{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UV5AU5KYYPI2EU4U3LG2LEDFFM","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":"cbe97b5d20b683cbc91ce09aad4e4b58416d4fd2bd86e620b4a78bf02be86d3e","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-02T17:34:53Z","title_canon_sha256":"4aa0d483a20a231e4ccdcd4a1589c9eaeeab8b627a8df08256c6c488b8f25b18"},"schema_version":"1.0","source":{"id":"2402.01591","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01591","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01591v3","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01591","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_12","alias_value":"UV5AU5KYYPI2","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_16","alias_value":"UV5AU5KYYPI2EU4U","created_at":"2026-07-05T11:04:35Z"},{"alias_kind":"pith_short_8","alias_value":"UV5AU5KY","created_at":"2026-07-05T11:04:35Z"}],"graph_snapshots":[{"event_id":"sha256:625441efe41efe69ed49319b567a1d7894d3b1635f5c4d67c883c8a82faaf43d","target":"graph","created_at":"2026-07-05T11:04:35Z","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/2402.01591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Harwath, Eunsol Choi, Puyuan Peng, Xie Chen, Zhisheng Zheng, Ziyang Ma","cross_cats":["cs.AI","cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-02T17:34:53Z","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01591","kind":"arxiv","version":3},"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:bb85d1be70427f83c6c78dc1d835ff2b7cdea9515cd01292c2eb2dc330d9d8cc","target":"record","created_at":"2026-07-05T11:04:35Z","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":"cbe97b5d20b683cbc91ce09aad4e4b58416d4fd2bd86e620b4a78bf02be86d3e","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-02T17:34:53Z","title_canon_sha256":"4aa0d483a20a231e4ccdcd4a1589c9eaeeab8b627a8df08256c6c488b8f25b18"},"schema_version":"1.0","source":{"id":"2402.01591","kind":"arxiv","version":3}},"canonical_sha256":"a57a0a7558c3d1a25394dacda590652b0aff12c733437fa62a1cf851a9312da9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a57a0a7558c3d1a25394dacda590652b0aff12c733437fa62a1cf851a9312da9","first_computed_at":"2026-07-05T11:04:35.672346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:35.672346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TYqgQ9+IkoJEy1697ZfF41qxs8G92jPruboC9rB+DGHR/EmecPtgW3TflTab2uB2CgBuyV9vRSowifRH3xOlAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:35.672841Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01591","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb85d1be70427f83c6c78dc1d835ff2b7cdea9515cd01292c2eb2dc330d9d8cc","sha256:625441efe41efe69ed49319b567a1d7894d3b1635f5c4d67c883c8a82faaf43d"],"state_sha256":"d318ddefd024340ef45c6c6ef6371ff7eb034e3ece024ff5fe7f06a1ce7147fd"}