{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MWS7BDZG66SGCUGXPPMPDNFJA7","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":"a81a6330b25e57427c83edff7dd59be4139c8b3ea35d051921b2363de511f83d","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T19:11:20Z","title_canon_sha256":"32b771136583d0880f34cd1539a6db89695b5124992c341f400cab163a9c3932"},"schema_version":"1.0","source":{"id":"2506.05414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05414","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05414v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05414","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"MWS7BDZG66SG","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"MWS7BDZG66SGCUGX","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"MWS7BDZG","created_at":"2026-07-05T11:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:9413c29cd5f113c0715f46a349314a70337a745bf185bc3c57c8c5bd3158fc16","target":"graph","created_at":"2026-07-05T11:17:02Z","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/2506.05414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Caleb Zheng, Eli Shlizerman, Jingyuan Li, Jinlin Xiang, Mingfei Chen, Xiulong Liu, Zijun Cui","cross_cats":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T19:11:20Z","title":"SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05414","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":"sha256:19946c4f8a608f493fd4a4fc8743fde45e04f7143b4c8fa02f6ec00a83ac99e2","target":"record","created_at":"2026-07-05T11:17:02Z","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":"a81a6330b25e57427c83edff7dd59be4139c8b3ea35d051921b2363de511f83d","cross_cats_sorted":["cs.AI","cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T19:11:20Z","title_canon_sha256":"32b771136583d0880f34cd1539a6db89695b5124992c341f400cab163a9c3932"},"schema_version":"1.0","source":{"id":"2506.05414","kind":"arxiv","version":1}},"canonical_sha256":"65a5f08f26f7a46150d77bd8f1b4a907c3f83f2b31e3334d7e5ebfac616561c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65a5f08f26f7a46150d77bd8f1b4a907c3f83f2b31e3334d7e5ebfac616561c1","first_computed_at":"2026-07-05T11:17:02.193867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:02.193867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EqlWRxgbBlZCeCZAZsoVrcv1R9375aIAbUUZ39r/7bi/ZbEBf+PBok3Ar0drjQR6YPF15jhH9O9fEKQgYItEBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:02.194282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19946c4f8a608f493fd4a4fc8743fde45e04f7143b4c8fa02f6ec00a83ac99e2","sha256:9413c29cd5f113c0715f46a349314a70337a745bf185bc3c57c8c5bd3158fc16"],"state_sha256":"6aa54147032f32f956ad919f624a675b7d9cb7d0d9d8b787f8dc6c3f5210133f"}