{"paper":{"title":"Cybersecurity AI (CAI) Dataset","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"V\\'ictor Mayoral-Vilches","submitted_at":"2026-05-27T08:29:28Z","abstract_excerpt":"We present CAI Dataset, a fourteen-month corpus of cybersecurity LLM trajectories collected through the open-source CAI agent framework, built in response to PentestGPT's finding that expert operator trajectories, not base-model capability, are the bottleneck for cybersecurity LLM performance. CAI Dataset aggregates 230,935 session logs and 26,027,742 user prompts from 16,768 source IPs across 123 countries, exercising 4,187 unique LLM identifiers against 23,147 target domains over 18.07 TB of durable storage. The mix is hands-on (36.4% offensive, 20.1% attacker-intent, 27.5% business / integr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28146","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/2605.28146/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"}