{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GJIDBRGCKPCLN3PQNUCU2HX2EB","short_pith_number":"pith:GJIDBRGC","schema_version":"1.0","canonical_sha256":"325030c4c253c4b6edf06d054d1efa2056b0d3195dc3f64cbfdbf8fbfd584298","source":{"kind":"arxiv","id":"2603.21511","version":2},"attestation_state":"computed","paper":{"title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Han, Gang Li, Jin Wan, Kaiqiang Li, Mingle Zhou, Min Li","submitted_at":"2026-03-23T02:59:00Z","abstract_excerpt":"Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for anomaly detection. However, such strategies inevitably discard geometric details and exhibit limited sensitivity to local anomalies. In this paper, we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection. We propose BT"},"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":"2603.21511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-23T02:59:00Z","cross_cats_sorted":[],"title_canon_sha256":"9a55ebcbd64ee4bb0c16c03a276a05de2902f090ade3d08b6e808f4bce077595","abstract_canon_sha256":"c91b25bc97bf41964062ad35cadac023147d10a9616f82e57c480f63faba7ef9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:24.604685Z","signature_b64":"4w8Z+omCVkq3AIV7HL4GsGqz4haomfZaewCZlcOELmQLNWPlMlzwZ6HobWM2iaLvHHsqRp2G3LN5iu2mIGOPDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325030c4c253c4b6edf06d054d1efa2056b0d3195dc3f64cbfdbf8fbfd584298","last_reissued_at":"2026-06-09T02:07:24.603729Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:24.603729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back to Point: Exploring Point-Language Models for Zero-Shot 3D Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Delong Han, Gang Li, Jin Wan, Kaiqiang Li, Mingle Zhou, Min Li","submitted_at":"2026-03-23T02:59:00Z","abstract_excerpt":"Zero-shot (ZS) 3D anomaly detection is crucial for reliable industrial inspection, as it enables detecting and localizing defects without requiring any target-category training data. Existing approaches render 3D point clouds into 2D images and leverage pre-trained Vision-Language Models (VLMs) for anomaly detection. However, such strategies inevitably discard geometric details and exhibit limited sensitivity to local anomalies. In this paper, we revisit intrinsic 3D representations and explore the potential of pre-trained Point-Language Models (PLMs) for ZS 3D anomaly detection. We propose BT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.21511","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/2603.21511/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":"2603.21511","created_at":"2026-06-09T02:07:24.603901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.21511v2","created_at":"2026-06-09T02:07:24.603901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.21511","created_at":"2026-06-09T02:07:24.603901+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJIDBRGCKPCL","created_at":"2026-06-09T02:07:24.603901+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJIDBRGCKPCLN3PQ","created_at":"2026-06-09T02:07:24.603901+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJIDBRGC","created_at":"2026-06-09T02:07:24.603901+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/GJIDBRGCKPCLN3PQNUCU2HX2EB","json":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB.json","graph_json":"https://pith.science/api/pith-number/GJIDBRGCKPCLN3PQNUCU2HX2EB/graph.json","events_json":"https://pith.science/api/pith-number/GJIDBRGCKPCLN3PQNUCU2HX2EB/events.json","paper":"https://pith.science/paper/GJIDBRGC"},"agent_actions":{"view_html":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB","download_json":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB.json","view_paper":"https://pith.science/paper/GJIDBRGC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.21511&json=true","fetch_graph":"https://pith.science/api/pith-number/GJIDBRGCKPCLN3PQNUCU2HX2EB/graph.json","fetch_events":"https://pith.science/api/pith-number/GJIDBRGCKPCLN3PQNUCU2HX2EB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB/action/storage_attestation","attest_author":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB/action/author_attestation","sign_citation":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB/action/citation_signature","submit_replication":"https://pith.science/pith/GJIDBRGCKPCLN3PQNUCU2HX2EB/action/replication_record"}},"created_at":"2026-06-09T02:07:24.603901+00:00","updated_at":"2026-06-09T02:07:24.603901+00:00"}