{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4N73FU7ZAOULCEA7T7BDWYRHRP","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":"e2d2b2997783293e1a7444bea1aba80ea55bf198bd88327f09cf154a9e651c7a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-03T19:17:45Z","title_canon_sha256":"b817f60f27d8753119c28caf5d3d907942c927a50733e6b2c959a4b69961f6ca"},"schema_version":"1.0","source":{"id":"2412.02776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.02776","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"arxiv_version","alias_value":"2412.02776v1","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.02776","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_12","alias_value":"4N73FU7ZAOUL","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_16","alias_value":"4N73FU7ZAOULCEA7","created_at":"2026-07-05T09:44:19Z"},{"alias_kind":"pith_short_8","alias_value":"4N73FU7Z","created_at":"2026-07-05T09:44:19Z"}],"graph_snapshots":[{"event_id":"sha256:72b5809ec1eba4fd635fd47a8493a02ff441130f1cf011308d806afbd10a4877","target":"graph","created_at":"2026-07-05T09:44:19Z","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/2412.02776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We saturate a high-school-level hacking benchmark with plain LLM agent design. Concretely, we obtain 95% performance on InterCode-CTF, a popular offensive security benchmark, using prompting, tool use, and multiple attempts. This beats prior work by Phuong et al. 2024 (29%) and Abramovich et al. 2024 (72%).\n  Our results suggest that current LLMs have surpassed the high school level in offensive cybersecurity. Their hacking capabilities remain underelicited: our ReAct&Plan prompting strategy solves many challenges in 1-2 turns without complex engineering or advanced harnessing.","authors_text":"Artem Petrov, Denis Volk, Dmitrii Volkov, Rustem Turtayev","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-03T19:17:45Z","title":"Hacking CTFs with Plain Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.02776","kind":"arxiv","version":1},"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":"sha256:2d819083ad1f4c5f53a319e17f46d9d181b8084b6083770763d64f81b6845c05","target":"record","created_at":"2026-07-05T09:44:19Z","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":"e2d2b2997783293e1a7444bea1aba80ea55bf198bd88327f09cf154a9e651c7a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2024-12-03T19:17:45Z","title_canon_sha256":"b817f60f27d8753119c28caf5d3d907942c927a50733e6b2c959a4b69961f6ca"},"schema_version":"1.0","source":{"id":"2412.02776","kind":"arxiv","version":1}},"canonical_sha256":"e37fb2d3f903a8b1101f9fc23b62278becc9fafa0193ebaacc516f58a71aba1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e37fb2d3f903a8b1101f9fc23b62278becc9fafa0193ebaacc516f58a71aba1b","first_computed_at":"2026-07-05T09:44:19.349493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:19.349493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNVotX67iqbekeP7Y++qjhDFiCZkrINejDoxrhgwFHSXbow6erJXXfwMTV7+ChKgceU+l/MUYMJi636YgQyJAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:19.349958Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.02776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d819083ad1f4c5f53a319e17f46d9d181b8084b6083770763d64f81b6845c05","sha256:72b5809ec1eba4fd635fd47a8493a02ff441130f1cf011308d806afbd10a4877"],"state_sha256":"497c259b604700bca42d59445b2ec05623ba9875d01d60ca214728c0c4584f0b"}