{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7W2XWO4KQ4LZAS4OZLGJUAXBYH","short_pith_number":"pith:7W2XWO4K","schema_version":"1.0","canonical_sha256":"fdb57b3b8a8717904b8ecacc9a02e1c1eafd20642b5c748e84a85c14ac8725ba","source":{"kind":"arxiv","id":"2312.03015","version":1},"attestation_state":"computed","paper":{"title":"PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Su, Jiayuan Gu, Minghua Liu, Xuanlin Li, Yuchen Zhou, Yunhao Fang","submitted_at":"2023-12-05T01:33:04Z","abstract_excerpt":"Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR. Traditional supervised methods often grapple with limited 3D data availability and struggle to generalize to unseen object categories. PartSLIP, a recent advancement, has made significant strides in zero- and few-shot 3D part segmentation. This is achieved by harnessing the capabilities of the 2D open-vocabulary detection module, GLIP, and introducing a heuristic method for converting and lifting multi-view 2D bounding box predictions into 3D segmentation masks. In this paper, we introduce PartSLIP++"},"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":"2312.03015","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-05T01:33:04Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e910329bd58cb73dd89bc83a4f65f8c5cc33789ad5cf62493b44e3da4d28ba60","abstract_canon_sha256":"1d88742e3ebf0bdcec4c9f81786d15940fdab977956f65b8d37ed8bcf04b8a3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:56.938597Z","signature_b64":"BUqdPeawIq92hu4kCGlmJJN8bQsw2q9KUoWCMG6S1HJ5VinxqngUzfcsnLHKFOoMgcosVC3yJj6kIvqnr5HRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb57b3b8a8717904b8ecacc9a02e1c1eafd20642b5c748e84a85c14ac8725ba","last_reissued_at":"2026-07-05T07:20:56.938071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:56.938071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PartSLIP++: Enhancing Low-Shot 3D Part Segmentation via Multi-View Instance Segmentation and Maximum Likelihood Estimation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Su, Jiayuan Gu, Minghua Liu, Xuanlin Li, Yuchen Zhou, Yunhao Fang","submitted_at":"2023-12-05T01:33:04Z","abstract_excerpt":"Open-world 3D part segmentation is pivotal in diverse applications such as robotics and AR/VR. Traditional supervised methods often grapple with limited 3D data availability and struggle to generalize to unseen object categories. PartSLIP, a recent advancement, has made significant strides in zero- and few-shot 3D part segmentation. This is achieved by harnessing the capabilities of the 2D open-vocabulary detection module, GLIP, and introducing a heuristic method for converting and lifting multi-view 2D bounding box predictions into 3D segmentation masks. In this paper, we introduce PartSLIP++"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03015","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/2312.03015/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":"2312.03015","created_at":"2026-07-05T07:20:56.938168+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03015v1","created_at":"2026-07-05T07:20:56.938168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03015","created_at":"2026-07-05T07:20:56.938168+00:00"},{"alias_kind":"pith_short_12","alias_value":"7W2XWO4KQ4LZ","created_at":"2026-07-05T07:20:56.938168+00:00"},{"alias_kind":"pith_short_16","alias_value":"7W2XWO4KQ4LZAS4O","created_at":"2026-07-05T07:20:56.938168+00:00"},{"alias_kind":"pith_short_8","alias_value":"7W2XWO4K","created_at":"2026-07-05T07:20:56.938168+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31533","citing_title":"MV-GEL: Language-Driven Multi-View Geometric Entity Localization on Meshes","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29786","citing_title":"OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05070","citing_title":"Part-Level 3D Gaussian Vehicle Generation with Joint and Hinge Axis Estimation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH","json":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH.json","graph_json":"https://pith.science/api/pith-number/7W2XWO4KQ4LZAS4OZLGJUAXBYH/graph.json","events_json":"https://pith.science/api/pith-number/7W2XWO4KQ4LZAS4OZLGJUAXBYH/events.json","paper":"https://pith.science/paper/7W2XWO4K"},"agent_actions":{"view_html":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH","download_json":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH.json","view_paper":"https://pith.science/paper/7W2XWO4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03015&json=true","fetch_graph":"https://pith.science/api/pith-number/7W2XWO4KQ4LZAS4OZLGJUAXBYH/graph.json","fetch_events":"https://pith.science/api/pith-number/7W2XWO4KQ4LZAS4OZLGJUAXBYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH/action/storage_attestation","attest_author":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH/action/author_attestation","sign_citation":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH/action/citation_signature","submit_replication":"https://pith.science/pith/7W2XWO4KQ4LZAS4OZLGJUAXBYH/action/replication_record"}},"created_at":"2026-07-05T07:20:56.938168+00:00","updated_at":"2026-07-05T07:20:56.938168+00:00"}