{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZEO4FDY3EEYLX3U53X3J4ZTDN","short_pith_number":"pith:RZEO4FDY","schema_version":"1.0","canonical_sha256":"8e48ee1478d90985df74eeefb4f3331b5931464f4e6f2929f98c24849f0be3a1","source":{"kind":"arxiv","id":"2406.18941","version":1},"attestation_state":"computed","paper":{"title":"CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Dong, Yanyun Qu, Yao Wu, Zongze Wu, Zuo Zuo","submitted_at":"2024-06-27T07:13:09Z","abstract_excerpt":"Few-shot anomaly detection methods can effectively address data collecting difficulty in industrial scenarios. Compared to 2D few-shot anomaly detection (2D-FSAD), 3D few-shot anomaly detection (3D-FSAD) is still an unexplored but essential task. In this paper, we propose CLIP3D-AD, an efficient 3D-FSAD method extended on CLIP. We successfully transfer strong generalization ability of CLIP into 3D-FSAD. Specifically, we synthesize anomalous images on given normal images as sample pairs to adapt CLIP for 3D anomaly classification and segmentation. For classification, we introduce an image adapt"},"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":"2406.18941","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-27T07:13:09Z","cross_cats_sorted":[],"title_canon_sha256":"2da3408ec79eb47c7b2d94adcd04a6539c19be4032bff888a715eb0d3f0023ac","abstract_canon_sha256":"5534d3ab68fb6455d762998810564c91fed1f925f70cf79943530aa71735115e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:27.828427Z","signature_b64":"/peRWmJfp4X0qK0zVPTgrYF0AtCceEEHm2Yle7x3XkMoUaJ76/rUbFBx0Dl8zTJ5IhxxMp9xRPae71wXYtauDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e48ee1478d90985df74eeefb4f3331b5931464f4e6f2929f98c24849f0be3a1","last_reissued_at":"2026-07-05T08:37:27.827989Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:27.827989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIP3D-AD: Extending CLIP for 3D Few-Shot Anomaly Detection with Multi-View Images Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiahao Dong, Yanyun Qu, Yao Wu, Zongze Wu, Zuo Zuo","submitted_at":"2024-06-27T07:13:09Z","abstract_excerpt":"Few-shot anomaly detection methods can effectively address data collecting difficulty in industrial scenarios. Compared to 2D few-shot anomaly detection (2D-FSAD), 3D few-shot anomaly detection (3D-FSAD) is still an unexplored but essential task. In this paper, we propose CLIP3D-AD, an efficient 3D-FSAD method extended on CLIP. We successfully transfer strong generalization ability of CLIP into 3D-FSAD. Specifically, we synthesize anomalous images on given normal images as sample pairs to adapt CLIP for 3D anomaly classification and segmentation. For classification, we introduce an image adapt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18941","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/2406.18941/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":"2406.18941","created_at":"2026-07-05T08:37:27.828046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18941v1","created_at":"2026-07-05T08:37:27.828046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18941","created_at":"2026-07-05T08:37:27.828046+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZEO4FDY3EEY","created_at":"2026-07-05T08:37:27.828046+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZEO4FDY3EEYLX3U","created_at":"2026-07-05T08:37:27.828046+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZEO4FDY","created_at":"2026-07-05T08:37:27.828046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23126","citing_title":"MambaADv2: Evolving Duality-enhanced State Space Model for Unsupervised Anomaly Detection","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04369","citing_title":"VT-3DAD: Cross-Category 3D Anomaly Detection via Visual-Text Normal Space Alignment","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29181","citing_title":"Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN","json":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN.json","graph_json":"https://pith.science/api/pith-number/RZEO4FDY3EEYLX3U53X3J4ZTDN/graph.json","events_json":"https://pith.science/api/pith-number/RZEO4FDY3EEYLX3U53X3J4ZTDN/events.json","paper":"https://pith.science/paper/RZEO4FDY"},"agent_actions":{"view_html":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN","download_json":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN.json","view_paper":"https://pith.science/paper/RZEO4FDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18941&json=true","fetch_graph":"https://pith.science/api/pith-number/RZEO4FDY3EEYLX3U53X3J4ZTDN/graph.json","fetch_events":"https://pith.science/api/pith-number/RZEO4FDY3EEYLX3U53X3J4ZTDN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN/action/storage_attestation","attest_author":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN/action/author_attestation","sign_citation":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN/action/citation_signature","submit_replication":"https://pith.science/pith/RZEO4FDY3EEYLX3U53X3J4ZTDN/action/replication_record"}},"created_at":"2026-07-05T08:37:27.828046+00:00","updated_at":"2026-07-05T08:37:27.828046+00:00"}