{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7H37TQILEOF75GQLWV27577LHE","short_pith_number":"pith:7H37TQIL","schema_version":"1.0","canonical_sha256":"f9f7f9c10b238bfe9a0bb575feffeb3938438ba8beffad0c06d2706f2aa77943","source":{"kind":"arxiv","id":"2501.14170","version":1},"attestation_state":"computed","paper":{"title":"Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Baris Kasikci, Jonathan Mace, Peng Cheng, Yifan Xiong, Yigong Hu, Yile Gu, Yuting Jiang","submitted_at":"2025-01-24T01:38:37Z","abstract_excerpt":"Observability in cloud infrastructure is critical for service providers, driving the widespread adoption of anomaly detection systems for monitoring metrics. However, existing systems often struggle to simultaneously achieve explainability, reproducibility, and autonomy, which are three indispensable properties for production use. We introduce Argos, an agentic system for detecting time-series anomalies in cloud infrastructure by leveraging large language models (LLMs). Argos proposes to use explainable and reproducible anomaly rules as intermediate representation and employs LLMs to autonomou"},"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":"2501.14170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-01-24T01:38:37Z","cross_cats_sorted":["cs.DC","cs.MA"],"title_canon_sha256":"ade675bd046f7d506dadcb498c873ea54ad43b70d740e0a59fde7b78434840c9","abstract_canon_sha256":"b61f8e01f1e28c654c51f53c83c1ef252e0158751f7f239de5fcc494d2ed120f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:46.602987Z","signature_b64":"3kHIBTcZR6XxcP9BxoyF78TXotvVAmvOYVoyDMdYGzUxw+7nv7jAqNhopdvIwCHNkSYq3VP3B2u+JReck0l5CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f7f9c10b238bfe9a0bb575feffeb3938438ba8beffad0c06d2706f2aa77943","last_reissued_at":"2026-07-05T10:04:46.602473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:46.602473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.MA"],"primary_cat":"cs.LG","authors_text":"Baris Kasikci, Jonathan Mace, Peng Cheng, Yifan Xiong, Yigong Hu, Yile Gu, Yuting Jiang","submitted_at":"2025-01-24T01:38:37Z","abstract_excerpt":"Observability in cloud infrastructure is critical for service providers, driving the widespread adoption of anomaly detection systems for monitoring metrics. However, existing systems often struggle to simultaneously achieve explainability, reproducibility, and autonomy, which are three indispensable properties for production use. We introduce Argos, an agentic system for detecting time-series anomalies in cloud infrastructure by leveraging large language models (LLMs). Argos proposes to use explainable and reproducible anomaly rules as intermediate representation and employs LLMs to autonomou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14170","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/2501.14170/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":"2501.14170","created_at":"2026-07-05T10:04:46.602541+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14170v1","created_at":"2026-07-05T10:04:46.602541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14170","created_at":"2026-07-05T10:04:46.602541+00:00"},{"alias_kind":"pith_short_12","alias_value":"7H37TQILEOF7","created_at":"2026-07-05T10:04:46.602541+00:00"},{"alias_kind":"pith_short_16","alias_value":"7H37TQILEOF75GQL","created_at":"2026-07-05T10:04:46.602541+00:00"},{"alias_kind":"pith_short_8","alias_value":"7H37TQIL","created_at":"2026-07-05T10:04:46.602541+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28371","citing_title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2506.11512","citing_title":"From Time Series Analysis to Question Answering: A Survey in the LLM Era","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23966","citing_title":"Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE","json":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE.json","graph_json":"https://pith.science/api/pith-number/7H37TQILEOF75GQLWV27577LHE/graph.json","events_json":"https://pith.science/api/pith-number/7H37TQILEOF75GQLWV27577LHE/events.json","paper":"https://pith.science/paper/7H37TQIL"},"agent_actions":{"view_html":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE","download_json":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE.json","view_paper":"https://pith.science/paper/7H37TQIL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14170&json=true","fetch_graph":"https://pith.science/api/pith-number/7H37TQILEOF75GQLWV27577LHE/graph.json","fetch_events":"https://pith.science/api/pith-number/7H37TQILEOF75GQLWV27577LHE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE/action/storage_attestation","attest_author":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE/action/author_attestation","sign_citation":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE/action/citation_signature","submit_replication":"https://pith.science/pith/7H37TQILEOF75GQLWV27577LHE/action/replication_record"}},"created_at":"2026-07-05T10:04:46.602541+00:00","updated_at":"2026-07-05T10:04:46.602541+00:00"}