{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FDOCL6CLMEMREYIVIY62AZBPQB","short_pith_number":"pith:FDOCL6CL","schema_version":"1.0","canonical_sha256":"28dc25f84b6119126115463da0642f8050294d838c92bca1e0d99291d96724aa","source":{"kind":"arxiv","id":"2412.06510","version":4},"attestation_state":"computed","paper":{"title":"AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Wang, Lei Liu, Shen Zhao, Shidan He, Xiujun Shu, Yuanhao Feng","submitted_at":"2024-12-09T14:13:21Z","abstract_excerpt":"Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual information or coarse-aligned visual features to guide the entire generation process. However, these methods often lack sufficient descriptors to capture the complicated characteristics of realistic anomalies (e.g., the fine-grained visual pattern of anomalies), limiting the realism and generalization of the generation process. To this end, we propose a novel a"},"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":"2412.06510","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-09T14:13:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff1ba28b3f7dd2b475a5b0f0435fa5ca0273ce439d5fdcd7084636dcf8bbce10","abstract_canon_sha256":"aae53746ecb93c2e6659e773605f94b6f4b228184f81368e083c9e3f4645fe60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:48.618349Z","signature_b64":"yEXzBvFhC+iyenv2i74vrJqFe2YWbWe7O2gWiCCtgvzx8Wcni6tCHUwWBRCaoGcwIZvGx7/9hMoyH1cALm06Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28dc25f84b6119126115463da0642f8050294d838c92bca1e0d99291d96724aa","last_reissued_at":"2026-07-05T11:49:48.617883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:48.617883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AnomalyControl: Learning Cross-modal Semantic Features for Controllable Anomaly Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Wang, Lei Liu, Shen Zhao, Shidan He, Xiujun Shu, Yuanhao Feng","submitted_at":"2024-12-09T14:13:21Z","abstract_excerpt":"Anomaly synthesis is a crucial approach to augment abnormal data for advancing anomaly inspection. Based on the knowledge from the large-scale pre-training, existing text-to-image anomaly synthesis methods predominantly focus on textual information or coarse-aligned visual features to guide the entire generation process. However, these methods often lack sufficient descriptors to capture the complicated characteristics of realistic anomalies (e.g., the fine-grained visual pattern of anomalies), limiting the realism and generalization of the generation process. To this end, we propose a novel a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.06510","kind":"arxiv","version":4},"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/2412.06510/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":"2412.06510","created_at":"2026-07-05T11:49:48.617939+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.06510v4","created_at":"2026-07-05T11:49:48.617939+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.06510","created_at":"2026-07-05T11:49:48.617939+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDOCL6CLMEMR","created_at":"2026-07-05T11:49:48.617939+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDOCL6CLMEMREYIV","created_at":"2026-07-05T11:49:48.617939+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDOCL6CL","created_at":"2026-07-05T11:49:48.617939+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07579","citing_title":"NexViTAD: Few-shot Unsupervised Cross-Domain Defect Detection via Vision Foundation Models and Multi-Task Learning","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB","json":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB.json","graph_json":"https://pith.science/api/pith-number/FDOCL6CLMEMREYIVIY62AZBPQB/graph.json","events_json":"https://pith.science/api/pith-number/FDOCL6CLMEMREYIVIY62AZBPQB/events.json","paper":"https://pith.science/paper/FDOCL6CL"},"agent_actions":{"view_html":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB","download_json":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB.json","view_paper":"https://pith.science/paper/FDOCL6CL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.06510&json=true","fetch_graph":"https://pith.science/api/pith-number/FDOCL6CLMEMREYIVIY62AZBPQB/graph.json","fetch_events":"https://pith.science/api/pith-number/FDOCL6CLMEMREYIVIY62AZBPQB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB/action/storage_attestation","attest_author":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB/action/author_attestation","sign_citation":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB/action/citation_signature","submit_replication":"https://pith.science/pith/FDOCL6CLMEMREYIVIY62AZBPQB/action/replication_record"}},"created_at":"2026-07-05T11:49:48.617939+00:00","updated_at":"2026-07-05T11:49:48.617939+00:00"}