{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6BBDULYJJSSWMYXNG453B2YCZS","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":"8f99774f3961136f5959f68bda3940be0308edbbe3ad975efc7f30fbcd367715","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T16:34:15Z","title_canon_sha256":"535f8fabb642c87ba248902f55c74bd502c08153d52ce98d7f06d4f37899f8a2"},"schema_version":"1.0","source":{"id":"2412.05167","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.05167","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"arxiv_version","alias_value":"2412.05167v2","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05167","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_12","alias_value":"6BBDULYJJSSW","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_16","alias_value":"6BBDULYJJSSWMYXN","created_at":"2026-07-05T11:43:59Z"},{"alias_kind":"pith_short_8","alias_value":"6BBDULYJ","created_at":"2026-07-05T11:43:59Z"}],"graph_snapshots":[{"event_id":"sha256:7edc67e9c9c1cd3ee737fb503d10f6bbe628a088d00a3ddde6349c7fe2869cb1","target":"graph","created_at":"2026-07-05T11:43:59Z","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/2412.05167/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Audio-Language Models (LALMs), such as GPT-4o, have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans. The potential of LALMs broadens their applicability across a wide range of practical scenarios supported by audio dialogues. However, given these advancements, a comprehensive benchmark to evaluate the performance of LALMs in the open-ended audio dialogue understanding remains absent currently. To address this gap, we propose an Audio Dialogue Understanding Benchmark (ADU-Bench), which consists of 4 benchmark datasets. They assess the open-ended","authors_text":"Jindong Gu, Ke Xu, Kuofeng Gao, Philip Torr, Shu-Tao Xia","cross_cats":["cs.CL","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T16:34:15Z","title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05167","kind":"arxiv","version":2},"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":"sha256:37442f7ec479b035b19dc2c1ea53fe1f66133a10367dae9e87d15eb65a91fd30","target":"record","created_at":"2026-07-05T11:43:59Z","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":"8f99774f3961136f5959f68bda3940be0308edbbe3ad975efc7f30fbcd367715","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T16:34:15Z","title_canon_sha256":"535f8fabb642c87ba248902f55c74bd502c08153d52ce98d7f06d4f37899f8a2"},"schema_version":"1.0","source":{"id":"2412.05167","kind":"arxiv","version":2}},"canonical_sha256":"f0423a2f094ca56662ed373bb0eb02cc97e533e6e050b175b2e0fe5b34427141","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f0423a2f094ca56662ed373bb0eb02cc97e533e6e050b175b2e0fe5b34427141","first_computed_at":"2026-07-05T11:43:59.449347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:59.449347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Po7Racrv8EgyryMEwCqfVcil/WzhkhUPPq8W7bTbQuKF6N4atnrOaTRZwH/J4oH5H5iP8jiGPvD1vj2Mofu9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:59.449934Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.05167","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37442f7ec479b035b19dc2c1ea53fe1f66133a10367dae9e87d15eb65a91fd30","sha256:7edc67e9c9c1cd3ee737fb503d10f6bbe628a088d00a3ddde6349c7fe2869cb1"],"state_sha256":"a56a38445ea62868ecd00c1d1704fc76081c1567464d581ad35e8a5d50a0c975"}