{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RCINUXBC4UEANKA4TV4A3VNTY4","short_pith_number":"pith:RCINUXBC","schema_version":"1.0","canonical_sha256":"8890da5c22e50806a81c9d780dd5b3c716dce69d8f761654846d486f2f160bfb","source":{"kind":"arxiv","id":"2405.20441","version":4},"attestation_state":"computed","paper":{"title":"SECURE: Benchmarking Large Language Models for Cybersecurity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CR","authors_text":"Ashim Mahara, Benjamin A. Blakely, Dipkamal Bhusal, Grace Long Torales, Le Nguyen, Md Tanvirul Alam, Nidhi Rastogi, Rodney Frazier, Romy Fieblinger, Zachary Lightcap","submitted_at":"2024-05-30T19:35:06Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but do not sufficiently address the practical and applied aspects of LLM performance in cybersecurity-specific tasks. To address this gap, we introduce the SECURE (Security Extraction, Understanding \\& Reasoning Evaluation), a benchmark designed to assess LLMs performance in realistic cybersecurity scenarios. SECURE includes six datasets focussed on the Industr"},"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":"2405.20441","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-30T19:35:06Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"2b51cbfe24807019902c757ad8fb88548330241dc09426fa5d41ac24ebdf3a09","abstract_canon_sha256":"a804f10daff0fe04bd30fee34b002f518a298d742b6254dca44b58ffc3dd52a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:31.526248Z","signature_b64":"EN/T+YNdi4ddzJA5ufii2r0uMFA6oZkObbd0I+bgSIYwKl1fe8LCyPrVZ/KusyiYDklCU5InKEd79I6kcAjwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8890da5c22e50806a81c9d780dd5b3c716dce69d8f761654846d486f2f160bfb","last_reissued_at":"2026-07-05T09:28:31.525788Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:31.525788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SECURE: Benchmarking Large Language Models for Cybersecurity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CR","authors_text":"Ashim Mahara, Benjamin A. Blakely, Dipkamal Bhusal, Grace Long Torales, Le Nguyen, Md Tanvirul Alam, Nidhi Rastogi, Rodney Frazier, Romy Fieblinger, Zachary Lightcap","submitted_at":"2024-05-30T19:35:06Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated potential in cybersecurity applications but have also caused lower confidence due to problems like hallucinations and a lack of truthfulness. Existing benchmarks provide general evaluations but do not sufficiently address the practical and applied aspects of LLM performance in cybersecurity-specific tasks. To address this gap, we introduce the SECURE (Security Extraction, Understanding \\& Reasoning Evaluation), a benchmark designed to assess LLMs performance in realistic cybersecurity scenarios. SECURE includes six datasets focussed on the Industr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20441","kind":"arxiv","version":4},"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/2405.20441/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":"2405.20441","created_at":"2026-07-05T09:28:31.525838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20441v4","created_at":"2026-07-05T09:28:31.525838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20441","created_at":"2026-07-05T09:28:31.525838+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCINUXBC4UEA","created_at":"2026-07-05T09:28:31.525838+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCINUXBC4UEANKA4","created_at":"2026-07-05T09:28:31.525838+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCINUXBC","created_at":"2026-07-05T09:28:31.525838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21377","citing_title":"ARENA: An Architecture for Measuring the Transferability of Autonomous Cyber Defense","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06921","citing_title":"Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities","ref_index":178,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4","json":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4.json","graph_json":"https://pith.science/api/pith-number/RCINUXBC4UEANKA4TV4A3VNTY4/graph.json","events_json":"https://pith.science/api/pith-number/RCINUXBC4UEANKA4TV4A3VNTY4/events.json","paper":"https://pith.science/paper/RCINUXBC"},"agent_actions":{"view_html":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4","download_json":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4.json","view_paper":"https://pith.science/paper/RCINUXBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20441&json=true","fetch_graph":"https://pith.science/api/pith-number/RCINUXBC4UEANKA4TV4A3VNTY4/graph.json","fetch_events":"https://pith.science/api/pith-number/RCINUXBC4UEANKA4TV4A3VNTY4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4/action/storage_attestation","attest_author":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4/action/author_attestation","sign_citation":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4/action/citation_signature","submit_replication":"https://pith.science/pith/RCINUXBC4UEANKA4TV4A3VNTY4/action/replication_record"}},"created_at":"2026-07-05T09:28:31.525838+00:00","updated_at":"2026-07-05T09:28:31.525838+00:00"}