{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2CKSS3ATPCE7WWUZHSZFJQ7UGC","short_pith_number":"pith:2CKSS3AT","schema_version":"1.0","canonical_sha256":"d095296c137889fb5a993cb254c3f430910504d69ba9880496ba77be36ce9474","source":{"kind":"arxiv","id":"2203.05550","version":3},"attestation_state":"computed","paper":{"title":"Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eliahu Horwitz, Yedid Hoshen","submitted_at":"2022-03-10T18:57:04Z","abstract_excerpt":"Despite significant advances in image anomaly detection and segmentation, few methods use 3D information. We utilize a recently introduced 3D anomaly detection dataset to evaluate whether or not using 3D information is a lost opportunity. First, we present a surprising finding: standard color-only methods outperform all current methods that are explicitly designed to exploit 3D information. This is counter-intuitive as even a simple inspection of the dataset shows that color-only methods are insufficient for images containing geometric anomalies. This motivates the question: how can anomaly de"},"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":"2203.05550","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-10T18:57:04Z","cross_cats_sorted":[],"title_canon_sha256":"ebefa7c78c61d13d24c76872f6a13a1b3ad1fee424faffb5cd71698251664969","abstract_canon_sha256":"59fa667b119c4010897d2e25a29715649ad31ca3f1cd3ed2167e843a9f33aa1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:19:52.090777Z","signature_b64":"K9mNZxpVPf8N3McY8F/7s2KL4ay4rBSmoNLH1XhqcRmqEOEkgdYQAwB5mg4UguKaU9mS4nMi8UMHuM6hge+hDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d095296c137889fb5a993cb254c3f430910504d69ba9880496ba77be36ce9474","last_reissued_at":"2026-07-05T05:19:52.090296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:19:52.090296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eliahu Horwitz, Yedid Hoshen","submitted_at":"2022-03-10T18:57:04Z","abstract_excerpt":"Despite significant advances in image anomaly detection and segmentation, few methods use 3D information. We utilize a recently introduced 3D anomaly detection dataset to evaluate whether or not using 3D information is a lost opportunity. First, we present a surprising finding: standard color-only methods outperform all current methods that are explicitly designed to exploit 3D information. This is counter-intuitive as even a simple inspection of the dataset shows that color-only methods are insufficient for images containing geometric anomalies. This motivates the question: how can anomaly de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.05550","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/2203.05550/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":"2203.05550","created_at":"2026-07-05T05:19:52.090365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.05550v3","created_at":"2026-07-05T05:19:52.090365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.05550","created_at":"2026-07-05T05:19:52.090365+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CKSS3ATPCE7","created_at":"2026-07-05T05:19:52.090365+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CKSS3ATPCE7WWUZ","created_at":"2026-07-05T05:19:52.090365+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CKSS3AT","created_at":"2026-07-05T05:19:52.090365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26868","citing_title":"Breaking the Rigid Prior: Towards Articulated 3D Anomaly Detection","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC","json":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC.json","graph_json":"https://pith.science/api/pith-number/2CKSS3ATPCE7WWUZHSZFJQ7UGC/graph.json","events_json":"https://pith.science/api/pith-number/2CKSS3ATPCE7WWUZHSZFJQ7UGC/events.json","paper":"https://pith.science/paper/2CKSS3AT"},"agent_actions":{"view_html":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC","download_json":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC.json","view_paper":"https://pith.science/paper/2CKSS3AT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.05550&json=true","fetch_graph":"https://pith.science/api/pith-number/2CKSS3ATPCE7WWUZHSZFJQ7UGC/graph.json","fetch_events":"https://pith.science/api/pith-number/2CKSS3ATPCE7WWUZHSZFJQ7UGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC/action/storage_attestation","attest_author":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC/action/author_attestation","sign_citation":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC/action/citation_signature","submit_replication":"https://pith.science/pith/2CKSS3ATPCE7WWUZHSZFJQ7UGC/action/replication_record"}},"created_at":"2026-07-05T05:19:52.090365+00:00","updated_at":"2026-07-05T05:19:52.090365+00:00"}