{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GX3D4N3VXB46JX5C2FJ7NPBCBI","short_pith_number":"pith:GX3D4N3V","schema_version":"1.0","canonical_sha256":"35f63e3775b879e4dfa2d153f6bc220a0477701b6f1b227e4b7b329265d066c4","source":{"kind":"arxiv","id":"2509.16749","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLM Generated Detection Rules in Cybersecurity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Aiden Mitchell, Anna Bertiger, Aryan Luthra, Bobby Filar, Sam Scholten, Stefano Meschiari, Vivek Sharath","submitted_at":"2025-09-20T17:21:51Z","abstract_excerpt":"LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark metrics for evaluating LLM-generated cybersecurity rules. The benchmark employs a holdout set-based methodology to measure the effectiveness of LLM-generated security rules in comparison to a human-generated corpus of rules. It provides three key metrics inspired by the way experts evaluate security rules, offering a realistic, multifaceted evaluation of the effe"},"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":"2509.16749","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-09-20T17:21:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68a003efabf0bc74b020f2f83743c0c7faa1e153026a9d018adba46346dc7f49","abstract_canon_sha256":"fb778af7a60e0fce1cdaed96ae3d1049524fb164d2dece71af6c085ac6f44d11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T00:21:13.039084Z","signature_b64":"PXC2p3EPI+OEbwfJLSIm4mYTyPkSgzlGOByAEVDq+TuPZjrSZgCZgm6zB0/4ei9QDOXugNYKqPWKyO8GxvB4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35f63e3775b879e4dfa2d153f6bc220a0477701b6f1b227e4b7b329265d066c4","last_reissued_at":"2026-08-13T00:21:13.037504Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T00:21:13.037504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLM Generated Detection Rules in Cybersecurity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Aiden Mitchell, Anna Bertiger, Aryan Luthra, Bobby Filar, Sam Scholten, Stefano Meschiari, Vivek Sharath","submitted_at":"2025-09-20T17:21:51Z","abstract_excerpt":"LLMs are increasingly pervasive in the security environment, with limited measures of their effectiveness, which limits trust and usefulness to security practitioners. Here, we present an open-source evaluation framework and benchmark metrics for evaluating LLM-generated cybersecurity rules. The benchmark employs a holdout set-based methodology to measure the effectiveness of LLM-generated security rules in comparison to a human-generated corpus of rules. It provides three key metrics inspired by the way experts evaluate security rules, offering a realistic, multifaceted evaluation of the effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.16749","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/2509.16749/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":"2509.16749","created_at":"2026-08-13T00:21:13.037795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.16749v1","created_at":"2026-08-13T00:21:13.037795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.16749","created_at":"2026-08-13T00:21:13.037795+00:00"},{"alias_kind":"pith_short_12","alias_value":"GX3D4N3VXB46","created_at":"2026-08-13T00:21:13.037795+00:00"},{"alias_kind":"pith_short_16","alias_value":"GX3D4N3VXB46JX5C","created_at":"2026-08-13T00:21:13.037795+00:00"},{"alias_kind":"pith_short_8","alias_value":"GX3D4N3V","created_at":"2026-08-13T00:21:13.037795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.13050","citing_title":"Operationalizing Cyber Threat Intelligence with GraphRAG","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI","json":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI.json","graph_json":"https://pith.science/api/pith-number/GX3D4N3VXB46JX5C2FJ7NPBCBI/graph.json","events_json":"https://pith.science/api/pith-number/GX3D4N3VXB46JX5C2FJ7NPBCBI/events.json","paper":"https://pith.science/paper/GX3D4N3V"},"agent_actions":{"view_html":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI","download_json":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI.json","view_paper":"https://pith.science/paper/GX3D4N3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.16749&json=true","fetch_graph":"https://pith.science/api/pith-number/GX3D4N3VXB46JX5C2FJ7NPBCBI/graph.json","fetch_events":"https://pith.science/api/pith-number/GX3D4N3VXB46JX5C2FJ7NPBCBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI/action/storage_attestation","attest_author":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI/action/author_attestation","sign_citation":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI/action/citation_signature","submit_replication":"https://pith.science/pith/GX3D4N3VXB46JX5C2FJ7NPBCBI/action/replication_record"}},"created_at":"2026-08-13T00:21:13.037795+00:00","updated_at":"2026-08-13T00:21:13.037795+00:00"}