{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PE4SXUZN6EP3GJ6ZQIWE7CBDIH","short_pith_number":"pith:PE4SXUZN","schema_version":"1.0","canonical_sha256":"79392bd32df11fb327d9822c4f882341ff914bf1160269c1caa1c5ffcb352c69","source":{"kind":"arxiv","id":"2502.03245","version":2},"attestation_state":"computed","paper":{"title":"Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.LG","authors_text":"Amir G. Aghdam, Saba Sanami","submitted_at":"2025-02-05T15:02:40Z","abstract_excerpt":"This paper investigates unsupervised anomaly detection in multivariate time-series data using reinforcement learning (RL) in the latent space of an autoencoder. A significant challenge is the limited availability of anomalous data, often leading to misclassifying anomalies as normal events, thus raising false negatives. RL can help overcome this limitation by promoting exploration and balancing exploitation during training, effectively preventing overfitting. Wavelet analysis is also utilized to enhance anomaly detection, enabling time-series data decomposition into both time and frequency dom"},"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":"2502.03245","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T15:02:40Z","cross_cats_sorted":["cs.SY","eess.SP","eess.SY"],"title_canon_sha256":"7b09173d84ba0ca06daeda3443116cea0e034fa4af33e7e46d04b9554bf2f96e","abstract_canon_sha256":"ffd884fc7537d3bc07e9914bbf0e9ff674f581438275bac1183334bacecd2d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:03.878632Z","signature_b64":"ZbbywBHoka3m7+cXuYgQd6zgIaL3dwG1RJ8GisSHFlg0XuKQiNOINQq2xi/RkrDToPyvv87vkn+W/EeiQpfQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79392bd32df11fb327d9822c4f882341ff914bf1160269c1caa1c5ffcb352c69","last_reissued_at":"2026-07-05T10:12:03.878148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:03.878148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SP","eess.SY"],"primary_cat":"cs.LG","authors_text":"Amir G. Aghdam, Saba Sanami","submitted_at":"2025-02-05T15:02:40Z","abstract_excerpt":"This paper investigates unsupervised anomaly detection in multivariate time-series data using reinforcement learning (RL) in the latent space of an autoencoder. A significant challenge is the limited availability of anomalous data, often leading to misclassifying anomalies as normal events, thus raising false negatives. RL can help overcome this limitation by promoting exploration and balancing exploitation during training, effectively preventing overfitting. Wavelet analysis is also utilized to enhance anomaly detection, enabling time-series data decomposition into both time and frequency dom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03245","kind":"arxiv","version":2},"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/2502.03245/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":"2502.03245","created_at":"2026-07-05T10:12:03.878206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.03245v2","created_at":"2026-07-05T10:12:03.878206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03245","created_at":"2026-07-05T10:12:03.878206+00:00"},{"alias_kind":"pith_short_12","alias_value":"PE4SXUZN6EP3","created_at":"2026-07-05T10:12:03.878206+00:00"},{"alias_kind":"pith_short_16","alias_value":"PE4SXUZN6EP3GJ6Z","created_at":"2026-07-05T10:12:03.878206+00:00"},{"alias_kind":"pith_short_8","alias_value":"PE4SXUZN","created_at":"2026-07-05T10:12:03.878206+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/PE4SXUZN6EP3GJ6ZQIWE7CBDIH","json":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH.json","graph_json":"https://pith.science/api/pith-number/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/graph.json","events_json":"https://pith.science/api/pith-number/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/events.json","paper":"https://pith.science/paper/PE4SXUZN"},"agent_actions":{"view_html":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH","download_json":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH.json","view_paper":"https://pith.science/paper/PE4SXUZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.03245&json=true","fetch_graph":"https://pith.science/api/pith-number/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/graph.json","fetch_events":"https://pith.science/api/pith-number/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/action/storage_attestation","attest_author":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/action/author_attestation","sign_citation":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/action/citation_signature","submit_replication":"https://pith.science/pith/PE4SXUZN6EP3GJ6ZQIWE7CBDIH/action/replication_record"}},"created_at":"2026-07-05T10:12:03.878206+00:00","updated_at":"2026-07-05T10:12:03.878206+00:00"}