{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KE23MVCR35QTJPBDSXG2EBWLE7","short_pith_number":"pith:KE23MVCR","schema_version":"1.0","canonical_sha256":"5135b65451df6134bc2395cda206cb27d3eab80ac2afed55bac299ac7e2ed5c3","source":{"kind":"arxiv","id":"2607.11969","version":1},"attestation_state":"computed","paper":{"title":"Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Zongye Lyu","submitted_at":"2026-07-12T22:33:07Z","abstract_excerpt":"Point-adjustment (PA), long the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al. (2022) to award near-perfect F1 to random scores. The field migrated to replacement metrics: PA%K, range-based precision/recall, affiliation precision/recall, and Volume-Under-the-Surface (VUS) ROC/PR. But did the fix work? Every robustness check to date is proposer-run or theoretical; no independent, adversarial, SOTA-relative audit on real benchmarks exists. We provide one. We stress-test 12 adopted metrics against trivial and adversarial no-skill score generators on the "},"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":"2607.11969","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-07-12T22:33:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb269588b583b6fd35e1a941e7e48f77a55ba37fc6d57e0ec231e3e1728c954f","abstract_canon_sha256":"c5809e06db1ba3e8838bc11ae2aba669ef9c39eda303b1428afb2096b49ef9fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-15T00:21:25.383275Z","signature_b64":"IYXzzyqU3nAJuJiJeQ9h2j0fGJXeIBnHNndZ1oGT4KZlmJbD7WQs++ih3JeiIsg9jujH4cEMCvMcyxwge2R+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5135b65451df6134bc2395cda206cb27d3eab80ac2afed55bac299ac7e2ed5c3","last_reissued_at":"2026-07-15T00:21:25.382439Z","signature_status":"signed_v1","first_computed_at":"2026-07-15T00:21:25.382439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Did We Actually Fix It? An Independent Adversarial Stress-Test of Post-Point-Adjustment Evaluation Metrics for Time-Series Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Zongye Lyu","submitted_at":"2026-07-12T22:33:07Z","abstract_excerpt":"Point-adjustment (PA), long the default scoring protocol in time-series anomaly detection (TSAD), was shown by Kim et al. (2022) to award near-perfect F1 to random scores. The field migrated to replacement metrics: PA%K, range-based precision/recall, affiliation precision/recall, and Volume-Under-the-Surface (VUS) ROC/PR. But did the fix work? Every robustness check to date is proposer-run or theoretical; no independent, adversarial, SOTA-relative audit on real benchmarks exists. We provide one. We stress-test 12 adopted metrics against trivial and adversarial no-skill score generators on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11969","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/2607.11969/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":"2607.11969","created_at":"2026-07-15T00:21:25.382878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11969v1","created_at":"2026-07-15T00:21:25.382878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11969","created_at":"2026-07-15T00:21:25.382878+00:00"},{"alias_kind":"pith_short_12","alias_value":"KE23MVCR35QT","created_at":"2026-07-15T00:21:25.382878+00:00"},{"alias_kind":"pith_short_16","alias_value":"KE23MVCR35QTJPBD","created_at":"2026-07-15T00:21:25.382878+00:00"},{"alias_kind":"pith_short_8","alias_value":"KE23MVCR","created_at":"2026-07-15T00:21:25.382878+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/KE23MVCR35QTJPBDSXG2EBWLE7","json":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7.json","graph_json":"https://pith.science/api/pith-number/KE23MVCR35QTJPBDSXG2EBWLE7/graph.json","events_json":"https://pith.science/api/pith-number/KE23MVCR35QTJPBDSXG2EBWLE7/events.json","paper":"https://pith.science/paper/KE23MVCR"},"agent_actions":{"view_html":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7","download_json":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7.json","view_paper":"https://pith.science/paper/KE23MVCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11969&json=true","fetch_graph":"https://pith.science/api/pith-number/KE23MVCR35QTJPBDSXG2EBWLE7/graph.json","fetch_events":"https://pith.science/api/pith-number/KE23MVCR35QTJPBDSXG2EBWLE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7/action/storage_attestation","attest_author":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7/action/author_attestation","sign_citation":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7/action/citation_signature","submit_replication":"https://pith.science/pith/KE23MVCR35QTJPBDSXG2EBWLE7/action/replication_record"}},"created_at":"2026-07-15T00:21:25.382878+00:00","updated_at":"2026-07-15T00:21:25.382878+00:00"}