{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5H7ZOZK6OEPBGC35ZDU5P4IZIQ","short_pith_number":"pith:5H7ZOZK6","schema_version":"1.0","canonical_sha256":"e9ff97655e711e130b7dc8e9d7f1194429a17f968afbd0c2def1fa4c9ce83235","source":{"kind":"arxiv","id":"2501.01163","version":2},"attestation_state":"computed","paper":{"title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feras Dayoub, Ian Reid, Jiajun Deng, Li Jiang, Tianyu He, Tianyu Wang","submitted_at":"2025-01-02T09:33:13Z","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"},"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":"2501.01163","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-02T09:33:13Z","cross_cats_sorted":[],"title_canon_sha256":"0c249370f46a49e459ed6c45f9e6ac0c871081d4cb4258c9fb3b8ff249aa5fa0","abstract_canon_sha256":"a86aa67bd60a875ad795922486acc833c7aaa9f9f9806cf307e123e12256d7bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:14.538343Z","signature_b64":"7CBopajTb+8r9jcbZvsNJG2tf1FLUER2faxzWyxz9mFubbD/4r8fWdV2MzrFj0RfGOVHL5nf+q8V5ihxp4BFCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9ff97655e711e130b7dc8e9d7f1194429a17f968afbd0c2def1fa4c9ce83235","last_reissued_at":"2026-07-05T10:53:14.537827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:14.537827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feras Dayoub, Ian Reid, Jiajun Deng, Li Jiang, Tianyu He, Tianyu Wang","submitted_at":"2025-01-02T09:33:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.01163","kind":"arxiv","version":2},"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/2501.01163/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":"2501.01163","created_at":"2026-07-05T10:53:14.537888+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.01163v2","created_at":"2026-07-05T10:53:14.537888+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.01163","created_at":"2026-07-05T10:53:14.537888+00:00"},{"alias_kind":"pith_short_12","alias_value":"5H7ZOZK6OEPB","created_at":"2026-07-05T10:53:14.537888+00:00"},{"alias_kind":"pith_short_16","alias_value":"5H7ZOZK6OEPBGC35","created_at":"2026-07-05T10:53:14.537888+00:00"},{"alias_kind":"pith_short_8","alias_value":"5H7ZOZK6","created_at":"2026-07-05T10:53:14.537888+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23747","citing_title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09167","citing_title":"MAG-3D: Multi-Agent Grounded Reasoning for 3D Understanding","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ","json":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ.json","graph_json":"https://pith.science/api/pith-number/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/graph.json","events_json":"https://pith.science/api/pith-number/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/events.json","paper":"https://pith.science/paper/5H7ZOZK6"},"agent_actions":{"view_html":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ","download_json":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ.json","view_paper":"https://pith.science/paper/5H7ZOZK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.01163&json=true","fetch_graph":"https://pith.science/api/pith-number/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/action/storage_attestation","attest_author":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/action/author_attestation","sign_citation":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/action/citation_signature","submit_replication":"https://pith.science/pith/5H7ZOZK6OEPBGC35ZDU5P4IZIQ/action/replication_record"}},"created_at":"2026-07-05T10:53:14.537888+00:00","updated_at":"2026-07-05T10:53:14.537888+00:00"}