{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DHMOXA56GC2YFZLIYFIZUPPBN5","short_pith_number":"pith:DHMOXA56","schema_version":"1.0","canonical_sha256":"19d8eb83be30b582e568c1519a3de16f4644da9aa2419f57a9bf4e5668a404da","source":{"kind":"arxiv","id":"2207.14315","version":1},"attestation_state":"computed","paper":{"title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongqing Zhang, Jongheon Jeong, Latha Pemula, Onkar Dabeer, Yang Zou","submitted_at":"2022-07-28T18:00:03Z","abstract_excerpt":"Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2-class 5/10/high-shot training setups. We release the Visual Anomaly (VisA) Dataset consisting of 10,821 high-resolution color images (9,621 normal and 1,200 anomalous samples) covering 12 objects in 3 domains, making it the largest industrial anomaly detection dataset to date. Both image and pixel-level labels are provided. We also propose a ne"},"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":"2207.14315","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-28T18:00:03Z","cross_cats_sorted":[],"title_canon_sha256":"58b0675a38e142e4b0b72ba41f4569f0f4ea5f7559ab8569fc6da9126ec6a98c","abstract_canon_sha256":"f4c9c8db68614d9fd4f1fe4be588d325ba792a18cdd8bbff5d0f9572f3113cd5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:44:32.804537Z","signature_b64":"FoRYwPlBiltX2nk5nhKBoySmJwxG2ADhG16lRSbHQ5pJcYStb25IZ+4zz74k/KJAKhYch55LHhPJOprNE/KHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19d8eb83be30b582e568c1519a3de16f4644da9aa2419f57a9bf4e5668a404da","last_reissued_at":"2026-07-05T04:44:32.804111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:44:32.804111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dongqing Zhang, Jongheon Jeong, Latha Pemula, Onkar Dabeer, Yang Zou","submitted_at":"2022-07-28T18:00:03Z","abstract_excerpt":"Visual anomaly detection is commonly used in industrial quality inspection. In this paper, we present a new dataset as well as a new self-supervised learning method for ImageNet pre-training to improve anomaly detection and segmentation in 1-class and 2-class 5/10/high-shot training setups. We release the Visual Anomaly (VisA) Dataset consisting of 10,821 high-resolution color images (9,621 normal and 1,200 anomalous samples) covering 12 objects in 3 domains, making it the largest industrial anomaly detection dataset to date. Both image and pixel-level labels are provided. We also propose a ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.14315","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/2207.14315/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":"2207.14315","created_at":"2026-07-05T04:44:32.804167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.14315v1","created_at":"2026-07-05T04:44:32.804167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.14315","created_at":"2026-07-05T04:44:32.804167+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHMOXA56GC2Y","created_at":"2026-07-05T04:44:32.804167+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHMOXA56GC2YFZLI","created_at":"2026-07-05T04:44:32.804167+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHMOXA56","created_at":"2026-07-05T04:44:32.804167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.02905","citing_title":"UniSpector: Towards Universal Open-set Defect Recognition via Spectral-Contrastive Visual Prompting","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07802","citing_title":"Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5","json":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5.json","graph_json":"https://pith.science/api/pith-number/DHMOXA56GC2YFZLIYFIZUPPBN5/graph.json","events_json":"https://pith.science/api/pith-number/DHMOXA56GC2YFZLIYFIZUPPBN5/events.json","paper":"https://pith.science/paper/DHMOXA56"},"agent_actions":{"view_html":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5","download_json":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5.json","view_paper":"https://pith.science/paper/DHMOXA56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.14315&json=true","fetch_graph":"https://pith.science/api/pith-number/DHMOXA56GC2YFZLIYFIZUPPBN5/graph.json","fetch_events":"https://pith.science/api/pith-number/DHMOXA56GC2YFZLIYFIZUPPBN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5/action/storage_attestation","attest_author":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5/action/author_attestation","sign_citation":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5/action/citation_signature","submit_replication":"https://pith.science/pith/DHMOXA56GC2YFZLIYFIZUPPBN5/action/replication_record"}},"created_at":"2026-07-05T04:44:32.804167+00:00","updated_at":"2026-07-05T04:44:32.804167+00:00"}