{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6NKJ2XAMJLAPNRI254U7XJXR64","short_pith_number":"pith:6NKJ2XAM","schema_version":"1.0","canonical_sha256":"f3549d5c0c4ac0f6c51aef29fba6f1f7234ce6b112bbfe0d6970367638dee66d","source":{"kind":"arxiv","id":"2303.14727","version":2},"attestation_state":"computed","paper":{"title":"You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Xiaojuan Qi, Zhengzhe Liu","submitted_at":"2023-03-26T13:57:00Z","abstract_excerpt":"3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose ``One Thing One Click,'' meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, f"},"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":"2303.14727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-26T13:57:00Z","cross_cats_sorted":[],"title_canon_sha256":"8d9da1c8bbda47a970051f6ae3d5ea7a1093e25fea3724f3fdeeb8481222bb72","abstract_canon_sha256":"802eca112f8b59a629e064b19a28b5daf9d59b88a65fae29439781d819514792"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:49:41.877051Z","signature_b64":"YNOtS6Xrq7VwKd13v/B6os0p1cjg7+oX8B3uZddKVFL7QLtQwxUFU/R+ca7LKBMgcfF43z3SIOjOQvHREowYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3549d5c0c4ac0f6c51aef29fba6f1f7234ce6b112bbfe0d6970367638dee66d","last_reissued_at":"2026-07-05T06:49:41.876580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:49:41.876580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chi-Wing Fu, Xiaojuan Qi, Zhengzhe Liu","submitted_at":"2023-03-26T13:57:00Z","abstract_excerpt":"3D scene understanding, e.g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare. While some recent methods propose to train a 3D network with small percentages of point labels, we take the approach to an extreme and propose ``One Thing One Click,'' meaning that the annotator only needs to label one point per object. To leverage these extremely sparse labels in network training, we design a novel self-training approach, in which we iteratively conduct the training and label propagation, f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14727","kind":"arxiv","version":2},"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/2303.14727/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":"2303.14727","created_at":"2026-07-05T06:49:41.876632+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14727v2","created_at":"2026-07-05T06:49:41.876632+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14727","created_at":"2026-07-05T06:49:41.876632+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NKJ2XAMJLAP","created_at":"2026-07-05T06:49:41.876632+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NKJ2XAMJLAPNRI2","created_at":"2026-07-05T06:49:41.876632+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NKJ2XAM","created_at":"2026-07-05T06:49:41.876632+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19909","citing_title":"Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64","json":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64.json","graph_json":"https://pith.science/api/pith-number/6NKJ2XAMJLAPNRI254U7XJXR64/graph.json","events_json":"https://pith.science/api/pith-number/6NKJ2XAMJLAPNRI254U7XJXR64/events.json","paper":"https://pith.science/paper/6NKJ2XAM"},"agent_actions":{"view_html":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64","download_json":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64.json","view_paper":"https://pith.science/paper/6NKJ2XAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14727&json=true","fetch_graph":"https://pith.science/api/pith-number/6NKJ2XAMJLAPNRI254U7XJXR64/graph.json","fetch_events":"https://pith.science/api/pith-number/6NKJ2XAMJLAPNRI254U7XJXR64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64/action/storage_attestation","attest_author":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64/action/author_attestation","sign_citation":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64/action/citation_signature","submit_replication":"https://pith.science/pith/6NKJ2XAMJLAPNRI254U7XJXR64/action/replication_record"}},"created_at":"2026-07-05T06:49:41.876632+00:00","updated_at":"2026-07-05T06:49:41.876632+00:00"}