{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FC2NHRM7KIPBPZOGCBLZUNO6C3","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":"f90dfe6f243b1d91fa4d8c46149e88a42627df038d247ee0bceebbba9afdc6ca","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T10:08:34Z","title_canon_sha256":"fa6e7d67e71292752f7d6b6c9b949b78d97d077f7c2b2e9f173c54395c84ed68"},"schema_version":"1.0","source":{"id":"2404.07616","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07616","created_at":"2026-07-05T08:06:55Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07616v1","created_at":"2026-07-05T08:06:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07616","created_at":"2026-07-05T08:06:55Z"},{"alias_kind":"pith_short_12","alias_value":"FC2NHRM7KIPB","created_at":"2026-07-05T08:06:55Z"},{"alias_kind":"pith_short_16","alias_value":"FC2NHRM7KIPBPZOG","created_at":"2026-07-05T08:06:55Z"},{"alias_kind":"pith_short_8","alias_value":"FC2NHRM7","created_at":"2026-07-05T08:06:55Z"}],"graph_snapshots":[{"event_id":"sha256:e60649de73cf56904e6e961a30df833889fe87ea7ddac0c1394dd4baacb3ba8c","target":"graph","created_at":"2026-07-05T08:06:55Z","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/2404.07616/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To address this gap, we introduce Audio Dialogues: a multi-turn dialogue dataset containing 163.8k samples for general audio sounds and music. In addition to dialogues, Audio Dialogues also has question-answer pairs to understand and compare multiple input audios together. Audio Dialogues leverages a prompting-based approach and caption annotations from existi","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Zhifeng Kong","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T10:08:34Z","title":"Audio Dialogues: Dialogues dataset for audio and music understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07616","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:d5d936b5d078202a687bc5d4fa91bdfb44557139a28a4600a2b76711775f6b0f","target":"record","created_at":"2026-07-05T08:06:55Z","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":"f90dfe6f243b1d91fa4d8c46149e88a42627df038d247ee0bceebbba9afdc6ca","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T10:08:34Z","title_canon_sha256":"fa6e7d67e71292752f7d6b6c9b949b78d97d077f7c2b2e9f173c54395c84ed68"},"schema_version":"1.0","source":{"id":"2404.07616","kind":"arxiv","version":1}},"canonical_sha256":"28b4d3c59f521e17e5c610579a35de16d436514d94be09f2e9f3dcd4d610480a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"28b4d3c59f521e17e5c610579a35de16d436514d94be09f2e9f3dcd4d610480a","first_computed_at":"2026-07-05T08:06:55.395172Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:06:55.395172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zrko44e4L3mCzd6rXXu0RinAgxUEPS5kf8/DFoLpJ1bOPsK/286OqtvTW45NpA4LGRwlKXyYYHq1U5291OpGAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:06:55.395669Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07616","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5d936b5d078202a687bc5d4fa91bdfb44557139a28a4600a2b76711775f6b0f","sha256:e60649de73cf56904e6e961a30df833889fe87ea7ddac0c1394dd4baacb3ba8c"],"state_sha256":"c653db53404f0f1889f73af53f47481628f6d7ade33092d404a7ad73e7a9399b"}