{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PMIY2P3XBLNKEFNAJEBCHPYLRY","short_pith_number":"pith:PMIY2P3X","schema_version":"1.0","canonical_sha256":"7b118d3f770adaa215a0490223bf0b8e0d236165ec65134dd65cfe20e2a59c86","source":{"kind":"arxiv","id":"2602.19206","version":3},"attestation_state":"computed","paper":{"title":"GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An Liu, Yan Wang, Zehao Deng","submitted_at":"2026-02-22T14:30:41Z","abstract_excerpt":"Zero-shot 3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target training data, which is particularly important in scenarios constrained by sample scarcity and data privacy concerns. While current methods adapt CLIP by projecting 3D point clouds into 2D representations, they face challenges. The projection inherently loses some geometric details, and the reliance on a single 2D modality provides an incomplete visual understanding, limiting their ability to detect diverse anomaly types. To address these limitations, we propose the Geometry-"},"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":"2602.19206","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-02-22T14:30:41Z","cross_cats_sorted":[],"title_canon_sha256":"5fe92eb58278378a92b52fb54bda96860371bcf06016ef48f9376fa9fc9d2900","abstract_canon_sha256":"e9ab932965c2261d3a0fc013b9bea581182cc1d8bdb5b3d548ee616c5c481c7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:04:56.403921Z","signature_b64":"GktpB9PsHKJLaeXCCG34fd++9+iUv8i3OCsGxFz2/KVx1dIpQ88trj3koUFDXTf2+jZtQmmsdTkAkgFrUn58AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b118d3f770adaa215a0490223bf0b8e0d236165ec65134dd65cfe20e2a59c86","last_reissued_at":"2026-05-27T01:04:56.403167Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:04:56.403167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GS-CLIP: Zero-shot 3D Anomaly Detection by Geometry-Aware Prompt and Synergistic View Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"An Liu, Yan Wang, Zehao Deng","submitted_at":"2026-02-22T14:30:41Z","abstract_excerpt":"Zero-shot 3D Anomaly Detection is an emerging task that aims to detect anomalies in a target dataset without any target training data, which is particularly important in scenarios constrained by sample scarcity and data privacy concerns. While current methods adapt CLIP by projecting 3D point clouds into 2D representations, they face challenges. The projection inherently loses some geometric details, and the reliance on a single 2D modality provides an incomplete visual understanding, limiting their ability to detect diverse anomaly types. To address these limitations, we propose the Geometry-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.19206","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/2602.19206/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":"2602.19206","created_at":"2026-05-27T01:04:56.403283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19206v3","created_at":"2026-05-27T01:04:56.403283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19206","created_at":"2026-05-27T01:04:56.403283+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMIY2P3XBLNK","created_at":"2026-05-27T01:04:56.403283+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMIY2P3XBLNKEFNA","created_at":"2026-05-27T01:04:56.403283+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMIY2P3X","created_at":"2026-05-27T01:04:56.403283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.05850","citing_title":"Align3D-AD: Cross-Modal Feature Alignment and Dual-Prompt Learning for Zero-shot 3D Anomaly Detection","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY","json":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY.json","graph_json":"https://pith.science/api/pith-number/PMIY2P3XBLNKEFNAJEBCHPYLRY/graph.json","events_json":"https://pith.science/api/pith-number/PMIY2P3XBLNKEFNAJEBCHPYLRY/events.json","paper":"https://pith.science/paper/PMIY2P3X"},"agent_actions":{"view_html":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY","download_json":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY.json","view_paper":"https://pith.science/paper/PMIY2P3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19206&json=true","fetch_graph":"https://pith.science/api/pith-number/PMIY2P3XBLNKEFNAJEBCHPYLRY/graph.json","fetch_events":"https://pith.science/api/pith-number/PMIY2P3XBLNKEFNAJEBCHPYLRY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY/action/storage_attestation","attest_author":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY/action/author_attestation","sign_citation":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY/action/citation_signature","submit_replication":"https://pith.science/pith/PMIY2P3XBLNKEFNAJEBCHPYLRY/action/replication_record"}},"created_at":"2026-05-27T01:04:56.403283+00:00","updated_at":"2026-05-27T01:04:56.403283+00:00"}