{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:R3GGZSR6GNL3CNPAK6DHFU42TP","short_pith_number":"pith:R3GGZSR6","schema_version":"1.0","canonical_sha256":"8ecc6cca3e3357b135e0578672d39a9be0592d32b74d9f8ed2ced4d2ffa69117","source":{"kind":"arxiv","id":"2507.12705","version":1},"attestation_state":"computed","paper":{"title":"AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ali Sartaz Khan, Diyi Yang, Kunat Pipatanakul, Michael J. Ryan, Potsawee Manakul, Warit Sirichotedumrong, William Held, Woody Haosheng Gan","submitted_at":"2025-07-17T00:39:18Z","abstract_excerpt":"Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor correlation between automatic evaluation methods and human preferences. This work presents a systematic study of Large Audio Model (LAM) as a Judge, AudioJudge, investigating whether it can provide a unified evaluation framework that addresses both challenges. We systematically explore AudioJudge across audio characteristic detection tasks, including pronunciation, speaking rate, speaker identification and speech quality,"},"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":"2507.12705","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T00:39:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"9043565358d1fed5921ba12d834343089d58f833fa5c20bac5e58cd65e69b048","abstract_canon_sha256":"8fe42abf0290d3f14a47706c610816608aaff6822acee1574499fd1c0de9c0f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:37.609293Z","signature_b64":"h74lkC4XmsemX8YvktTDQfsYC8YmkmH4oLxMSTqMJW931ltVZ44rH6j905o/iSIfsyOmSIMoGhGlaBAfYbMGBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ecc6cca3e3357b135e0578672d39a9be0592d32b74d9f8ed2ced4d2ffa69117","last_reissued_at":"2026-07-05T11:38:37.608805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:37.608805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ali Sartaz Khan, Diyi Yang, Kunat Pipatanakul, Michael J. Ryan, Potsawee Manakul, Warit Sirichotedumrong, William Held, Woody Haosheng Gan","submitted_at":"2025-07-17T00:39:18Z","abstract_excerpt":"Current speech evaluation suffers from two critical limitations: the need and difficulty of designing specialized systems targeting individual audio characteristics, and poor correlation between automatic evaluation methods and human preferences. This work presents a systematic study of Large Audio Model (LAM) as a Judge, AudioJudge, investigating whether it can provide a unified evaluation framework that addresses both challenges. We systematically explore AudioJudge across audio characteristic detection tasks, including pronunciation, speaking rate, speaker identification and speech quality,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12705","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/2507.12705/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":"2507.12705","created_at":"2026-07-05T11:38:37.608859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.12705v1","created_at":"2026-07-05T11:38:37.608859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12705","created_at":"2026-07-05T11:38:37.608859+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3GGZSR6GNL3","created_at":"2026-07-05T11:38:37.608859+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3GGZSR6GNL3CNPA","created_at":"2026-07-05T11:38:37.608859+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3GGZSR6","created_at":"2026-07-05T11:38:37.608859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07985","citing_title":"A Reliability Assessment of LALM Audio Judges for Full-Duplex Voice Agents","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24648","citing_title":"ParaPairAudioBench: Paralinguistic Pairwise Audio Benchmark for LALM-as-a-Judge","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22225","citing_title":"TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis","ref_index":19,"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":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP","json":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP.json","graph_json":"https://pith.science/api/pith-number/R3GGZSR6GNL3CNPAK6DHFU42TP/graph.json","events_json":"https://pith.science/api/pith-number/R3GGZSR6GNL3CNPAK6DHFU42TP/events.json","paper":"https://pith.science/paper/R3GGZSR6"},"agent_actions":{"view_html":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP","download_json":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP.json","view_paper":"https://pith.science/paper/R3GGZSR6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.12705&json=true","fetch_graph":"https://pith.science/api/pith-number/R3GGZSR6GNL3CNPAK6DHFU42TP/graph.json","fetch_events":"https://pith.science/api/pith-number/R3GGZSR6GNL3CNPAK6DHFU42TP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP/action/storage_attestation","attest_author":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP/action/author_attestation","sign_citation":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP/action/citation_signature","submit_replication":"https://pith.science/pith/R3GGZSR6GNL3CNPAK6DHFU42TP/action/replication_record"}},"created_at":"2026-07-05T11:38:37.608859+00:00","updated_at":"2026-07-05T11:38:37.608859+00:00"}