{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OYRH24A57R5OTOCDIBAD3CPXIO","short_pith_number":"pith:OYRH24A5","schema_version":"1.0","canonical_sha256":"76227d701dfc7ae9b84340403d89f743bd7a88e122caff43f0666b9af3da3b01","source":{"kind":"arxiv","id":"2505.12594","version":1},"attestation_state":"computed","paper":{"title":"AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjuan Song, Cheng cheng, Jiahang Wang, Junjun Liu, Tiankai Yang, Wingchun Siu, Xiyang Hu, Yue Zhao, Zhuangzhuang Qian","submitted_at":"2025-05-19T01:14:57Z","abstract_excerpt":"Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for non-expert users who lack in-depth library-specific knowledge and advanced programming skills. To tackle this, we present AD-AGENT, an LLM-driven multi-agent framework that turns natural-language instructions into fully executable AD pipelines. AD-AGENT coordinates specialized agents for intent parsing, data preparation, library and model selection, documentation min"},"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":"2505.12594","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T01:14:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f5e5d48c6ee8d509724b1fcafdc560617ebd7700ff87aee7206b2591d02b9522","abstract_canon_sha256":"faf791f7ac6118b39b2498a8894c1f0c03ef3e452ad870dcdcf67a2a2daa5d85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:06.617811Z","signature_b64":"dbJ02qlooJHFGBzhJ54zzU2dKvhhbo2BMfJPsGrEmTax2fqYGZ+wPKj9SYFFZIqDjAtzTCJVP3HXF3fL5ggfBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76227d701dfc7ae9b84340403d89f743bd7a88e122caff43f0666b9af3da3b01","last_reissued_at":"2026-07-05T11:05:06.617271Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:06.617271Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chanjuan Song, Cheng cheng, Jiahang Wang, Junjun Liu, Tiankai Yang, Wingchun Siu, Xiyang Hu, Yue Zhao, Zhuangzhuang Qian","submitted_at":"2025-05-19T01:14:57Z","abstract_excerpt":"Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for non-expert users who lack in-depth library-specific knowledge and advanced programming skills. To tackle this, we present AD-AGENT, an LLM-driven multi-agent framework that turns natural-language instructions into fully executable AD pipelines. AD-AGENT coordinates specialized agents for intent parsing, data preparation, library and model selection, documentation min"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12594","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/2505.12594/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":"2505.12594","created_at":"2026-07-05T11:05:06.617336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12594v1","created_at":"2026-07-05T11:05:06.617336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12594","created_at":"2026-07-05T11:05:06.617336+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYRH24A57R5O","created_at":"2026-07-05T11:05:06.617336+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYRH24A57R5OTOCD","created_at":"2026-07-05T11:05:06.617336+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYRH24A5","created_at":"2026-07-05T11:05:06.617336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31789","citing_title":"Distributed Hierarchical Temporal Memory with Shared Associative Memory for Cross-Entity Preemptive Warning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19538","citing_title":"Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO","json":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO.json","graph_json":"https://pith.science/api/pith-number/OYRH24A57R5OTOCDIBAD3CPXIO/graph.json","events_json":"https://pith.science/api/pith-number/OYRH24A57R5OTOCDIBAD3CPXIO/events.json","paper":"https://pith.science/paper/OYRH24A5"},"agent_actions":{"view_html":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO","download_json":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO.json","view_paper":"https://pith.science/paper/OYRH24A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12594&json=true","fetch_graph":"https://pith.science/api/pith-number/OYRH24A57R5OTOCDIBAD3CPXIO/graph.json","fetch_events":"https://pith.science/api/pith-number/OYRH24A57R5OTOCDIBAD3CPXIO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO/action/storage_attestation","attest_author":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO/action/author_attestation","sign_citation":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO/action/citation_signature","submit_replication":"https://pith.science/pith/OYRH24A57R5OTOCDIBAD3CPXIO/action/replication_record"}},"created_at":"2026-07-05T11:05:06.617336+00:00","updated_at":"2026-07-05T11:05:06.617336+00:00"}