{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6BBDULYJJSSWMYXNG453B2YCZS","short_pith_number":"pith:6BBDULYJ","canonical_record":{"source":{"id":"2412.05167","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T16:34:15Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"535f8fabb642c87ba248902f55c74bd502c08153d52ce98d7f06d4f37899f8a2","abstract_canon_sha256":"8f99774f3961136f5959f68bda3940be0308edbbe3ad975efc7f30fbcd367715"},"schema_version":"1.0"},"canonical_sha256":"f0423a2f094ca56662ed373bb0eb02cc97e533e6e050b175b2e0fe5b34427141","source":{"kind":"arxiv","id":"2412.05167","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6BBDULYJJSSWMYXNG453B2YCZS","target":"record","payload":{"canonical_record":{"source":{"id":"2412.05167","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T16:34:15Z","cross_cats_sorted":["cs.CL","cs.SD","eess.AS"],"title_canon_sha256":"535f8fabb642c87ba248902f55c74bd502c08153d52ce98d7f06d4f37899f8a2","abstract_canon_sha256":"8f99774f3961136f5959f68bda3940be0308edbbe3ad975efc7f30fbcd367715"},"schema_version":"1.0"},"canonical_sha256":"f0423a2f094ca56662ed373bb0eb02cc97e533e6e050b175b2e0fe5b34427141","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:59.449934Z","signature_b64":"Po7Racrv8EgyryMEwCqfVcil/WzhkhUPPq8W7bTbQuKF6N4atnrOaTRZwH/J4oH5H5iP8jiGPvD1vj2Mofu9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0423a2f094ca56662ed373bb0eb02cc97e533e6e050b175b2e0fe5b34427141","last_reissued_at":"2026-07-05T11:43:59.449347Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:59.449347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.05167","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9w1RuzToCTYqg0xlL20F4jjRsrH+gkBzRTnYk+pD8kIVjJN/z5OyMOQW06ChmTQ+hWzlbqOFA+hI3PXFqOqJDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:53:56.413409Z"},"content_sha256":"37442f7ec479b035b19dc2c1ea53fe1f66133a10367dae9e87d15eb65a91fd30","schema_version":"1.0","event_id":"sha256:37442f7ec479b035b19dc2c1ea53fe1f66133a10367dae9e87d15eb65a91fd30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6BBDULYJJSSWMYXNG453B2YCZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD","eess.AS"],"primary_cat":"cs.AI","authors_text":"Jindong Gu, Ke Xu, Kuofeng Gao, Philip Torr, Shu-Tao Xia","submitted_at":"2024-12-06T16:34:15Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05167","kind":"arxiv","version":2},"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/2412.05167/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:43:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SMyphfrtYHQqyO6nPnQ3xANfvBOw0xLWYww+bmqbTDo7CfJv7HH5jwvGkoN4xdyNWaBZYTMBDjrCa/+2ahAEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T17:53:56.413786Z"},"content_sha256":"7edc67e9c9c1cd3ee737fb503d10f6bbe628a088d00a3ddde6349c7fe2869cb1","schema_version":"1.0","event_id":"sha256:7edc67e9c9c1cd3ee737fb503d10f6bbe628a088d00a3ddde6349c7fe2869cb1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6BBDULYJJSSWMYXNG453B2YCZS/bundle.json","state_url":"https://pith.science/pith/6BBDULYJJSSWMYXNG453B2YCZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6BBDULYJJSSWMYXNG453B2YCZS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-23T17:53:56Z","links":{"resolver":"https://pith.science/pith/6BBDULYJJSSWMYXNG453B2YCZS","bundle":"https://pith.science/pith/6BBDULYJJSSWMYXNG453B2YCZS/bundle.json","state":"https://pith.science/pith/6BBDULYJJSSWMYXNG453B2YCZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6BBDULYJJSSWMYXNG453B2YCZS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vcwqNTdLOE/SPBKuvkqKpV+ft9NN6n5lnOdmhgzbHwLeyrGnawDLtEW3SCtYJapclNutt7iMZxCqBQhiDxwAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T17:53:56.416518Z","bundle_sha256":"829e40228260a511719413d7465cf209956ecba7b6cd6a1549d600474b9fe4ac"}}