{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FC2NHRM7KIPBPZOGCBLZUNO6C3","short_pith_number":"pith:FC2NHRM7","schema_version":"1.0","canonical_sha256":"28b4d3c59f521e17e5c610579a35de16d436514d94be09f2e9f3dcd4d610480a","source":{"kind":"arxiv","id":"2404.07616","version":1},"attestation_state":"computed","paper":{"title":"Audio Dialogues: Dialogues dataset for audio and music understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Zhifeng Kong","submitted_at":"2024-04-11T10:08:34Z","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"},"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":"2404.07616","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T10:08:34Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"fa6e7d67e71292752f7d6b6c9b949b78d97d077f7c2b2e9f173c54395c84ed68","abstract_canon_sha256":"f90dfe6f243b1d91fa4d8c46149e88a42627df038d247ee0bceebbba9afdc6ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:55.395669Z","signature_b64":"Zrko44e4L3mCzd6rXXu0RinAgxUEPS5kf8/DFoLpJ1bOPsK/286OqtvTW45NpA4LGRwlKXyYYHq1U5291OpGAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28b4d3c59f521e17e5c610579a35de16d436514d94be09f2e9f3dcd4d610480a","last_reissued_at":"2026-07-05T08:06:55.395172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:55.395172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Audio Dialogues: Dialogues dataset for audio and music understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Arushi Goel, Bryan Catanzaro, Rafael Valle, Zhifeng Kong","submitted_at":"2024-04-11T10:08:34Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07616","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/2404.07616/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":"2404.07616","created_at":"2026-07-05T08:06:55.395232+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07616v1","created_at":"2026-07-05T08:06:55.395232+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07616","created_at":"2026-07-05T08:06:55.395232+00:00"},{"alias_kind":"pith_short_12","alias_value":"FC2NHRM7KIPB","created_at":"2026-07-05T08:06:55.395232+00:00"},{"alias_kind":"pith_short_16","alias_value":"FC2NHRM7KIPBPZOG","created_at":"2026-07-05T08:06:55.395232+00:00"},{"alias_kind":"pith_short_8","alias_value":"FC2NHRM7","created_at":"2026-07-05T08:06:55.395232+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05196","citing_title":"Unified Audio Intelligence Without Regressing on Text Intelligence","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2507.08128","citing_title":"Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3","json":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3.json","graph_json":"https://pith.science/api/pith-number/FC2NHRM7KIPBPZOGCBLZUNO6C3/graph.json","events_json":"https://pith.science/api/pith-number/FC2NHRM7KIPBPZOGCBLZUNO6C3/events.json","paper":"https://pith.science/paper/FC2NHRM7"},"agent_actions":{"view_html":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3","download_json":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3.json","view_paper":"https://pith.science/paper/FC2NHRM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07616&json=true","fetch_graph":"https://pith.science/api/pith-number/FC2NHRM7KIPBPZOGCBLZUNO6C3/graph.json","fetch_events":"https://pith.science/api/pith-number/FC2NHRM7KIPBPZOGCBLZUNO6C3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3/action/storage_attestation","attest_author":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3/action/author_attestation","sign_citation":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3/action/citation_signature","submit_replication":"https://pith.science/pith/FC2NHRM7KIPBPZOGCBLZUNO6C3/action/replication_record"}},"created_at":"2026-07-05T08:06:55.395232+00:00","updated_at":"2026-07-05T08:06:55.395232+00:00"}