{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UV5AU5KYYPI2EU4U3LG2LEDFFM","short_pith_number":"pith:UV5AU5KY","schema_version":"1.0","canonical_sha256":"a57a0a7558c3d1a25394dacda590652b0aff12c733437fa62a1cf851a9312da9","source":{"kind":"arxiv","id":"2402.01591","version":3},"attestation_state":"computed","paper":{"title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Harwath, Eunsol Choi, Puyuan Peng, Xie Chen, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-02-02T17:34:53Z","abstract_excerpt":"Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene analysis model with the natural language reasoning capabilities of a large language model (LLM) to replicate this innate ability. To address the lack of existing datasets of in-the-wild spatial sounds, we synthesized a binaural audio dataset using AudioSet and SoundSpaces 2.0. Next, we developed SpatialSoundQA, a spatial sound-based question-answering dataset, o"},"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":"2402.01591","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-02T17:34:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"4aa0d483a20a231e4ccdcd4a1589c9eaeeab8b627a8df08256c6c488b8f25b18","abstract_canon_sha256":"cbe97b5d20b683cbc91ce09aad4e4b58416d4fd2bd86e620b4a78bf02be86d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:35.672841Z","signature_b64":"TYqgQ9+IkoJEy1697ZfF41qxs8G92jPruboC9rB+DGHR/EmecPtgW3TflTab2uB2CgBuyV9vRSowifRH3xOlAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57a0a7558c3d1a25394dacda590652b0aff12c733437fa62a1cf851a9312da9","last_reissued_at":"2026-07-05T11:04:35.672346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:35.672346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"David Harwath, Eunsol Choi, Puyuan Peng, Xie Chen, Zhisheng Zheng, Ziyang Ma","submitted_at":"2024-02-02T17:34:53Z","abstract_excerpt":"Spatial sound reasoning is a fundamental human skill, enabling us to navigate and interpret our surroundings based on sound. In this paper we present BAT, which combines the spatial sound perception ability of a binaural acoustic scene analysis model with the natural language reasoning capabilities of a large language model (LLM) to replicate this innate ability. To address the lack of existing datasets of in-the-wild spatial sounds, we synthesized a binaural audio dataset using AudioSet and SoundSpaces 2.0. Next, we developed SpatialSoundQA, a spatial sound-based question-answering dataset, o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01591","kind":"arxiv","version":3},"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/2402.01591/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":"2402.01591","created_at":"2026-07-05T11:04:35.672407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01591v3","created_at":"2026-07-05T11:04:35.672407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01591","created_at":"2026-07-05T11:04:35.672407+00:00"},{"alias_kind":"pith_short_12","alias_value":"UV5AU5KYYPI2","created_at":"2026-07-05T11:04:35.672407+00:00"},{"alias_kind":"pith_short_16","alias_value":"UV5AU5KYYPI2EU4U","created_at":"2026-07-05T11:04:35.672407+00:00"},{"alias_kind":"pith_short_8","alias_value":"UV5AU5KY","created_at":"2026-07-05T11:04:35.672407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05544","citing_title":"Probing Spatial Structure in Pretrained Audio Representations","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05459","citing_title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02954","citing_title":"The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM","json":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM.json","graph_json":"https://pith.science/api/pith-number/UV5AU5KYYPI2EU4U3LG2LEDFFM/graph.json","events_json":"https://pith.science/api/pith-number/UV5AU5KYYPI2EU4U3LG2LEDFFM/events.json","paper":"https://pith.science/paper/UV5AU5KY"},"agent_actions":{"view_html":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM","download_json":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM.json","view_paper":"https://pith.science/paper/UV5AU5KY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01591&json=true","fetch_graph":"https://pith.science/api/pith-number/UV5AU5KYYPI2EU4U3LG2LEDFFM/graph.json","fetch_events":"https://pith.science/api/pith-number/UV5AU5KYYPI2EU4U3LG2LEDFFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM/action/storage_attestation","attest_author":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM/action/author_attestation","sign_citation":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM/action/citation_signature","submit_replication":"https://pith.science/pith/UV5AU5KYYPI2EU4U3LG2LEDFFM/action/replication_record"}},"created_at":"2026-07-05T11:04:35.672407+00:00","updated_at":"2026-07-05T11:04:35.672407+00:00"}