{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NCL4GC3KUCB7D4B57LMB4L2ALJ","short_pith_number":"pith:NCL4GC3K","schema_version":"1.0","canonical_sha256":"6897c30b6aa083f1f03dfad81e2f405a4a47c1bccb37e5e537d393363b6fa6d0","source":{"kind":"arxiv","id":"2607.22286","version":1},"attestation_state":"computed","paper":{"title":"An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Djamila Aouada, Nesryne Mejri, Romain Hermary","submitted_at":"2026-07-24T13:25:06Z","abstract_excerpt":"Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC, AUPR, F1-score, and MCC are widely used, their values convey different meanings depending on the anomaly ratio. In this work, we analyse the behaviour of those four common anomaly detection metrics under varying levels of imbalance. We focus on the study of metric landscapes, visualisations that relate metric values to true positive and true negative rates, providing an intuitive view of metric preferences and stability. Our analy"},"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":"2607.22286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-24T13:25:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0063f2ba328620c1d7bedf91e3254e2835676cb3e24c2c66779c777b16b60530","abstract_canon_sha256":"04729bba567bf0d5c9efc5b6a2184c21c6ae47a54d7e0f7cb27b01121872aa43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-27T01:20:57.866239Z","signature_b64":"N+hLIi+YcCapmeK6CoqLjU3So6uGHHzSKnodzgu3v1iQ0dlqBb8FiFRof59vgi8SY5oAB+oE5grLnookU/YNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6897c30b6aa083f1f03dfad81e2f405a4a47c1bccb37e5e537d393363b6fa6d0","last_reissued_at":"2026-07-27T01:20:57.865322Z","signature_status":"signed_v1","first_computed_at":"2026-07-27T01:20:57.865322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Insight on Evaluation Metrics Under the Imbalanced Case of Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Djamila Aouada, Nesryne Mejri, Romain Hermary","submitted_at":"2026-07-24T13:25:06Z","abstract_excerpt":"Anomaly detection is inherently characterised by severe class imbalance, making the interpretation of evaluation metrics challenging. Although metrics such as AUROC, AUPR, F1-score, and MCC are widely used, their values convey different meanings depending on the anomaly ratio. In this work, we analyse the behaviour of those four common anomaly detection metrics under varying levels of imbalance. We focus on the study of metric landscapes, visualisations that relate metric values to true positive and true negative rates, providing an intuitive view of metric preferences and stability. Our analy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22286","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/2607.22286/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":"2607.22286","created_at":"2026-07-27T01:20:57.865811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.22286v1","created_at":"2026-07-27T01:20:57.865811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22286","created_at":"2026-07-27T01:20:57.865811+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCL4GC3KUCB7","created_at":"2026-07-27T01:20:57.865811+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCL4GC3KUCB7D4B5","created_at":"2026-07-27T01:20:57.865811+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCL4GC3K","created_at":"2026-07-27T01:20:57.865811+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/NCL4GC3KUCB7D4B57LMB4L2ALJ","json":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ.json","graph_json":"https://pith.science/api/pith-number/NCL4GC3KUCB7D4B57LMB4L2ALJ/graph.json","events_json":"https://pith.science/api/pith-number/NCL4GC3KUCB7D4B57LMB4L2ALJ/events.json","paper":"https://pith.science/paper/NCL4GC3K"},"agent_actions":{"view_html":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ","download_json":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ.json","view_paper":"https://pith.science/paper/NCL4GC3K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.22286&json=true","fetch_graph":"https://pith.science/api/pith-number/NCL4GC3KUCB7D4B57LMB4L2ALJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NCL4GC3KUCB7D4B57LMB4L2ALJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ/action/storage_attestation","attest_author":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ/action/author_attestation","sign_citation":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ/action/citation_signature","submit_replication":"https://pith.science/pith/NCL4GC3KUCB7D4B57LMB4L2ALJ/action/replication_record"}},"created_at":"2026-07-27T01:20:57.865811+00:00","updated_at":"2026-07-27T01:20:57.865811+00:00"}