{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U52ITS5N6ONL7XKJVGEMZSH4GC","short_pith_number":"pith:U52ITS5N","schema_version":"1.0","canonical_sha256":"a77489cbadf39abfdd49a988ccc8fc30b116e62151e55c295ef4c8d8411c7cfe","source":{"kind":"arxiv","id":"2506.17644","version":1},"attestation_state":"computed","paper":{"title":"Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daoyuan Wu, Pingchuan Ma, Shuai Wang, Wenyuan Jiang, Zimo Ji, Zongjie Li","submitted_at":"2025-06-21T08:56:20Z","abstract_excerpt":"Capture-the-Flag (CTF) competitions are crucial for cybersecurity education and training. As large language models (LLMs) evolve, there is increasing interest in their ability to automate CTF challenge solving. For example, DARPA has organized the AIxCC competition since 2023 to advance AI-powered automated offense and defense. However, this demands a combination of multiple abilities, from knowledge to reasoning and further to actions. In this paper, we highlight the importance of technical knowledge in solving CTF problems and deliberately construct a focused benchmark, CTFKnow, with 3,992 q"},"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":"2506.17644","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-21T08:56:20Z","cross_cats_sorted":[],"title_canon_sha256":"163f4a78fdc6f8a009446e86761947daa3de57567ad1b1a3e159f2fcd1cc8695","abstract_canon_sha256":"dadcf80669d3e443bbf89d4514b6e4d3522dd88e576a48163278f2279a0ef399"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:20.960910Z","signature_b64":"6j67kXam8uiyjaPaku/9mbISEjsw2QmuI/9LsEiO4m/DynFXZfEuu4YVVA+22WijIJKjkCmEj8cfelJTp7yMBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a77489cbadf39abfdd49a988ccc8fc30b116e62151e55c295ef4c8d8411c7cfe","last_reissued_at":"2026-07-05T11:25:20.960287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:20.960287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Measuring and Augmenting Large Language Models for Solving Capture-the-Flag Challenges","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daoyuan Wu, Pingchuan Ma, Shuai Wang, Wenyuan Jiang, Zimo Ji, Zongjie Li","submitted_at":"2025-06-21T08:56:20Z","abstract_excerpt":"Capture-the-Flag (CTF) competitions are crucial for cybersecurity education and training. As large language models (LLMs) evolve, there is increasing interest in their ability to automate CTF challenge solving. For example, DARPA has organized the AIxCC competition since 2023 to advance AI-powered automated offense and defense. However, this demands a combination of multiple abilities, from knowledge to reasoning and further to actions. In this paper, we highlight the importance of technical knowledge in solving CTF problems and deliberately construct a focused benchmark, CTFKnow, with 3,992 q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17644","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/2506.17644/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":"2506.17644","created_at":"2026-07-05T11:25:20.960372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17644v1","created_at":"2026-07-05T11:25:20.960372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17644","created_at":"2026-07-05T11:25:20.960372+00:00"},{"alias_kind":"pith_short_12","alias_value":"U52ITS5N6ONL","created_at":"2026-07-05T11:25:20.960372+00:00"},{"alias_kind":"pith_short_16","alias_value":"U52ITS5N6ONL7XKJ","created_at":"2026-07-05T11:25:20.960372+00:00"},{"alias_kind":"pith_short_8","alias_value":"U52ITS5N","created_at":"2026-07-05T11:25:20.960372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC","json":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC.json","graph_json":"https://pith.science/api/pith-number/U52ITS5N6ONL7XKJVGEMZSH4GC/graph.json","events_json":"https://pith.science/api/pith-number/U52ITS5N6ONL7XKJVGEMZSH4GC/events.json","paper":"https://pith.science/paper/U52ITS5N"},"agent_actions":{"view_html":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC","download_json":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC.json","view_paper":"https://pith.science/paper/U52ITS5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17644&json=true","fetch_graph":"https://pith.science/api/pith-number/U52ITS5N6ONL7XKJVGEMZSH4GC/graph.json","fetch_events":"https://pith.science/api/pith-number/U52ITS5N6ONL7XKJVGEMZSH4GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC/action/storage_attestation","attest_author":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC/action/author_attestation","sign_citation":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC/action/citation_signature","submit_replication":"https://pith.science/pith/U52ITS5N6ONL7XKJVGEMZSH4GC/action/replication_record"}},"created_at":"2026-07-05T11:25:20.960372+00:00","updated_at":"2026-07-05T11:25:20.960372+00:00"}