{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CGLNWCYOTLN6BYHLVH3H7OMHV5","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":"dc390d3a880ab13d05aafc85e71df929a1d4a06f6859d2b18ad20ecc89113711","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-20T04:06:07Z","title_canon_sha256":"8d944196f2f7e4c8d61826212b34e3289b4adde81190b0362910eb44fb19837a"},"schema_version":"1.0","source":{"id":"2602.18527","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.18527","created_at":"2026-05-26T01:03:25Z"},{"alias_kind":"arxiv_version","alias_value":"2602.18527v2","created_at":"2026-05-26T01:03:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18527","created_at":"2026-05-26T01:03:25Z"},{"alias_kind":"pith_short_12","alias_value":"CGLNWCYOTLN6","created_at":"2026-05-26T01:03:25Z"},{"alias_kind":"pith_short_16","alias_value":"CGLNWCYOTLN6BYHL","created_at":"2026-05-26T01:03:25Z"},{"alias_kind":"pith_short_8","alias_value":"CGLNWCYO","created_at":"2026-05-26T01:03:25Z"}],"graph_snapshots":[{"event_id":"sha256:700a2857f7b6574bc113d6c700c5932f9c140ededd80725f99a6a9d1cd185695","target":"graph","created_at":"2026-05-26T01:03:25Z","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/2602.18527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current audio-visual large language models (AV-LLMs) are predominantly restricted to 2D perception, relying on RGB video and monaural audio. This design choice introduces a fundamental dimensionality mismatch that precludes reliable source localization and spatial reasoning in complex 3D environments. We address this limitation by presenting JAEGER, a framework that extends AV-LLMs to 3D space, to enable joint spatial grounding and reasoning through the integration of RGB-D observations and multi-channel first-order ambisonics. A core contribution of our work is the neural intensity vector (Ne","authors_text":"Changli Tang, Chao Zhang, Lei Ke, Tianzi Wang, Yiwen Shao, Youjun Chen, Yuxin Wang, Zengrui Jin, Zhan Liu, Zhiyuan Zhu","cross_cats":["cs.AI","cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-20T04:06:07Z","title":"JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18527","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":"sha256:8660a033f3ea02cac7e51fca540d187032868446df537c04a6412fe951f07a11","target":"record","created_at":"2026-05-26T01:03:25Z","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":"dc390d3a880ab13d05aafc85e71df929a1d4a06f6859d2b18ad20ecc89113711","cross_cats_sorted":["cs.AI","cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-20T04:06:07Z","title_canon_sha256":"8d944196f2f7e4c8d61826212b34e3289b4adde81190b0362910eb44fb19837a"},"schema_version":"1.0","source":{"id":"2602.18527","kind":"arxiv","version":2}},"canonical_sha256":"1196db0b0e9adbe0e0eba9f67fb987af75f65023ff1cd83d117b21d902f1bc03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1196db0b0e9adbe0e0eba9f67fb987af75f65023ff1cd83d117b21d902f1bc03","first_computed_at":"2026-05-26T01:03:25.763193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:03:25.763193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NYQ5TCV+nCI2n9eBE1mMk2wRKtxLZlhsg9x4hJ6rm790Xn160FEIxIsxnB5TxZ0rApJLl0PaShgizOQS5Di0BQ==","signature_status":"signed_v1","signed_at":"2026-05-26T01:03:25.764158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.18527","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8660a033f3ea02cac7e51fca540d187032868446df537c04a6412fe951f07a11","sha256:700a2857f7b6574bc113d6c700c5932f9c140ededd80725f99a6a9d1cd185695"],"state_sha256":"8e9e9ef603b76e65515963d066ef9e8d04d858fd02769794dc28760cabd2d7bd"}