{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XYMA55LSZXW5E4DGQCR3A7DZBP","short_pith_number":"pith:XYMA55LS","schema_version":"1.0","canonical_sha256":"be180ef572cdedd2706680a3b07c790bd63589e269645879aa96b47de593c440","source":{"kind":"arxiv","id":"2407.01312","version":1},"attestation_state":"computed","paper":{"title":"ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anyang Su, Donglin Di, Junjie Huang, Lei Fan, Yun Liang, Zhiguang Hu","submitted_at":"2024-07-01T14:19:36Z","abstract_excerpt":"Current unsupervised anomaly detection approaches perform well on public datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains. To tackle this issue, this paper presents a two-stage training strategy, called \\textbf{ToCoAD}. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive le"},"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":"2407.01312","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-01T14:19:36Z","cross_cats_sorted":[],"title_canon_sha256":"00bcb607fba18c80fd42d73c6a3ba793da487ae912c3892d24f26f7583dc1ea6","abstract_canon_sha256":"7b77bf00fd5687d01c95c70b7138b9d6a938053d991cd744928d83303bd5d9a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:46.165366Z","signature_b64":"QCCZkMxvXXqiammibL9yWAO0d9qeR1XezCcScZltg2+4Lz0m3cQtyVIzV+9/arsa85tv2h1cdt9m5WGDOq3RAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be180ef572cdedd2706680a3b07c790bd63589e269645879aa96b47de593c440","last_reissued_at":"2026-07-05T08:38:46.164908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:46.164908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anyang Su, Donglin Di, Junjie Huang, Lei Fan, Yun Liang, Zhiguang Hu","submitted_at":"2024-07-01T14:19:36Z","abstract_excerpt":"Current unsupervised anomaly detection approaches perform well on public datasets but struggle with specific anomaly types due to the domain gap between pre-trained feature extractors and target-specific domains. To tackle this issue, this paper presents a two-stage training strategy, called \\textbf{ToCoAD}. In the first stage, a discriminative network is trained by using synthetic anomalies in a self-supervised learning manner. This network is then utilized in the second stage to provide a negative feature guide, aiding in the training of the feature extractor through bootstrap contrastive le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01312","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/2407.01312/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":"2407.01312","created_at":"2026-07-05T08:38:46.164975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01312v1","created_at":"2026-07-05T08:38:46.164975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01312","created_at":"2026-07-05T08:38:46.164975+00:00"},{"alias_kind":"pith_short_12","alias_value":"XYMA55LSZXW5","created_at":"2026-07-05T08:38:46.164975+00:00"},{"alias_kind":"pith_short_16","alias_value":"XYMA55LSZXW5E4DG","created_at":"2026-07-05T08:38:46.164975+00:00"},{"alias_kind":"pith_short_8","alias_value":"XYMA55LS","created_at":"2026-07-05T08:38:46.164975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05107","citing_title":"CL-ISR: A Contrastive Learning and Implicit Stance Reasoning Framework for Misleading Text Detection on Social Media","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP","json":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP.json","graph_json":"https://pith.science/api/pith-number/XYMA55LSZXW5E4DGQCR3A7DZBP/graph.json","events_json":"https://pith.science/api/pith-number/XYMA55LSZXW5E4DGQCR3A7DZBP/events.json","paper":"https://pith.science/paper/XYMA55LS"},"agent_actions":{"view_html":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP","download_json":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP.json","view_paper":"https://pith.science/paper/XYMA55LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01312&json=true","fetch_graph":"https://pith.science/api/pith-number/XYMA55LSZXW5E4DGQCR3A7DZBP/graph.json","fetch_events":"https://pith.science/api/pith-number/XYMA55LSZXW5E4DGQCR3A7DZBP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP/action/storage_attestation","attest_author":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP/action/author_attestation","sign_citation":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP/action/citation_signature","submit_replication":"https://pith.science/pith/XYMA55LSZXW5E4DGQCR3A7DZBP/action/replication_record"}},"created_at":"2026-07-05T08:38:46.164975+00:00","updated_at":"2026-07-05T08:38:46.164975+00:00"}