{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CGLNWCYOTLN6BYHLVH3H7OMHV5","short_pith_number":"pith:CGLNWCYO","schema_version":"1.0","canonical_sha256":"1196db0b0e9adbe0e0eba9f67fb987af75f65023ff1cd83d117b21d902f1bc03","source":{"kind":"arxiv","id":"2602.18527","version":2},"attestation_state":"computed","paper":{"title":"JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CV","authors_text":"Changli Tang, Chao Zhang, Lei Ke, Tianzi Wang, Yiwen Shao, Youjun Chen, Yuxin Wang, Zengrui Jin, Zhan Liu, Zhiyuan Zhu","submitted_at":"2026-02-20T04:06:07Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2602.18527","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-20T04:06:07Z","cross_cats_sorted":["cs.AI","cs.SD"],"title_canon_sha256":"8d944196f2f7e4c8d61826212b34e3289b4adde81190b0362910eb44fb19837a","abstract_canon_sha256":"dc390d3a880ab13d05aafc85e71df929a1d4a06f6859d2b18ad20ecc89113711"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:25.764158Z","signature_b64":"NYQ5TCV+nCI2n9eBE1mMk2wRKtxLZlhsg9x4hJ6rm790Xn160FEIxIsxnB5TxZ0rApJLl0PaShgizOQS5Di0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1196db0b0e9adbe0e0eba9f67fb987af75f65023ff1cd83d117b21d902f1bc03","last_reissued_at":"2026-05-26T01:03:25.763193Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:25.763193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"JAEGER: Joint 3D Audio-Visual Grounding and Reasoning in Simulated Physical Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SD"],"primary_cat":"cs.CV","authors_text":"Changli Tang, Chao Zhang, Lei Ke, Tianzi Wang, Yiwen Shao, Youjun Chen, Yuxin Wang, Zengrui Jin, Zhan Liu, Zhiyuan Zhu","submitted_at":"2026-02-20T04:06:07Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.18527","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/2602.18527/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2602.18527","created_at":"2026-05-26T01:03:25.763333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.18527v2","created_at":"2026-05-26T01:03:25.763333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.18527","created_at":"2026-05-26T01:03:25.763333+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGLNWCYOTLN6","created_at":"2026-05-26T01:03:25.763333+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGLNWCYOTLN6BYHL","created_at":"2026-05-26T01:03:25.763333+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGLNWCYO","created_at":"2026-05-26T01:03:25.763333+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5","json":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5.json","graph_json":"https://pith.science/api/pith-number/CGLNWCYOTLN6BYHLVH3H7OMHV5/graph.json","events_json":"https://pith.science/api/pith-number/CGLNWCYOTLN6BYHLVH3H7OMHV5/events.json","paper":"https://pith.science/paper/CGLNWCYO"},"agent_actions":{"view_html":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5","download_json":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5.json","view_paper":"https://pith.science/paper/CGLNWCYO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.18527&json=true","fetch_graph":"https://pith.science/api/pith-number/CGLNWCYOTLN6BYHLVH3H7OMHV5/graph.json","fetch_events":"https://pith.science/api/pith-number/CGLNWCYOTLN6BYHLVH3H7OMHV5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5/action/storage_attestation","attest_author":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5/action/author_attestation","sign_citation":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5/action/citation_signature","submit_replication":"https://pith.science/pith/CGLNWCYOTLN6BYHLVH3H7OMHV5/action/replication_record"}},"created_at":"2026-05-26T01:03:25.763333+00:00","updated_at":"2026-05-26T01:03:25.763333+00:00"}