{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZANPQFQENNY4XCSUNJ5LNDFLCJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1777b9c95f1f97ed4c527c589d7e475f02b540b453f530eadb29bf856351e30b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T04:09:04Z","title_canon_sha256":"9b11092db4fec8952fa64938ae3a40ec6a48d8c79f11e1be65bb2b85918716db"},"schema_version":"1.0","source":{"id":"2511.18739","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.18739","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"arxiv_version","alias_value":"2511.18739v2","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.18739","created_at":"2026-05-17T23:39:17Z"},{"alias_kind":"pith_short_12","alias_value":"ZANPQFQENNY4","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"ZANPQFQENNY4XCSU","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"ZANPQFQE","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:39d859dcc85195432b1bc00541a3f451bdd5c309ea8fe12688a4bec1b7b767e4","target":"graph","created_at":"2026-05-17T23:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"The results show that while most event-level metrics exhibit strong separability, several widely used metrics (e.g., NAB, Point-Adjust) demonstrate limited resistance to random-score inflation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the six proposed dimensions capture the main evaluation challenges and that the genuine/random/oracle experimental scenarios sufficiently represent real application behavior without additional confounding factors."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A problem-oriented taxonomy groups anomaly detection metrics into six dimensions and experiments show that some popular ones like NAB and Point-Adjust fail to resist random-score inflation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A problem-oriented taxonomy of time series anomaly detection metrics finds that most separate real detections from noise but NAB and Point-Adjust inflate easily under random scores."}],"snapshot_sha256":"e067e1e76bffad5e570c1654804b9ab568b4a4aaecf083a27bcc3a5c7cba9e9f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Time series anomaly detection is widely used in IoT and cyber-physical systems, yet its evaluation remains challenging due to diverse application objectives and heterogeneous metric assumptions. This study introduces a problem-oriented framework that reinterprets existing metrics based on the specific evaluation challenges they are designed to address, rather than their mathematical forms or output structures. We categorize over twenty commonly used metrics into six dimensions: 1) basic accuracy-driven evaluation; 2) timeliness-aware reward mechanisms; 3) tolerance to labeling imprecision; 4) ","authors_text":"Jiarong Liu, Kaixiang Yang, Shuanghua Yang, Yujue Zhou, Yupeng Song","cross_cats":["cs.LG","stat.ML"],"headline":"A problem-oriented taxonomy of time series anomaly detection metrics finds that most separate real detections from noise but NAB and Point-Adjust inflate easily under random scores.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T04:09:04Z","title":"A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly Detection"},"references":{"count":51,"internal_anchors":0,"resolved_work":51,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Anomaly detection for iot time- series data: A survey,","work_id":"17e777af-1517-4e4a-8d5d-fd86f7f9b0a1","year":2019},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Iot platforms: enabling the internet of things,","work_id":"d2993d78-0144-4990-886e-240e7b9d5a46","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Idc forecasts connected iot devices to generate 79.4 zb of data in 2025,","work_id":"aad2e2a9-da5e-470e-b920-e686f202f491","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Time series anomaly detection for cyber-physical systems via neural system identification and bayesian filtering,","work_id":"d1815392-2b55-4bbf-a80d-7922eb7f1e59","year":2021},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Mac: Measuring the impacts of anomalies on travel time of multiple transportation systems,","work_id":"c3dbaaaf-3461-40cb-99a9-c0ef54672b25","year":2019}],"snapshot_sha256":"1ef22056e5713733accf58eb7f2980acdba922079adf3ba94b938315d83a9a2c"},"source":{"id":"2511.18739","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T06:53:41.964049Z","id":"2c913dd0-291c-410c-8e9e-b5aa11cdddb6","model_set":{"reader":"grok-4.3"},"one_line_summary":"A problem-oriented taxonomy groups anomaly detection metrics into six dimensions and experiments show that some popular ones like NAB and Point-Adjust fail to resist random-score inflation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A problem-oriented taxonomy of time series anomaly detection metrics finds that most separate real detections from noise but NAB and Point-Adjust inflate easily under random scores.","strongest_claim":"The results show that while most event-level metrics exhibit strong separability, several widely used metrics (e.g., NAB, Point-Adjust) demonstrate limited resistance to random-score inflation.","weakest_assumption":"That the six proposed dimensions capture the main evaluation challenges and that the genuine/random/oracle experimental scenarios sufficiently represent real application behavior without additional confounding factors."}},"verdict_id":"2c913dd0-291c-410c-8e9e-b5aa11cdddb6"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2227b76cd3ace271aaeb8885390beb97eb6571ea529980e6882a42faf5c44fe4","target":"record","created_at":"2026-05-17T23:39:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1777b9c95f1f97ed4c527c589d7e475f02b540b453f530eadb29bf856351e30b","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-11-24T04:09:04Z","title_canon_sha256":"9b11092db4fec8952fa64938ae3a40ec6a48d8c79f11e1be65bb2b85918716db"},"schema_version":"1.0","source":{"id":"2511.18739","kind":"arxiv","version":2}},"canonical_sha256":"c81af816046b71cb8a546a7ab68cab127609eed2841d90f24821100c030bae1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c81af816046b71cb8a546a7ab68cab127609eed2841d90f24821100c030bae1a","first_computed_at":"2026-05-17T23:39:17.052381Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:17.052381Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LZYmgdDJeLt0S2NOl1hDHE7fzscB7Yx6iP5I8c/MSyHa1iduWLHgob+i11GVdeAtaGBxsEvfipxnwe4ouPA/Bg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:17.053472Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.18739","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2227b76cd3ace271aaeb8885390beb97eb6571ea529980e6882a42faf5c44fe4","sha256:39d859dcc85195432b1bc00541a3f451bdd5c309ea8fe12688a4bec1b7b767e4"],"state_sha256":"da14c7965a6920f65c5a0f3f6ca93ff7e8762d28e97ffa5747cb0af1a80da742"}