{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QSPZALICZ3NIAW4GFO2H4LSEE7","short_pith_number":"pith:QSPZALIC","schema_version":"1.0","canonical_sha256":"849f902d02ceda805b862bb47e2e4427e8bf6da67d807a0d7d8c9dcfcaa66c74","source":{"kind":"arxiv","id":"2312.04891","version":1},"attestation_state":"computed","paper":{"title":"Cross-BERT for Point Cloud Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Lee Wang, Haoran Xie, Jing Qin, Junhui Hou, Liangliang Nan, Mingqiang Wei, Peng Li, Xin Li, Zeyong Wei, Zhe Zhu","submitted_at":"2023-12-08T08:18:12Z","abstract_excerpt":"Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different modalities. In this paper, we address these challenges by exploring the implicit semantic and geometric correlations between 2D and 3D data of the same objects/scenes. We propose a new cross-modal BERT-style self-supervised learning paradigm, called Cross-BERT. To facilitate pretraining for irregular and sparse point clouds, we design two self-supervised tasks"},"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":"2312.04891","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-08T08:18:12Z","cross_cats_sorted":[],"title_canon_sha256":"d1740557931029f65043efb7e0d6f36dbd12bd249fc339d31a3de5265a7c771d","abstract_canon_sha256":"b37490a63dcce2b09159344aaaefe3577ad278beb0622675ca61081f87858ac7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:53.868667Z","signature_b64":"r18qS4ZhUIxoE5CuUysSnd9CmQ3GN6/v/Denk7F07WCIgWsZ92C4VPYbG1qTn9s5X2G4EJOz+IGmagGbyFIuBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"849f902d02ceda805b862bb47e2e4427e8bf6da67d807a0d7d8c9dcfcaa66c74","last_reissued_at":"2026-07-05T07:21:53.868221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:53.868221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-BERT for Point Cloud Pretraining","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fu Lee Wang, Haoran Xie, Jing Qin, Junhui Hou, Liangliang Nan, Mingqiang Wei, Peng Li, Xin Li, Zeyong Wei, Zhe Zhu","submitted_at":"2023-12-08T08:18:12Z","abstract_excerpt":"Introducing BERT into cross-modal settings raises difficulties in its optimization for handling multiple modalities. Both the BERT architecture and training objective need to be adapted to incorporate and model information from different modalities. In this paper, we address these challenges by exploring the implicit semantic and geometric correlations between 2D and 3D data of the same objects/scenes. We propose a new cross-modal BERT-style self-supervised learning paradigm, called Cross-BERT. To facilitate pretraining for irregular and sparse point clouds, we design two self-supervised tasks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.04891","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/2312.04891/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":"2312.04891","created_at":"2026-07-05T07:21:53.868270+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.04891v1","created_at":"2026-07-05T07:21:53.868270+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.04891","created_at":"2026-07-05T07:21:53.868270+00:00"},{"alias_kind":"pith_short_12","alias_value":"QSPZALICZ3NI","created_at":"2026-07-05T07:21:53.868270+00:00"},{"alias_kind":"pith_short_16","alias_value":"QSPZALICZ3NIAW4G","created_at":"2026-07-05T07:21:53.868270+00:00"},{"alias_kind":"pith_short_8","alias_value":"QSPZALIC","created_at":"2026-07-05T07:21:53.868270+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01250","citing_title":"Towards More Diverse and Challenging Pre-training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7","json":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7.json","graph_json":"https://pith.science/api/pith-number/QSPZALICZ3NIAW4GFO2H4LSEE7/graph.json","events_json":"https://pith.science/api/pith-number/QSPZALICZ3NIAW4GFO2H4LSEE7/events.json","paper":"https://pith.science/paper/QSPZALIC"},"agent_actions":{"view_html":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7","download_json":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7.json","view_paper":"https://pith.science/paper/QSPZALIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.04891&json=true","fetch_graph":"https://pith.science/api/pith-number/QSPZALICZ3NIAW4GFO2H4LSEE7/graph.json","fetch_events":"https://pith.science/api/pith-number/QSPZALICZ3NIAW4GFO2H4LSEE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7/action/storage_attestation","attest_author":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7/action/author_attestation","sign_citation":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7/action/citation_signature","submit_replication":"https://pith.science/pith/QSPZALICZ3NIAW4GFO2H4LSEE7/action/replication_record"}},"created_at":"2026-07-05T07:21:53.868270+00:00","updated_at":"2026-07-05T07:21:53.868270+00:00"}