{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:R3GGZSR6GNL3CNPAK6DHFU42TP","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":"8fe42abf0290d3f14a47706c610816608aaff6822acee1574499fd1c0de9c0f1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T00:39:18Z","title_canon_sha256":"9043565358d1fed5921ba12d834343089d58f833fa5c20bac5e58cd65e69b048"},"schema_version":"1.0","source":{"id":"2507.12705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12705","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12705v1","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12705","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_12","alias_value":"R3GGZSR6GNL3","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_16","alias_value":"R3GGZSR6GNL3CNPA","created_at":"2026-07-05T11:38:37Z"},{"alias_kind":"pith_short_8","alias_value":"R3GGZSR6","created_at":"2026-07-05T11:38:37Z"}],"graph_snapshots":[{"event_id":"sha256:7c40e3987059896d5a0991509b46a289a64ed0b1e1fbd2963d20bc76f8e572ac","target":"graph","created_at":"2026-07-05T11:38:37Z","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/2507.12705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Ali Sartaz Khan, Diyi Yang, Kunat Pipatanakul, Michael J. Ryan, Potsawee Manakul, Warit Sirichotedumrong, William Held, Woody Haosheng Gan","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T00:39:18Z","title":"AudioJudge: Understanding What Works in Large Audio Model Based Speech Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12705","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:f0a13faa4d97e9b2ac4bb9023eef5b57329c99487700ab1673e5c2164ae0e6f6","target":"record","created_at":"2026-07-05T11:38:37Z","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":"8fe42abf0290d3f14a47706c610816608aaff6822acee1574499fd1c0de9c0f1","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T00:39:18Z","title_canon_sha256":"9043565358d1fed5921ba12d834343089d58f833fa5c20bac5e58cd65e69b048"},"schema_version":"1.0","source":{"id":"2507.12705","kind":"arxiv","version":1}},"canonical_sha256":"8ecc6cca3e3357b135e0578672d39a9be0592d32b74d9f8ed2ced4d2ffa69117","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ecc6cca3e3357b135e0578672d39a9be0592d32b74d9f8ed2ced4d2ffa69117","first_computed_at":"2026-07-05T11:38:37.608805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:37.608805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h74lkC4XmsemX8YvktTDQfsYC8YmkmH4oLxMSTqMJW931ltVZ44rH6j905o/iSIfsyOmSIMoGhGlaBAfYbMGBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:37.609293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f0a13faa4d97e9b2ac4bb9023eef5b57329c99487700ab1673e5c2164ae0e6f6","sha256:7c40e3987059896d5a0991509b46a289a64ed0b1e1fbd2963d20bc76f8e572ac"],"state_sha256":"54e06fd0d40511b218e57e836037ea48e7ac2a91ad19a3ed65d68206ad7f1f79"}