{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QLVYSNVNZX2WMRPUUIPDXNPWDO","short_pith_number":"pith:QLVYSNVN","schema_version":"1.0","canonical_sha256":"82eb8936adcdf56645f4a21e3bb5f61ba6792e079e6c79f2f34e9bb03bd4a417","source":{"kind":"arxiv","id":"2212.00836","version":1},"attestation_state":"computed","paper":{"title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Dave Zhenyu Chen, Matthias Nie{\\ss}ner, Ronghang Hu, Xinlei Chen","submitted_at":"2022-12-01T19:45:09Z","abstract_excerpt":"Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks"},"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":"2212.00836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-12-01T19:45:09Z","cross_cats_sorted":[],"title_canon_sha256":"b1527da68aab4d2781adc3325e3a4d1549bfcb93487f3971b26806139506bd21","abstract_canon_sha256":"c7626768c2e8465ab38d5ec7f5919b768554fae038bae025ff32763da6ecf4c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:21:46.227466Z","signature_b64":"m6soDVRDRg/BqJnSzkxySWgfKj8DpmLvmuWfbwM1yAQRHt/4tvR217j9YGdpkmgDFoyz+xPj39WFPhl1AJY2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82eb8936adcdf56645f4a21e3bb5f61ba6792e079e6c79f2f34e9bb03bd4a417","last_reissued_at":"2026-07-05T05:21:46.226997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:21:46.226997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniT3D: A Unified Transformer for 3D Dense Captioning and Visual Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Angel X. Chang, Dave Zhenyu Chen, Matthias Nie{\\ss}ner, Ronghang Hu, Xinlei Chen","submitted_at":"2022-12-01T19:45:09Z","abstract_excerpt":"Performing 3D dense captioning and visual grounding requires a common and shared understanding of the underlying multimodal relationships. However, despite some previous attempts on connecting these two related tasks with highly task-specific neural modules, it remains understudied how to explicitly depict their shared nature to learn them simultaneously. In this work, we propose UniT3D, a simple yet effective fully unified transformer-based architecture for jointly solving 3D visual grounding and dense captioning. UniT3D enables learning a strong multimodal representation across the two tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.00836","kind":"arxiv","version":1},"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/2212.00836/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":"2212.00836","created_at":"2026-07-05T05:21:46.227052+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.00836v1","created_at":"2026-07-05T05:21:46.227052+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.00836","created_at":"2026-07-05T05:21:46.227052+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLVYSNVNZX2W","created_at":"2026-07-05T05:21:46.227052+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLVYSNVNZX2WMRPU","created_at":"2026-07-05T05:21:46.227052+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLVYSNVN","created_at":"2026-07-05T05:21:46.227052+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO","json":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO.json","graph_json":"https://pith.science/api/pith-number/QLVYSNVNZX2WMRPUUIPDXNPWDO/graph.json","events_json":"https://pith.science/api/pith-number/QLVYSNVNZX2WMRPUUIPDXNPWDO/events.json","paper":"https://pith.science/paper/QLVYSNVN"},"agent_actions":{"view_html":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO","download_json":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO.json","view_paper":"https://pith.science/paper/QLVYSNVN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.00836&json=true","fetch_graph":"https://pith.science/api/pith-number/QLVYSNVNZX2WMRPUUIPDXNPWDO/graph.json","fetch_events":"https://pith.science/api/pith-number/QLVYSNVNZX2WMRPUUIPDXNPWDO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO/action/storage_attestation","attest_author":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO/action/author_attestation","sign_citation":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO/action/citation_signature","submit_replication":"https://pith.science/pith/QLVYSNVNZX2WMRPUUIPDXNPWDO/action/replication_record"}},"created_at":"2026-07-05T05:21:46.227052+00:00","updated_at":"2026-07-05T05:21:46.227052+00:00"}