{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GL4NGUGEKMZANHZHGUW4KNWX2M","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":"f35b9709b50edd1c27ea3e54e393092dce0bf15c118f3581b47c50f5742ebedb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T06:34:21Z","title_canon_sha256":"9886a2953d74a07200af07261a0e5a4974479626d003aafb66deb8bd7932f5e3"},"schema_version":"1.0","source":{"id":"2406.07914","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07914","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07914v2","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07914","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_12","alias_value":"GL4NGUGEKMZA","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_16","alias_value":"GL4NGUGEKMZANHZH","created_at":"2026-07-05T08:31:52Z"},{"alias_kind":"pith_short_8","alias_value":"GL4NGUGE","created_at":"2026-07-05T08:31:52Z"}],"graph_snapshots":[{"event_id":"sha256:57563b372e8006ffed24206579bc72bc7b5c60af1bf30e4d25ab221e4a5bea3b","target":"graph","created_at":"2026-07-05T08:31:52Z","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/2406.07914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores enabling large language models (LLMs) to understand spatial information from multichannel audio, a skill currently lacking in auditory LLMs. By leveraging LLMs' advanced cognitive and inferential abilities, the aim is to enhance understanding of 3D environments via audio. We study 3 spatial audio tasks: sound source localization (SSL), far-field speech recognition (FSR), and localisation-informed speech extraction (LSE), achieving notable progress in each task. For SSL, our approach achieves an MAE of $2.70^{\\circ}$ on the Spatial LibriSpeech dataset, substantially surpassi","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jun Zhang, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Yuxuan Wang, Zejun Ma","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T06:34:21Z","title":"Can Large Language Models Understand Spatial Audio?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07914","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":"sha256:8d56d7629193352e2a42048c34ecbbef2909f2371474527a531c0a977e80f7df","target":"record","created_at":"2026-07-05T08:31:52Z","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":"f35b9709b50edd1c27ea3e54e393092dce0bf15c118f3581b47c50f5742ebedb","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T06:34:21Z","title_canon_sha256":"9886a2953d74a07200af07261a0e5a4974479626d003aafb66deb8bd7932f5e3"},"schema_version":"1.0","source":{"id":"2406.07914","kind":"arxiv","version":2}},"canonical_sha256":"32f8d350c45332069f27352dc536d7d302d8a3d6cc4cc28795af8d16c3b8ce22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"32f8d350c45332069f27352dc536d7d302d8a3d6cc4cc28795af8d16c3b8ce22","first_computed_at":"2026-07-05T08:31:52.958388Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:31:52.958388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vmt/kn/etemGAlCbwPylDBg0FNkda3FWQm1TGA34zaaYxsVdLG5D2WXOhprjSFWMB/e6JE+J5dQ8dZXhNjwFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:31:52.958870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07914","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d56d7629193352e2a42048c34ecbbef2909f2371474527a531c0a977e80f7df","sha256:57563b372e8006ffed24206579bc72bc7b5c60af1bf30e4d25ab221e4a5bea3b"],"state_sha256":"c2e00f84bb38ef33906505a41d8405a212f80be1fe14ef4bceebbe254893501b"}