{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:AK3QSTNU623OJMBRRZCYWK4VE4","short_pith_number":"pith:AK3QSTNU","schema_version":"1.0","canonical_sha256":"02b7094db4f6b6e4b0318e458b2b9527118a35387cdcebdfbdd79f1d2fe83369","source":{"kind":"arxiv","id":"2312.03026","version":1},"attestation_state":"computed","paper":{"title":"Uni3DL: Unified Model for 3D and Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Ding, Mohamed Elhoseiny, Xiang Li, Zhaoyang Chen","submitted_at":"2023-12-05T08:30:27Z","abstract_excerpt":"In this work, we present Uni3DL, a unified model for 3D and Language understanding. Distinct from existing unified vision-language models in 3D which are limited in task variety and predominantly dependent on projected multi-view images, Uni3DL operates directly on point clouds. This approach significantly expands the range of supported tasks in 3D, encompassing both vision and vision-language tasks in 3D. At the core of Uni3DL, a query transformer is designed to learn task-agnostic semantic and mask outputs by attending to 3D visual features, and a task router is employed to selectively gener"},"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":"2312.03026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T08:30:27Z","cross_cats_sorted":[],"title_canon_sha256":"5d824a4894abe627d10d9aed5711c958be6e82e17e859ed1212ba4b210a73cb9","abstract_canon_sha256":"d086a370c19d71acd6f1e7bce0cb3df0ce208332b4407539616494356bdc3eac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:57.164461Z","signature_b64":"30g17OJGjARKfLIhiMk1/0IZExErjKt2EAZQWkSdOiHX2wi1HeNXyDgiqlQBusxFqt95E2qHYO+Rgp7Wd9/VDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02b7094db4f6b6e4b0318e458b2b9527118a35387cdcebdfbdd79f1d2fe83369","last_reissued_at":"2026-07-05T07:20:57.163982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:57.163982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni3DL: Unified Model for 3D and Language Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Ding, Mohamed Elhoseiny, Xiang Li, Zhaoyang Chen","submitted_at":"2023-12-05T08:30:27Z","abstract_excerpt":"In this work, we present Uni3DL, a unified model for 3D and Language understanding. Distinct from existing unified vision-language models in 3D which are limited in task variety and predominantly dependent on projected multi-view images, Uni3DL operates directly on point clouds. This approach significantly expands the range of supported tasks in 3D, encompassing both vision and vision-language tasks in 3D. At the core of Uni3DL, a query transformer is designed to learn task-agnostic semantic and mask outputs by attending to 3D visual features, and a task router is employed to selectively gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03026","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/2312.03026/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":"2312.03026","created_at":"2026-07-05T07:20:57.164038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03026v1","created_at":"2026-07-05T07:20:57.164038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03026","created_at":"2026-07-05T07:20:57.164038+00:00"},{"alias_kind":"pith_short_12","alias_value":"AK3QSTNU623O","created_at":"2026-07-05T07:20:57.164038+00:00"},{"alias_kind":"pith_short_16","alias_value":"AK3QSTNU623OJMBR","created_at":"2026-07-05T07:20:57.164038+00:00"},{"alias_kind":"pith_short_8","alias_value":"AK3QSTNU","created_at":"2026-07-05T07:20:57.164038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22429","citing_title":"Zero-Shot 3D Visual Grounding from Vision-Language Models","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4","json":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4.json","graph_json":"https://pith.science/api/pith-number/AK3QSTNU623OJMBRRZCYWK4VE4/graph.json","events_json":"https://pith.science/api/pith-number/AK3QSTNU623OJMBRRZCYWK4VE4/events.json","paper":"https://pith.science/paper/AK3QSTNU"},"agent_actions":{"view_html":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4","download_json":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4.json","view_paper":"https://pith.science/paper/AK3QSTNU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03026&json=true","fetch_graph":"https://pith.science/api/pith-number/AK3QSTNU623OJMBRRZCYWK4VE4/graph.json","fetch_events":"https://pith.science/api/pith-number/AK3QSTNU623OJMBRRZCYWK4VE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4/action/storage_attestation","attest_author":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4/action/author_attestation","sign_citation":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4/action/citation_signature","submit_replication":"https://pith.science/pith/AK3QSTNU623OJMBRRZCYWK4VE4/action/replication_record"}},"created_at":"2026-07-05T07:20:57.164038+00:00","updated_at":"2026-07-05T07:20:57.164038+00:00"}