{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RCINUXBC4UEANKA4TV4A3VNTY4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a804f10daff0fe04bd30fee34b002f518a298d742b6254dca44b58ffc3dd52a6","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-30T19:35:06Z","title_canon_sha256":"2b51cbfe24807019902c757ad8fb88548330241dc09426fa5d41ac24ebdf3a09"},"schema_version":"1.0","source":{"id":"2405.20441","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20441","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20441v4","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20441","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_12","alias_value":"RCINUXBC4UEA","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_16","alias_value":"RCINUXBC4UEANKA4","created_at":"2026-07-05T09:28:31Z"},{"alias_kind":"pith_short_8","alias_value":"RCINUXBC","created_at":"2026-07-05T09:28:31Z"}],"graph_snapshots":[{"event_id":"sha256:2d65104c76aa76b772255f9b75beb4732b98d955fa36560a1429cda9f376801a","target":"graph","created_at":"2026-07-05T09:28:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2405.20441/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-30T19:35:06Z","title":"SECURE: Benchmarking Large Language Models for Cybersecurity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20441","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3905438b66420cbfc38079255d95bf450b89a1d87d3f3df00c0d85bdc588d4d8","target":"record","created_at":"2026-07-05T09:28:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a804f10daff0fe04bd30fee34b002f518a298d742b6254dca44b58ffc3dd52a6","cross_cats_sorted":["cs.AI","cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-05-30T19:35:06Z","title_canon_sha256":"2b51cbfe24807019902c757ad8fb88548330241dc09426fa5d41ac24ebdf3a09"},"schema_version":"1.0","source":{"id":"2405.20441","kind":"arxiv","version":4}},"canonical_sha256":"8890da5c22e50806a81c9d780dd5b3c716dce69d8f761654846d486f2f160bfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8890da5c22e50806a81c9d780dd5b3c716dce69d8f761654846d486f2f160bfb","first_computed_at":"2026-07-05T09:28:31.525788Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:31.525788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EN/T+YNdi4ddzJA5ufii2r0uMFA6oZkObbd0I+bgSIYwKl1fe8LCyPrVZ/KusyiYDklCU5InKEd79I6kcAjwCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:31.526248Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20441","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3905438b66420cbfc38079255d95bf450b89a1d87d3f3df00c0d85bdc588d4d8","sha256:2d65104c76aa76b772255f9b75beb4732b98d955fa36560a1429cda9f376801a"],"state_sha256":"e3b08351abbbdf2ed93c13ad056bfa32f1d7468ce080826334d1a8e164042513"}