{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JC6ZRCGTU4R4H3JNCF36DLWYQN","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":"ef1054067ea70719d9905f84f2c1aa81f17ee35dc47b006bf89464751c024a25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T18:03:41Z","title_canon_sha256":"91a5d4a68f16ca737b3fe08773e817e82bbed835ee469461f2446b7e115cb4c0"},"schema_version":"1.0","source":{"id":"2405.10370","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.10370","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"arxiv_version","alias_value":"2405.10370v2","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10370","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_12","alias_value":"JC6ZRCGTU4R4","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_16","alias_value":"JC6ZRCGTU4R4H3JN","created_at":"2026-07-05T09:36:40Z"},{"alias_kind":"pith_short_8","alias_value":"JC6ZRCGT","created_at":"2026-07-05T09:36:40Z"}],"graph_snapshots":[{"event_id":"sha256:627fbf17a6360125c74dab0a5c8ad335afca90f2c5b9b9caf9dc22facce2b163","target":"graph","created_at":"2026-07-05T09:36:40Z","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/2405.10370/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior studies on 3D scene understanding have primarily developed specialized models for specific tasks or required task-specific fine-tuning. In this study, we propose Grounded 3D-LLM, which explores the potential of 3D large multi-modal models (3D LMMs) to consolidate various 3D vision tasks within a unified generative framework. The model uses scene referent tokens as special noun phrases to reference 3D scenes, enabling it to handle sequences that interleave 3D and textual data. Per-task instruction-following templates are employed to ensure natural and diversity in translating 3D vision ta","authors_text":"Dahua Lin, Haifeng Huang, Jiangmiao Pang, Ruiyuan Lyu, Runsen Xu, Shuai Yang, Tai Wang, Yilun Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T18:03:41Z","title":"Grounded 3D-LLM with Referent Tokens"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10370","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":"sha256:4c263635e64722e8910d9cfca4670aff5bd144a9abdb0d6f2efcce71ae0830ee","target":"record","created_at":"2026-07-05T09:36:40Z","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":"ef1054067ea70719d9905f84f2c1aa81f17ee35dc47b006bf89464751c024a25","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T18:03:41Z","title_canon_sha256":"91a5d4a68f16ca737b3fe08773e817e82bbed835ee469461f2446b7e115cb4c0"},"schema_version":"1.0","source":{"id":"2405.10370","kind":"arxiv","version":2}},"canonical_sha256":"48bd9888d3a723c3ed2d1177e1aed8835e51119f416bd6f86ce89db5335994e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48bd9888d3a723c3ed2d1177e1aed8835e51119f416bd6f86ce89db5335994e1","first_computed_at":"2026-07-05T09:36:40.877755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:36:40.877755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wkkh+WpC/VXFKuRb8B68t7Zv37G4XDCZxmygKepvUBFOfrjbXIVXHhglLgupVLrM9BxSh2lYfO3T4oiSgu2sCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:36:40.878224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.10370","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c263635e64722e8910d9cfca4670aff5bd144a9abdb0d6f2efcce71ae0830ee","sha256:627fbf17a6360125c74dab0a5c8ad335afca90f2c5b9b9caf9dc22facce2b163"],"state_sha256":"9f454d98f7253569c773a5da65f07def7be602b3122288dd33670571e029e598"}