{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4UCKOHNBJ7H4XIT6OJUWIYHIUM","short_pith_number":"pith:4UCKOHNB","schema_version":"1.0","canonical_sha256":"e504a71da14fcfcba27e72696460e8a310edf6f315be74c004f088fc69dae369","source":{"kind":"arxiv","id":"2406.07599","version":3},"attestation_state":"computed","paper":{"title":"CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dipkamal Bhusal, Le Nguyen, Md Tanvirul Alam, Nidhi Rastogi","submitted_at":"2024-06-11T16:42:02Z","abstract_excerpt":"Cyber threat intelligence (CTI) is crucial in today's cybersecurity landscape, providing essential insights to understand and mitigate the ever-evolving cyber threats. The recent rise of Large Language Models (LLMs) have shown potential in this domain, but concerns about their reliability, accuracy, and hallucinations persist. While existing benchmarks provide general evaluations of LLMs, there are no benchmarks that address the practical and applied aspects of CTI-specific tasks. To bridge this gap, we introduce CTIBench, a benchmark designed to assess LLMs' performance in CTI applications. C"},"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":"2406.07599","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2024-06-11T16:42:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"565cdd92193516c26d88c0e36a11fce7acbd50af0fc4c9b1a5c2ced08bcc94dd","abstract_canon_sha256":"0ce05ff56d90d82479585dba886bb5dee3fa78e6efe3324943f9115a9d885757"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:33.111944Z","signature_b64":"GYo4A8sLE1DAMai5dG2BZOEbnC9MVqXsKWkc9pRc2svT05G3nYbZL50VuC6FScC/HDORIG2KoDqIfz7W1MKPCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e504a71da14fcfcba27e72696460e8a310edf6f315be74c004f088fc69dae369","last_reissued_at":"2026-07-05T09:33:33.111460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:33.111460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Dipkamal Bhusal, Le Nguyen, Md Tanvirul Alam, Nidhi Rastogi","submitted_at":"2024-06-11T16:42:02Z","abstract_excerpt":"Cyber threat intelligence (CTI) is crucial in today's cybersecurity landscape, providing essential insights to understand and mitigate the ever-evolving cyber threats. The recent rise of Large Language Models (LLMs) have shown potential in this domain, but concerns about their reliability, accuracy, and hallucinations persist. While existing benchmarks provide general evaluations of LLMs, there are no benchmarks that address the practical and applied aspects of CTI-specific tasks. To bridge this gap, we introduce CTIBench, a benchmark designed to assess LLMs' performance in CTI applications. C"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07599","kind":"arxiv","version":3},"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/2406.07599/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":"2406.07599","created_at":"2026-07-05T09:33:33.111521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07599v3","created_at":"2026-07-05T09:33:33.111521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07599","created_at":"2026-07-05T09:33:33.111521+00:00"},{"alias_kind":"pith_short_12","alias_value":"4UCKOHNBJ7H4","created_at":"2026-07-05T09:33:33.111521+00:00"},{"alias_kind":"pith_short_16","alias_value":"4UCKOHNBJ7H4XIT6","created_at":"2026-07-05T09:33:33.111521+00:00"},{"alias_kind":"pith_short_8","alias_value":"4UCKOHNB","created_at":"2026-07-05T09:33:33.111521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02674","citing_title":"Cross-Vendor Sola ISPM Benchmark: Evaluating Agentic AI for Federated Identity Security Reasoning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28146","citing_title":"Cybersecurity AI (CAI) Dataset","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06252","citing_title":"False Alarms, Real Damage: Adversarial Attacks Using LLM-based Models on Text-based Cyber Threat Intelligence Systems","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14153","citing_title":"ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24184","citing_title":"Dynamic Cyber Ranges","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM","json":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM.json","graph_json":"https://pith.science/api/pith-number/4UCKOHNBJ7H4XIT6OJUWIYHIUM/graph.json","events_json":"https://pith.science/api/pith-number/4UCKOHNBJ7H4XIT6OJUWIYHIUM/events.json","paper":"https://pith.science/paper/4UCKOHNB"},"agent_actions":{"view_html":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM","download_json":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM.json","view_paper":"https://pith.science/paper/4UCKOHNB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07599&json=true","fetch_graph":"https://pith.science/api/pith-number/4UCKOHNBJ7H4XIT6OJUWIYHIUM/graph.json","fetch_events":"https://pith.science/api/pith-number/4UCKOHNBJ7H4XIT6OJUWIYHIUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM/action/storage_attestation","attest_author":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM/action/author_attestation","sign_citation":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM/action/citation_signature","submit_replication":"https://pith.science/pith/4UCKOHNBJ7H4XIT6OJUWIYHIUM/action/replication_record"}},"created_at":"2026-07-05T09:33:33.111521+00:00","updated_at":"2026-07-05T09:33:33.111521+00:00"}