{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TOR7CXG3SRXOZEUI6GXI3ZQF75","short_pith_number":"pith:TOR7CXG3","schema_version":"1.0","canonical_sha256":"9ba3f15cdb946eec9288f1ae8de605ff4dab4edc3cf30ef8eebdcdd6956b8843","source":{"kind":"arxiv","id":"2503.18385","version":1},"attestation_state":"computed","paper":{"title":"RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hui Wang, Jie Sun, Rui Wang, Tianyu Wo, Xudong Liu, Xudong Mou","submitted_at":"2025-03-24T06:52:28Z","abstract_excerpt":"The accumulation of time-series signals and the absence of labels make time-series Anomaly Detection (AD) a self-supervised task of deep learning. Methods based on normality assumptions face the following three limitations: (1) A single assumption could hardly characterize the whole normality or lead to some deviation. (2) Some assumptions may go against the principle of AD. (3) Their basic assumption is that the training data is uncontaminated (free of anomalies), which is unrealistic in practice, leading to a decline in robustness. This paper proposes a novel robust approach, RoCA, which is "},"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":"2503.18385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T06:52:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6515e7597803b9ec8a60a33076232900fb023ca9487008b345200941fd988490","abstract_canon_sha256":"07646b37c18749fd1f14720218e386762e87f7b2ea0ec03c5f07cf98c9d3436f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:09.380700Z","signature_b64":"PpPgnkzf2pn85hK/utv8eO/tU8JOyLJCjJRBQI0a8NZtjT5JdDZ8eykqHRmUduirHWP1g/fDQzkWmB9YmPdYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ba3f15cdb946eec9288f1ae8de605ff4dab4edc3cf30ef8eebdcdd6956b8843","last_reissued_at":"2026-07-05T10:38:09.380057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:09.380057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Li, Hui Wang, Jie Sun, Rui Wang, Tianyu Wo, Xudong Liu, Xudong Mou","submitted_at":"2025-03-24T06:52:28Z","abstract_excerpt":"The accumulation of time-series signals and the absence of labels make time-series Anomaly Detection (AD) a self-supervised task of deep learning. Methods based on normality assumptions face the following three limitations: (1) A single assumption could hardly characterize the whole normality or lead to some deviation. (2) Some assumptions may go against the principle of AD. (3) Their basic assumption is that the training data is uncontaminated (free of anomalies), which is unrealistic in practice, leading to a decline in robustness. This paper proposes a novel robust approach, RoCA, which is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.18385","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/2503.18385/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":"2503.18385","created_at":"2026-07-05T10:38:09.380123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.18385v1","created_at":"2026-07-05T10:38:09.380123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.18385","created_at":"2026-07-05T10:38:09.380123+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOR7CXG3SRXO","created_at":"2026-07-05T10:38:09.380123+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOR7CXG3SRXOZEUI","created_at":"2026-07-05T10:38:09.380123+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOR7CXG3","created_at":"2026-07-05T10:38:09.380123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06419","citing_title":"CAPMix: Robust KPI Anomaly Detection for AIOps in Noisy and Dynamic Environments","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75","json":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75.json","graph_json":"https://pith.science/api/pith-number/TOR7CXG3SRXOZEUI6GXI3ZQF75/graph.json","events_json":"https://pith.science/api/pith-number/TOR7CXG3SRXOZEUI6GXI3ZQF75/events.json","paper":"https://pith.science/paper/TOR7CXG3"},"agent_actions":{"view_html":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75","download_json":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75.json","view_paper":"https://pith.science/paper/TOR7CXG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.18385&json=true","fetch_graph":"https://pith.science/api/pith-number/TOR7CXG3SRXOZEUI6GXI3ZQF75/graph.json","fetch_events":"https://pith.science/api/pith-number/TOR7CXG3SRXOZEUI6GXI3ZQF75/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75/action/storage_attestation","attest_author":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75/action/author_attestation","sign_citation":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75/action/citation_signature","submit_replication":"https://pith.science/pith/TOR7CXG3SRXOZEUI6GXI3ZQF75/action/replication_record"}},"created_at":"2026-07-05T10:38:09.380123+00:00","updated_at":"2026-07-05T10:38:09.380123+00:00"}