":"https://pith.science/api/pith-number/ISXX2GXN2OLIEBWPVZ5YKQBJTP/graph.json","fetch_events":"https://pith.science/api/pith-number/ISXX2GXN2OLIEBWPVZ5YKQBJTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP/action/storage_attestation","attest_author":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP/action/author_attestation","sign_citation":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP/action/citation_signature","submit_replication":"https://pith.science/pith/ISXX2GXN2OLIEBWPVZ5YKQBJTP/action/replication_record"}},"created_at":"2026-06-24T01:15:38.105300+00:00","updated_at":"2026-06-24T01:15:38.105300+00:00"}