{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7M6BLS7SUCY7UBBRWYURT5REER","short_pith_number":"pith:7M6BLS7S","schema_version":"1.0","canonical_sha256":"fb3c15cbf2a0b1fa0431b62919f62424698842aae5393e6afa0f9403bc780116","source":{"kind":"arxiv","id":"2309.00616","version":5},"attestation_state":"computed","paper":{"title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Joan Lasenby, Lei Zhu, Xiaoyang Wu, Xi Chen, Zhening Huang","submitted_at":"2023-09-01T17:59:56Z","abstract_excerpt":"In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a \"Mask-Snap-Lookup\" scheme. The \"Mask\" module learns class-agnostic mask proposals in 3D point clouds, the \"Snap\" module generates synthetic scene-level images at multiple scales and leverages 2D vision-language models to extract interesting objects, and the \"Lookup\" module searches through the outcomes of \"Snap\" to assign category names to the proposed masks. This approach, yet simple, achieves state-of-the-art performance across a wide range of 3D o"},"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":"2309.00616","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-01T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"83b429027c9e518539a2fa04c44254a903bbb3ee14026d28e4918bc660f9dfb4","abstract_canon_sha256":"160f89613702c8fb270410735161d9bcd061f2a4e7ef65bd0e66c41003588f95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:35.463309Z","signature_b64":"BPbqWwBLmJqj/t01cJ3nTMWUNIXKR+DlsJHGLbCR+FIpt8ykX7hdecIXVyAzakZPGABe9eu7JTOqgEUqEVL9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb3c15cbf2a0b1fa0431b62919f62424698842aae5393e6afa0f9403bc780116","last_reissued_at":"2026-07-05T08:54:35.462893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:35.462893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, Joan Lasenby, Lei Zhu, Xiaoyang Wu, Xi Chen, Zhening Huang","submitted_at":"2023-09-01T17:59:56Z","abstract_excerpt":"In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a \"Mask-Snap-Lookup\" scheme. The \"Mask\" module learns class-agnostic mask proposals in 3D point clouds, the \"Snap\" module generates synthetic scene-level images at multiple scales and leverages 2D vision-language models to extract interesting objects, and the \"Lookup\" module searches through the outcomes of \"Snap\" to assign category names to the proposed masks. This approach, yet simple, achieves state-of-the-art performance across a wide range of 3D o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.00616","kind":"arxiv","version":5},"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/2309.00616/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":"2309.00616","created_at":"2026-07-05T08:54:35.462948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.00616v5","created_at":"2026-07-05T08:54:35.462948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.00616","created_at":"2026-07-05T08:54:35.462948+00:00"},{"alias_kind":"pith_short_12","alias_value":"7M6BLS7SUCY7","created_at":"2026-07-05T08:54:35.462948+00:00"},{"alias_kind":"pith_short_16","alias_value":"7M6BLS7SUCY7UBBR","created_at":"2026-07-05T08:54:35.462948+00:00"},{"alias_kind":"pith_short_8","alias_value":"7M6BLS7S","created_at":"2026-07-05T08:54:35.462948+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26831","citing_title":"OSMa-Bench++: Toward Open-Ended Benchmarking of Semantic Mapping for Manipulation with Prompt-Generated Synthetic Scenes","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER","json":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER.json","graph_json":"https://pith.science/api/pith-number/7M6BLS7SUCY7UBBRWYURT5REER/graph.json","events_json":"https://pith.science/api/pith-number/7M6BLS7SUCY7UBBRWYURT5REER/events.json","paper":"https://pith.science/paper/7M6BLS7S"},"agent_actions":{"view_html":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER","download_json":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER.json","view_paper":"https://pith.science/paper/7M6BLS7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.00616&json=true","fetch_graph":"https://pith.science/api/pith-number/7M6BLS7SUCY7UBBRWYURT5REER/graph.json","fetch_events":"https://pith.science/api/pith-number/7M6BLS7SUCY7UBBRWYURT5REER/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER/action/storage_attestation","attest_author":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER/action/author_attestation","sign_citation":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER/action/citation_signature","submit_replication":"https://pith.science/pith/7M6BLS7SUCY7UBBRWYURT5REER/action/replication_record"}},"created_at":"2026-07-05T08:54:35.462948+00:00","updated_at":"2026-07-05T08:54:35.462948+00:00"}