{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DP5XRMJSNTEQSWYR2Y5AJAG4OL","short_pith_number":"pith:DP5XRMJS","schema_version":"1.0","canonical_sha256":"1bfb78b1326cc9095b11d63a0480dc72ff64d7eac5c250190fda39bdb41dbe23","source":{"kind":"arxiv","id":"2311.06018","version":1},"attestation_state":"computed","paper":{"title":"U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hubert P.H. Shum, Jiaxu Liu, Toby P. Breckon, Zhengdi Yu","submitted_at":"2023-11-10T12:05:35Z","abstract_excerpt":"Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is still a lack of investigation into fully unsupervised scene segmentation for point clouds, especially for holistic 3D scenes. This paper presents U3DS$^3$, as a step towards completely unsupervised point cloud segmentation for any holistic 3D scenes. To achieve this, U3DS$^3$ leverages a generalized unsupervised segmentation method for both object and backgrou"},"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":"2311.06018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-10T12:05:35Z","cross_cats_sorted":[],"title_canon_sha256":"c44f3e85af60ea459974a66cc742fc25f41f4659544f8494bd0d2ad8546f9497","abstract_canon_sha256":"0404d57360791ffc2512696cd0d519a19de762e4dc9a5708ff9ae8196665b466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:26.695021Z","signature_b64":"Cpjy8KF3TJQlY/TlNF+1sa5rgCUkRsnBeeMeyYdYmtAe3uYhjKiEd2Ey4qS2lUEGf7yRBsFlobG5XvKsDnz+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bfb78b1326cc9095b11d63a0480dc72ff64d7eac5c250190fda39bdb41dbe23","last_reissued_at":"2026-07-05T07:11:26.694475Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:26.694475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"U3DS$^3$: Unsupervised 3D Semantic Scene Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hubert P.H. Shum, Jiaxu Liu, Toby P. Breckon, Zhengdi Yu","submitted_at":"2023-11-10T12:05:35Z","abstract_excerpt":"Contemporary point cloud segmentation approaches largely rely on richly annotated 3D training data. However, it is both time-consuming and challenging to obtain consistently accurate annotations for such 3D scene data. Moreover, there is still a lack of investigation into fully unsupervised scene segmentation for point clouds, especially for holistic 3D scenes. This paper presents U3DS$^3$, as a step towards completely unsupervised point cloud segmentation for any holistic 3D scenes. To achieve this, U3DS$^3$ leverages a generalized unsupervised segmentation method for both object and backgrou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06018","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/2311.06018/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":"2311.06018","created_at":"2026-07-05T07:11:26.694544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06018v1","created_at":"2026-07-05T07:11:26.694544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06018","created_at":"2026-07-05T07:11:26.694544+00:00"},{"alias_kind":"pith_short_12","alias_value":"DP5XRMJSNTEQ","created_at":"2026-07-05T07:11:26.694544+00:00"},{"alias_kind":"pith_short_16","alias_value":"DP5XRMJSNTEQSWYR","created_at":"2026-07-05T07:11:26.694544+00:00"},{"alias_kind":"pith_short_8","alias_value":"DP5XRMJS","created_at":"2026-07-05T07:11:26.694544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.03901","citing_title":"LeAP: Consistent multi-domain 3D labeling using Foundation Models","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL","json":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL.json","graph_json":"https://pith.science/api/pith-number/DP5XRMJSNTEQSWYR2Y5AJAG4OL/graph.json","events_json":"https://pith.science/api/pith-number/DP5XRMJSNTEQSWYR2Y5AJAG4OL/events.json","paper":"https://pith.science/paper/DP5XRMJS"},"agent_actions":{"view_html":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL","download_json":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL.json","view_paper":"https://pith.science/paper/DP5XRMJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06018&json=true","fetch_graph":"https://pith.science/api/pith-number/DP5XRMJSNTEQSWYR2Y5AJAG4OL/graph.json","fetch_events":"https://pith.science/api/pith-number/DP5XRMJSNTEQSWYR2Y5AJAG4OL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL/action/storage_attestation","attest_author":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL/action/author_attestation","sign_citation":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL/action/citation_signature","submit_replication":"https://pith.science/pith/DP5XRMJSNTEQSWYR2Y5AJAG4OL/action/replication_record"}},"created_at":"2026-07-05T07:11:26.694544+00:00","updated_at":"2026-07-05T07:11:26.694544+00:00"}