{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XV2K4OUONMGDETSHPZRB2DDWIU","short_pith_number":"pith:XV2K4OUO","schema_version":"1.0","canonical_sha256":"bd74ae3a8e6b0c324e477e621d0c76452eb1674187b40b5987979f66c8d35452","source":{"kind":"arxiv","id":"2305.10764","version":2},"attestation_state":"computed","paper":{"title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hao Su, Hong Cai, Kaiming Kuang, Minghua Liu, Ruoxi Shi, Shizhong Han, Xuanlin Li, Yinhao Zhu","submitted_at":"2023-05-18T07:07:19Z","abstract_excerpt":"We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus on scaling up 3D representations to enable open-world 3D shape understanding. To achieve this, we scale up training data by ensembling multiple 3D datasets and propose several strategies to automatically filter and enrich noisy text descriptions. We also explore and compare strategies for scaling 3D backbone networks and introduce a novel hard negative minin"},"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":"2305.10764","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-05-18T07:07:19Z","cross_cats_sorted":[],"title_canon_sha256":"dc3c5ba048c891d68fb097f13f9a9454c6c61185a7d5dde35a81a98a23098237","abstract_canon_sha256":"b2659dc8bf5eca9466718a4b214035e27052d20163b8d2371d52b5124e61a9aa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:31.770251Z","signature_b64":"0zhblgHcby4UrU7heZqRzf5ayM5kM5fw4KbmXrZ3pLaufiIQMAl0vmWlopoBVAtp2rCVWfN2GIlbsgADZFcuAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd74ae3a8e6b0c324e477e621d0c76452eb1674187b40b5987979f66c8d35452","last_reissued_at":"2026-07-05T06:21:31.769796Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:31.769796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fatih Porikli, Hao Su, Hong Cai, Kaiming Kuang, Minghua Liu, Ruoxi Shi, Shizhong Han, Xuanlin Li, Yinhao Zhu","submitted_at":"2023-05-18T07:07:19Z","abstract_excerpt":"We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus on scaling up 3D representations to enable open-world 3D shape understanding. To achieve this, we scale up training data by ensembling multiple 3D datasets and propose several strategies to automatically filter and enrich noisy text descriptions. We also explore and compare strategies for scaling 3D backbone networks and introduce a novel hard negative minin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.10764","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/2305.10764/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":"2305.10764","created_at":"2026-07-05T06:21:31.769853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.10764v2","created_at":"2026-07-05T06:21:31.769853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.10764","created_at":"2026-07-05T06:21:31.769853+00:00"},{"alias_kind":"pith_short_12","alias_value":"XV2K4OUONMGD","created_at":"2026-07-05T06:21:31.769853+00:00"},{"alias_kind":"pith_short_16","alias_value":"XV2K4OUONMGDETSH","created_at":"2026-07-05T06:21:31.769853+00:00"},{"alias_kind":"pith_short_8","alias_value":"XV2K4OUO","created_at":"2026-07-05T06:21:31.769853+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.27507","citing_title":"Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11043","citing_title":"EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU","json":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU.json","graph_json":"https://pith.science/api/pith-number/XV2K4OUONMGDETSHPZRB2DDWIU/graph.json","events_json":"https://pith.science/api/pith-number/XV2K4OUONMGDETSHPZRB2DDWIU/events.json","paper":"https://pith.science/paper/XV2K4OUO"},"agent_actions":{"view_html":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU","download_json":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU.json","view_paper":"https://pith.science/paper/XV2K4OUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.10764&json=true","fetch_graph":"https://pith.science/api/pith-number/XV2K4OUONMGDETSHPZRB2DDWIU/graph.json","fetch_events":"https://pith.science/api/pith-number/XV2K4OUONMGDETSHPZRB2DDWIU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU/action/storage_attestation","attest_author":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU/action/author_attestation","sign_citation":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU/action/citation_signature","submit_replication":"https://pith.science/pith/XV2K4OUONMGDETSHPZRB2DDWIU/action/replication_record"}},"created_at":"2026-07-05T06:21:31.769853+00:00","updated_at":"2026-07-05T06:21:31.769853+00:00"}