{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YGY7IPLKGZI7IO2HBJ6XQX47CM","short_pith_number":"pith:YGY7IPLK","schema_version":"1.0","canonical_sha256":"c1b1f43d6a3651f43b470a7d785f9f13089268aea76dafd455161f9d0e876a38","source":{"kind":"arxiv","id":"2311.18402","version":3},"attestation_state":"computed","paper":{"title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anan Liu, Dan Song, Lanjun Wang, Ning Liu, Weizhi Nie, Wenhui Li, Xinwei Fu, You Yang","submitted_at":"2023-11-30T09:51:53Z","abstract_excerpt":"Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on th"},"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":"2311.18402","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T09:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"5096d675ea8aefd94f8548b2c04d6d0c4fe4ffc041c87170b01950071eca7700","abstract_canon_sha256":"070ea0ddcaea53aa694c78f966d76bd88b9e2062498fe2c088a734122328b482"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:32.745033Z","signature_b64":"NXkx+bKFcgKD6gLYbgRo5dVPQekcmzAfLlDY4Q9aN3lqtQW1NK8mcGPnqUkEzFFhi+jKpZXt3OMbOGzULXLLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1b1f43d6a3651f43b470a7d785f9f13089268aea76dafd455161f9d0e876a38","last_reissued_at":"2026-07-05T09:05:32.744590Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:32.744590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anan Liu, Dan Song, Lanjun Wang, Ning Liu, Weizhi Nie, Wenhui Li, Xinwei Fu, You Yang","submitted_at":"2023-11-30T09:51:53Z","abstract_excerpt":"Large-scale pre-trained models have demonstrated impressive performance in vision and language tasks within open-world scenarios. Due to the lack of comparable pre-trained models for 3D shapes, recent methods utilize language-image pre-training to realize zero-shot 3D shape recognition. However, due to the modality gap, pretrained language-image models are not confident enough in the generalization to 3D shape recognition. Consequently, this paper aims to improve the confidence with view selection and hierarchical prompts. Leveraging the CLIP model as an example, we employ view selection on th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18402","kind":"arxiv","version":3},"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/2311.18402/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":"2311.18402","created_at":"2026-07-05T09:05:32.744648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18402v3","created_at":"2026-07-05T09:05:32.744648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18402","created_at":"2026-07-05T09:05:32.744648+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGY7IPLKGZI7","created_at":"2026-07-05T09:05:32.744648+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGY7IPLKGZI7IO2H","created_at":"2026-07-05T09:05:32.744648+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGY7IPLK","created_at":"2026-07-05T09:05:32.744648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19432","citing_title":"DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM","json":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM.json","graph_json":"https://pith.science/api/pith-number/YGY7IPLKGZI7IO2HBJ6XQX47CM/graph.json","events_json":"https://pith.science/api/pith-number/YGY7IPLKGZI7IO2HBJ6XQX47CM/events.json","paper":"https://pith.science/paper/YGY7IPLK"},"agent_actions":{"view_html":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM","download_json":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM.json","view_paper":"https://pith.science/paper/YGY7IPLK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18402&json=true","fetch_graph":"https://pith.science/api/pith-number/YGY7IPLKGZI7IO2HBJ6XQX47CM/graph.json","fetch_events":"https://pith.science/api/pith-number/YGY7IPLKGZI7IO2HBJ6XQX47CM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM/action/storage_attestation","attest_author":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM/action/author_attestation","sign_citation":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM/action/citation_signature","submit_replication":"https://pith.science/pith/YGY7IPLKGZI7IO2HBJ6XQX47CM/action/replication_record"}},"created_at":"2026-07-05T09:05:32.744648+00:00","updated_at":"2026-07-05T09:05:32.744648+00:00"}