{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3HFYN3KJSXUPIOLBCLNUX5J2WM","short_pith_number":"pith:3HFYN3KJ","schema_version":"1.0","canonical_sha256":"d9cb86ed4995e8f4396112db4bf53ab33254f90de06addd6de07ebc247d4acb8","source":{"kind":"arxiv","id":"2305.10714","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Dai Tao, Shu-Tao Xia, Sunan He, Taolin Zhang, Zhi Wang","submitted_at":"2023-05-18T05:25:40Z","abstract_excerpt":"In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vis"},"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":"2305.10714","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T05:25:40Z","cross_cats_sorted":[],"title_canon_sha256":"1a92060483b2fd06d1995536548fbb5ef5cbf218b5779ade8eb8f255cba53f80","abstract_canon_sha256":"216fc2c8e74342f27ba7efd68bdb9c8d4ab7c289a014845431346265872405d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:25.876491Z","signature_b64":"4pL5kZLHz/m+V8voAxdfxh9PA5QvySSR49EdpRBKYgcdQXy/F+psiRb3U8SWFj1RDhcnXwKRjcJ2KiTSEzFGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9cb86ed4995e8f4396112db4bf53ab33254f90de06addd6de07ebc247d4acb8","last_reissued_at":"2026-07-05T06:11:25.876040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:25.876040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language Pre-training with Object Contrastive Learning for 3D Scene Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Chen, Dai Tao, Shu-Tao Xia, Sunan He, Taolin Zhang, Zhi Wang","submitted_at":"2023-05-18T05:25:40Z","abstract_excerpt":"In recent years, vision language pre-training frameworks have made significant progress in natural language processing and computer vision, achieving remarkable performance improvement on various downstream tasks. However, when extended to point cloud data, existing works mainly focus on building task-specific models, and fail to extract universal 3D vision-language embedding that generalize well. We carefully investigate three common tasks in semantic 3D scene understanding, and derive key insights into the development of a pre-training model. Motivated by these observations, we propose a vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10714","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/2305.10714/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":"2305.10714","created_at":"2026-07-05T06:11:25.876099+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10714v1","created_at":"2026-07-05T06:11:25.876099+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10714","created_at":"2026-07-05T06:11:25.876099+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HFYN3KJSXUP","created_at":"2026-07-05T06:11:25.876099+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HFYN3KJSXUPIOLB","created_at":"2026-07-05T06:11:25.876099+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HFYN3KJ","created_at":"2026-07-05T06:11:25.876099+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM","json":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM.json","graph_json":"https://pith.science/api/pith-number/3HFYN3KJSXUPIOLBCLNUX5J2WM/graph.json","events_json":"https://pith.science/api/pith-number/3HFYN3KJSXUPIOLBCLNUX5J2WM/events.json","paper":"https://pith.science/paper/3HFYN3KJ"},"agent_actions":{"view_html":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM","download_json":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM.json","view_paper":"https://pith.science/paper/3HFYN3KJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10714&json=true","fetch_graph":"https://pith.science/api/pith-number/3HFYN3KJSXUPIOLBCLNUX5J2WM/graph.json","fetch_events":"https://pith.science/api/pith-number/3HFYN3KJSXUPIOLBCLNUX5J2WM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM/action/storage_attestation","attest_author":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM/action/author_attestation","sign_citation":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM/action/citation_signature","submit_replication":"https://pith.science/pith/3HFYN3KJSXUPIOLBCLNUX5J2WM/action/replication_record"}},"created_at":"2026-07-05T06:11:25.876099+00:00","updated_at":"2026-07-05T06:11:25.876099+00:00"}