{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y3HET5ENYXP2XO5GOQA4FRLKTS","short_pith_number":"pith:Y3HET5EN","schema_version":"1.0","canonical_sha256":"c6ce49f48dc5dfabbba67401c2c56a9cac9d024de93433200fe240c1244d3a2f","source":{"kind":"arxiv","id":"2504.00428","version":1},"attestation_state":"computed","paper":{"title":"LLM-Assisted Proactive Threat Intelligence for Automated Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Farhad Alemi, Richard Macwan, Shuva Paul","submitted_at":"2025-04-01T05:19:33Z","abstract_excerpt":"Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large language models (LLMs) and Retrieval-Augmented Generation (RAG) systems with continuous threat intelligence feeds. Leveraging recent advancements in LLMs, specifically GPT-4o, and the innovative application of RAG techniques, our approach addresses the limitations of traditional static threat analysis by incorporating dynamic, real-time data sources. We leverage"},"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":"2504.00428","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-04-01T05:19:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3eba3e4114d12e03c1c5169c4e9d089f070b2fb43898b3781e7c2657b611d430","abstract_canon_sha256":"f508b9ebc6ba27feec90d95e21d398202bbacda6c847c1503b0a6c2ff102926e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:26.284556Z","signature_b64":"TSrOfiH7c1YfohbaTCd6AmWMexMBJeFTMJtVYI82/D8RiyvMGNCEkMpAXh91XRSimmF5Pjg1jLeap5Q5rM4tDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6ce49f48dc5dfabbba67401c2c56a9cac9d024de93433200fe240c1244d3a2f","last_reissued_at":"2026-07-05T10:42:26.284068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:26.284068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Assisted Proactive Threat Intelligence for Automated Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Farhad Alemi, Richard Macwan, Shuva Paul","submitted_at":"2025-04-01T05:19:33Z","abstract_excerpt":"Successful defense against dynamically evolving cyber threats requires advanced and sophisticated techniques. This research presents a novel approach to enhance real-time cybersecurity threat detection and response by integrating large language models (LLMs) and Retrieval-Augmented Generation (RAG) systems with continuous threat intelligence feeds. Leveraging recent advancements in LLMs, specifically GPT-4o, and the innovative application of RAG techniques, our approach addresses the limitations of traditional static threat analysis by incorporating dynamic, real-time data sources. We leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.00428","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/2504.00428/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":"2504.00428","created_at":"2026-07-05T10:42:26.284120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.00428v1","created_at":"2026-07-05T10:42:26.284120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.00428","created_at":"2026-07-05T10:42:26.284120+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3HET5ENYXP2","created_at":"2026-07-05T10:42:26.284120+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3HET5ENYXP2XO5G","created_at":"2026-07-05T10:42:26.284120+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3HET5EN","created_at":"2026-07-05T10:42:26.284120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30479","citing_title":"COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS","json":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS.json","graph_json":"https://pith.science/api/pith-number/Y3HET5ENYXP2XO5GOQA4FRLKTS/graph.json","events_json":"https://pith.science/api/pith-number/Y3HET5ENYXP2XO5GOQA4FRLKTS/events.json","paper":"https://pith.science/paper/Y3HET5EN"},"agent_actions":{"view_html":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS","download_json":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS.json","view_paper":"https://pith.science/paper/Y3HET5EN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.00428&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3HET5ENYXP2XO5GOQA4FRLKTS/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3HET5ENYXP2XO5GOQA4FRLKTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS/action/storage_attestation","attest_author":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS/action/author_attestation","sign_citation":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS/action/citation_signature","submit_replication":"https://pith.science/pith/Y3HET5ENYXP2XO5GOQA4FRLKTS/action/replication_record"}},"created_at":"2026-07-05T10:42:26.284120+00:00","updated_at":"2026-07-05T10:42:26.284120+00:00"}