{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GL4NGUGEKMZANHZHGUW4KNWX2M","short_pith_number":"pith:GL4NGUGE","canonical_record":{"source":{"id":"2406.07914","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T06:34:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9886a2953d74a07200af07261a0e5a4974479626d003aafb66deb8bd7932f5e3","abstract_canon_sha256":"f35b9709b50edd1c27ea3e54e393092dce0bf15c118f3581b47c50f5742ebedb"},"schema_version":"1.0"},"canonical_sha256":"32f8d350c45332069f27352dc536d7d302d8a3d6cc4cc28795af8d16c3b8ce22","source":{"kind":"arxiv","id":"2406.07914","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GL4NGUGEKMZANHZHGUW4KNWX2M","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07914","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-06-12T06:34:21Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"9886a2953d74a07200af07261a0e5a4974479626d003aafb66deb8bd7932f5e3","abstract_canon_sha256":"f35b9709b50edd1c27ea3e54e393092dce0bf15c118f3581b47c50f5742ebedb"},"schema_version":"1.0"},"canonical_sha256":"32f8d350c45332069f27352dc536d7d302d8a3d6cc4cc28795af8d16c3b8ce22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:52.958870Z","signature_b64":"Vmt/kn/etemGAlCbwPylDBg0FNkda3FWQm1TGA34zaaYxsVdLG5D2WXOhprjSFWMB/e6JE+J5dQ8dZXhNjwFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32f8d350c45332069f27352dc536d7d302d8a3d6cc4cc28795af8d16c3b8ce22","last_reissued_at":"2026-07-05T08:31:52.958388Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:52.958388Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07914","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1zV6he3hoiIDH9uieA6x1WcDHik9tH7i5fzpwKvLq5bHTd+cN1l1uFfbnmXLgUJtB03H5fd33fmBZCbeeX90DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:54.159725Z"},"content_sha256":"8d56d7629193352e2a42048c34ecbbef2909f2371474527a531c0a977e80f7df","schema_version":"1.0","event_id":"sha256:8d56d7629193352e2a42048c34ecbbef2909f2371474527a531c0a977e80f7df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GL4NGUGEKMZANHZHGUW4KNWX2M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Large Language Models Understand Spatial Audio?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Changli Tang, Chao Zhang, Guangzhi Sun, Jun Zhang, Lu Lu, Tian Tan, Wei Li, Wenyi Yu, Xianzhao Chen, Yuxuan Wang, Zejun Ma","submitted_at":"2024-06-12T06:34:21Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07914","kind":"arxiv","version":2},"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/2406.07914/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:31:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3lW9Pdjtj2iMQteKTZV/dHE/5y1iPIfKQQIy2C/AN7VLDJ6WuJU+pVRwlO2WDxDqQDHi/S/MIQSC7mxAn2LJAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:51:54.160602Z"},"content_sha256":"57563b372e8006ffed24206579bc72bc7b5c60af1bf30e4d25ab221e4a5bea3b","schema_version":"1.0","event_id":"sha256:57563b372e8006ffed24206579bc72bc7b5c60af1bf30e4d25ab221e4a5bea3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/bundle.json","state_url":"https://pith.science/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:51:54Z","links":{"resolver":"https://pith.science/pith/GL4NGUGEKMZANHZHGUW4KNWX2M","bundle":"https://pith.science/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/bundle.json","state":"https://pith.science/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GL4NGUGEKMZANHZHGUW4KNWX2M/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5cul6AFjyMUSrvKa4U7cTpy0J1MWSRhbiT1JMkgRPNPD85BWSmZTrHInUiOt0bZHemzkPw3/XvGf5qPjLU/IDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:51:54.168001Z","bundle_sha256":"e583b1d798a674ea5c98449004b198579967845d5e687a31d0f83e756b91129d"}}