{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MWS7BDZG66SGCUGXPPMPDNFJA7","short_pith_number":"pith:MWS7BDZG","schema_version":"1.0","canonical_sha256":"65a5f08f26f7a46150d77bd8f1b4a907c3f83f2b31e3334d7e5ebfac616561c1","source":{"kind":"arxiv","id":"2506.05414","version":1},"attestation_state":"computed","paper":{"title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Caleb Zheng, Eli Shlizerman, Jingyuan Li, Jinlin Xiang, Mingfei Chen, Xiulong Liu, Zijun Cui","submitted_at":"2025-06-04T19:11:20Z","abstract_excerpt":"3D spatial reasoning in dynamic, audio-visual environments is a cornerstone of human cognition yet remains largely unexplored by existing Audio-Visual Large Language Models (AV-LLMs) and benchmarks, which predominantly focus on static or 2D scenes. We introduce SAVVY-Bench, the first benchmark for 3D spatial reasoning in dynamic scenes with synchronized spatial audio. SAVVY-Bench is comprised of thousands of relationships involving static and moving objects, and requires fine-grained temporal grounding, consistent 3D localization, and multi-modal annotation. To tackle this challenge, we propos"},"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":"2506.05414","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T19:11:20Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"32b771136583d0880f34cd1539a6db89695b5124992c341f400cab163a9c3932","abstract_canon_sha256":"a81a6330b25e57427c83edff7dd59be4139c8b3ea35d051921b2363de511f83d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:02.194282Z","signature_b64":"EqlWRxgbBlZCeCZAZsoVrcv1R9375aIAbUUZ39r/7bi/ZbEBf+PBok3Ar0drjQR6YPF15jhH9O9fEKQgYItEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65a5f08f26f7a46150d77bd8f1b4a907c3f83f2b31e3334d7e5ebfac616561c1","last_reissued_at":"2026-07-05T11:17:02.193867Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:02.193867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Caleb Zheng, Eli Shlizerman, Jingyuan Li, Jinlin Xiang, Mingfei Chen, Xiulong Liu, Zijun Cui","submitted_at":"2025-06-04T19:11:20Z","abstract_excerpt":"3D spatial reasoning in dynamic, audio-visual environments is a cornerstone of human cognition yet remains largely unexplored by existing Audio-Visual Large Language Models (AV-LLMs) and benchmarks, which predominantly focus on static or 2D scenes. We introduce SAVVY-Bench, the first benchmark for 3D spatial reasoning in dynamic scenes with synchronized spatial audio. SAVVY-Bench is comprised of thousands of relationships involving static and moving objects, and requires fine-grained temporal grounding, consistent 3D localization, and multi-modal annotation. To tackle this challenge, we propos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05414","kind":"arxiv","version":1},"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/2506.05414/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":"2506.05414","created_at":"2026-07-05T11:17:02.193928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05414v1","created_at":"2026-07-05T11:17:02.193928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05414","created_at":"2026-07-05T11:17:02.193928+00:00"},{"alias_kind":"pith_short_12","alias_value":"MWS7BDZG66SG","created_at":"2026-07-05T11:17:02.193928+00:00"},{"alias_kind":"pith_short_16","alias_value":"MWS7BDZG66SGCUGX","created_at":"2026-07-05T11:17:02.193928+00:00"},{"alias_kind":"pith_short_8","alias_value":"MWS7BDZG","created_at":"2026-07-05T11:17:02.193928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07061","citing_title":"Do Joint Audio-Video Generation Models Understand Physics?","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18194","citing_title":"Beyond the Cartesian Illusion: Testing Two-Stage Multi-Modal Theory of Mind under Perceptual Bottlenecks","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.14122","citing_title":"EgoSound: Benchmarking Sound Understanding in Egocentric Videos","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7","json":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7.json","graph_json":"https://pith.science/api/pith-number/MWS7BDZG66SGCUGXPPMPDNFJA7/graph.json","events_json":"https://pith.science/api/pith-number/MWS7BDZG66SGCUGXPPMPDNFJA7/events.json","paper":"https://pith.science/paper/MWS7BDZG"},"agent_actions":{"view_html":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7","download_json":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7.json","view_paper":"https://pith.science/paper/MWS7BDZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05414&json=true","fetch_graph":"https://pith.science/api/pith-number/MWS7BDZG66SGCUGXPPMPDNFJA7/graph.json","fetch_events":"https://pith.science/api/pith-number/MWS7BDZG66SGCUGXPPMPDNFJA7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7/action/storage_attestation","attest_author":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7/action/author_attestation","sign_citation":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7/action/citation_signature","submit_replication":"https://pith.science/pith/MWS7BDZG66SGCUGXPPMPDNFJA7/action/replication_record"}},"created_at":"2026-07-05T11:17:02.193928+00:00","updated_at":"2026-07-05T11:17:02.193928+00:00"}