{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GTRMRQCBZUIWC766PD5ZSMBSTM","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":"b7aa8f5baa36ec0d53eb0c06403ea00f7ca98f1f8a9f0b2e87384a8abf668498","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T11:50:06Z","title_canon_sha256":"4c5cb5120bcc7574c34d16f06acb5635dece3261492140bbf6792a245d02dcc1"},"schema_version":"1.0","source":{"id":"2606.10738","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.10738","created_at":"2026-06-10T01:10:37Z"},{"alias_kind":"arxiv_version","alias_value":"2606.10738v1","created_at":"2026-06-10T01:10:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10738","created_at":"2026-06-10T01:10:37Z"},{"alias_kind":"pith_short_12","alias_value":"GTRMRQCBZUIW","created_at":"2026-06-10T01:10:37Z"},{"alias_kind":"pith_short_16","alias_value":"GTRMRQCBZUIWC766","created_at":"2026-06-10T01:10:37Z"},{"alias_kind":"pith_short_8","alias_value":"GTRMRQCB","created_at":"2026-06-10T01:10:37Z"}],"graph_snapshots":[{"event_id":"sha256:b5949ff27fff1861baa98056bb62d13cebf4e489e94db90c24672d31f8d90e00","target":"graph","created_at":"2026-06-10T01:10:37Z","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/2606.10738/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent multimodal large language models mainly process audio as monaural signals, thereby discarding the spatial cues contained in spatial audio for sound localization, spatial relation reasoning, and spatial scene understanding. We propose Spatial-Omni, a lightweight method that implements SO-Encoder to inject First-Order Ambisonics (FOA) spatial audio into existing Omni LLMs as an independent modality, without modifying their original audio encoders. SO-Encoder provides spatial tokens with limited additional context cost and improves spatial audio understanding through efficient staged train","authors_text":"Changhao Pan, Chengkuan Zeng, Houhua Zhang, Liefeng Bo, Rui Yang, Steve Yves, Wei Liu, Wenbo Cheng, Wenxiang Guo, Yiwen Shao, Yixuan Chen, Yunxi Liu, Yuxiang Wang, Yu Zhang, Zhiyuan Zhu, Zhou Zhao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T11:50:06Z","title":"Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA Encoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10738","kind":"arxiv","version":1},"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":"sha256:305c59ee2838b422cb61a8035f1425dac3f6141e66642aa16bbbce00b3047229","target":"record","created_at":"2026-06-10T01:10:37Z","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":"b7aa8f5baa36ec0d53eb0c06403ea00f7ca98f1f8a9f0b2e87384a8abf668498","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2026-06-09T11:50:06Z","title_canon_sha256":"4c5cb5120bcc7574c34d16f06acb5635dece3261492140bbf6792a245d02dcc1"},"schema_version":"1.0","source":{"id":"2606.10738","kind":"arxiv","version":1}},"canonical_sha256":"34e2c8c041cd11617fde78fb9930329b23344d15d95b6b850191191e3f0db806","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34e2c8c041cd11617fde78fb9930329b23344d15d95b6b850191191e3f0db806","first_computed_at":"2026-06-10T01:10:37.590207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:10:37.590207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hEe3W8zvwvr8RfkvsZofiVzPeQlS6hujvLiUMlzrVoMu6YduygfvvHStAlzxE3syNlvH3ZeZA+F/P6lFVY4gBg==","signature_status":"signed_v1","signed_at":"2026-06-10T01:10:37.591061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.10738","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:305c59ee2838b422cb61a8035f1425dac3f6141e66642aa16bbbce00b3047229","sha256:b5949ff27fff1861baa98056bb62d13cebf4e489e94db90c24672d31f8d90e00"],"state_sha256":"1f324d1cf56c78f9bac60f5b4772e57abf8411879e0421128c73e27489d937de"}