{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5H7ZOZK6OEPBGC35ZDU5P4IZIQ","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":"a86aa67bd60a875ad795922486acc833c7aaa9f9f9806cf307e123e12256d7bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T09:33:13Z","title_canon_sha256":"0c249370f46a49e459ed6c45f9e6ac0c871081d4cb4258c9fb3b8ff249aa5fa0"},"schema_version":"1.0","source":{"id":"2501.01163","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.01163","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"arxiv_version","alias_value":"2501.01163v2","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01163","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_12","alias_value":"5H7ZOZK6OEPB","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_16","alias_value":"5H7ZOZK6OEPBGC35","created_at":"2026-07-05T10:53:14Z"},{"alias_kind":"pith_short_8","alias_value":"5H7ZOZK6","created_at":"2026-07-05T10:53:14Z"}],"graph_snapshots":[{"event_id":"sha256:9de185e7d9c295b6e534d36346b2811034ddbdb26260ac00bd4c2da504eb2ada","target":"graph","created_at":"2026-07-05T10:53:14Z","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/2501.01163/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current 3D Large Multimodal Models (3D LMMs) have shown tremendous potential in 3D-vision-based dialogue and reasoning. However, how to further enhance 3D LMMs to achieve fine-grained scene understanding and facilitate flexible human-agent interaction remains a challenging problem. In this work, we introduce 3D-LLaVA, a simple yet highly powerful 3D LMM designed to act as an intelligent assistant in comprehending, reasoning, and interacting with the 3D world. Unlike existing top-performing methods that rely on complicated pipelines-such as offline multi-view feature extraction or additional ta","authors_text":"Feras Dayoub, Ian Reid, Jiajun Deng, Li Jiang, Tianyu He, Tianyu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T09:33:13Z","title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01163","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":"sha256:3a341efdb81beae7011e53b3f47cfb67be94695db73d0beddbf93384ef749df2","target":"record","created_at":"2026-07-05T10:53:14Z","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":"a86aa67bd60a875ad795922486acc833c7aaa9f9f9806cf307e123e12256d7bb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T09:33:13Z","title_canon_sha256":"0c249370f46a49e459ed6c45f9e6ac0c871081d4cb4258c9fb3b8ff249aa5fa0"},"schema_version":"1.0","source":{"id":"2501.01163","kind":"arxiv","version":2}},"canonical_sha256":"e9ff97655e711e130b7dc8e9d7f1194429a17f968afbd0c2def1fa4c9ce83235","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9ff97655e711e130b7dc8e9d7f1194429a17f968afbd0c2def1fa4c9ce83235","first_computed_at":"2026-07-05T10:53:14.537827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:14.537827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7CBopajTb+8r9jcbZvsNJG2tf1FLUER2faxzWyxz9mFubbD/4r8fWdV2MzrFj0RfGOVHL5nf+q8V5ihxp4BFCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:14.538343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.01163","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a341efdb81beae7011e53b3f47cfb67be94695db73d0beddbf93384ef749df2","sha256:9de185e7d9c295b6e534d36346b2811034ddbdb26260ac00bd4c2da504eb2ada"],"state_sha256":"7239d150d535ba6e7a1b5e350acb123bb277cb82fa8b2a657c37e0bf7c0ccdce"}