{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:TV4BA2V6DITEQ3G5SGAJI3WRHC","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":"1a40aec2a40ae6f4aecf9d06294804361f65db4f2d867b291460273de4aebc8b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-24T02:51:58Z","title_canon_sha256":"011fd40b1cf4675db3588f64bcfdb48768cd41fab8b7adffa4f83cbb17c93bca"},"schema_version":"1.0","source":{"id":"2606.25332","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.25332","created_at":"2026-06-25T01:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.25332v1","created_at":"2026-06-25T01:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25332","created_at":"2026-06-25T01:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"TV4BA2V6DITE","created_at":"2026-06-25T01:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"TV4BA2V6DITEQ3G5","created_at":"2026-06-25T01:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"TV4BA2V6","created_at":"2026-06-25T01:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:1e5ab2c8d47693979cd0cb4b1ced616ef120eae994ecc1b80dde82e5c14f3a21","target":"graph","created_at":"2026-06-25T01:18:02Z","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/2606.25332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have shown promise for automated penetration testing, yet existing end-to-end black-box evaluations are highly susceptible to error cascading: failures in early reconnaissance can mask an agent's actual ability to exploit vulnerabilities. To more accurately characterize these capabilities, we propose a two-stage decoupled evaluation framework that separates exploit execution from reconnaissance. Using ground-truth injection and knowledge-driven ablation across 70 high-fidelity web vulnerability testbeds, our framework isolates exploitation performance from reconnai","authors_text":"Ge Chu, Liwei Yu, Ming Zhou, Shuo Li, Yan Guo","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-24T02:51:58Z","title":"Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25332","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":"sha256:983e0bf139e7d9a45b1e8e5d4f850fc40f08e67aa4ac7509a9092bdc003c0a1a","target":"record","created_at":"2026-06-25T01:18:02Z","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":"1a40aec2a40ae6f4aecf9d06294804361f65db4f2d867b291460273de4aebc8b","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-24T02:51:58Z","title_canon_sha256":"011fd40b1cf4675db3588f64bcfdb48768cd41fab8b7adffa4f83cbb17c93bca"},"schema_version":"1.0","source":{"id":"2606.25332","kind":"arxiv","version":1}},"canonical_sha256":"9d78106abe1a26486cdd9180946ed13889ffac5da9d985c671307b9f4d8ba68a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d78106abe1a26486cdd9180946ed13889ffac5da9d985c671307b9f4d8ba68a","first_computed_at":"2026-06-25T01:18:02.329383Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-25T01:18:02.329383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M1x1ackrpt75GMDiEPMjkuvhW3zrQVGUBkgF2UqzyuX2cNn9oGfPkMoDLRLDBEaID6TiffvAKgQqozxg38xPCg==","signature_status":"signed_v1","signed_at":"2026-06-25T01:18:02.329787Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.25332","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:983e0bf139e7d9a45b1e8e5d4f850fc40f08e67aa4ac7509a9092bdc003c0a1a","sha256:1e5ab2c8d47693979cd0cb4b1ced616ef120eae994ecc1b80dde82e5c14f3a21"],"state_sha256":"cb870b908475e2c4bc0db9cc7d606523be7c501df74aade80fc0b5dace3dbf21"}