{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HS3RHO2LP7GO7T5HRHKKMPIVYQ","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":"48d86c47b07bbae13307d6a9e4b55fb4a00962ef074d4e012a68c3607f29537f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T12:03:30Z","title_canon_sha256":"189b79fb70189cb98d7a05fa7abbe77a2634f8fcf409e1bf86765f5824b591db"},"schema_version":"1.0","source":{"id":"2505.21079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21079","created_at":"2026-07-05T11:10:23Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21079v1","created_at":"2026-07-05T11:10:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21079","created_at":"2026-07-05T11:10:23Z"},{"alias_kind":"pith_short_12","alias_value":"HS3RHO2LP7GO","created_at":"2026-07-05T11:10:23Z"},{"alias_kind":"pith_short_16","alias_value":"HS3RHO2LP7GO7T5H","created_at":"2026-07-05T11:10:23Z"},{"alias_kind":"pith_short_8","alias_value":"HS3RHO2L","created_at":"2026-07-05T11:10:23Z"}],"graph_snapshots":[{"event_id":"sha256:465e0840d7ea72babdc4793c5c3b732a37c14b9ea28595e9e126dcf185c7303b","target":"graph","created_at":"2026-07-05T11:10:23Z","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/2505.21079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have demonstrated considerable potential for comprehensive 3D scene understanding. However, existing approaches typically utilize only one or a limited subset of 3D modalities, resulting in incomplete representations of 3D scenes and reduced interpretive accuracy. Furthermore, different types of queries inherently depend on distinct modalities, indicating that uniform processing of all modality tokens may fail to effectively capture query-specific context. To address these challenges, we propose Uni3D-MoE, a sparse Mixture-of-Expe","authors_text":"Hehe Fan, Roger Zimmermann, Yingzhao Jian, Yi Yang, Yue Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T12:03:30Z","title":"Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21079","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":"sha256:4fd6ecb69012a2b5438a85b7c1efd7322f6c5634d31f65cbb84af8d7fee8d175","target":"record","created_at":"2026-07-05T11:10:23Z","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":"48d86c47b07bbae13307d6a9e4b55fb4a00962ef074d4e012a68c3607f29537f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-27T12:03:30Z","title_canon_sha256":"189b79fb70189cb98d7a05fa7abbe77a2634f8fcf409e1bf86765f5824b591db"},"schema_version":"1.0","source":{"id":"2505.21079","kind":"arxiv","version":1}},"canonical_sha256":"3cb713bb4b7fccefcfa789d4a63d15c436a4857b94af48e934eb769c2f5be786","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cb713bb4b7fccefcfa789d4a63d15c436a4857b94af48e934eb769c2f5be786","first_computed_at":"2026-07-05T11:10:23.302687Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:23.302687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LRkZB4WZxmP7dFw0vXwd+8MJd6WfDJbYRkcTfxLeI8Um+/IxrrZUQsPtlabloYA/wVwIJRvCTQin22t5HuzWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:23.303254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd6ecb69012a2b5438a85b7c1efd7322f6c5634d31f65cbb84af8d7fee8d175","sha256:465e0840d7ea72babdc4793c5c3b732a37c14b9ea28595e9e126dcf185c7303b"],"state_sha256":"497da3c1cd5bf0b132ba95dd8f044c0de314b900d999d6874ff033c5417dbf8d"}