{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QUVXACU53YBLXZRF7HYQJWKV6S","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":"a38aa80ad942eee57e41519637ac334eb55d1fd181d4a78fbd93c57c6b0e82fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-10-01T18:38:20Z","title_canon_sha256":"69ab896ea1e4bf9c90702ddfe1a6637754d77e5f2725b81e1347548d87f0060d"},"schema_version":"1.0","source":{"id":"2510.01359","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01359","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01359v2","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01359","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_12","alias_value":"QUVXACU53YBL","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_16","alias_value":"QUVXACU53YBLXZRF","created_at":"2026-06-19T16:09:51Z"},{"alias_kind":"pith_short_8","alias_value":"QUVXACU5","created_at":"2026-06-19T16:09:51Z"}],"graph_snapshots":[{"event_id":"sha256:89b1c445d01fbb10f3292dd4a5f88f2d0d5dd02bfdbbbae00ca181d22049d04f","target":"graph","created_at":"2026-06-19T16:09:51Z","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/2510.01359/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-capable large language model (LLM) agents are embedded in software engineering workflows where they can read, write, and execute code, raising \"jailbreak\" stakes beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection, leaving open whether agents compile and run malicious programs. We present JAWS-Bench (Jailbreaks Across WorkSpaces), a benchmark spanning three escalating workspace regimes mirroring attacker capability: empty (JAWS-0), single-file (JAWS-1), and multi-file (JAWS-M). We pair this with a hierarchical, executable-aware Judge Framework that tes","authors_text":"Jifan Chen, Sam Mayers, Sanjay Krishna Gouda, Shoumik Saha, Varun Kumar, Zijian Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-10-01T18:38:20Z","title":"Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01359","kind":"arxiv","version":2},"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:f5d7a4d403dbb11788a6d707f7e57141540c4ff7e98ba24f5c59ab6f74a16185","target":"record","created_at":"2026-06-19T16:09:51Z","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":"a38aa80ad942eee57e41519637ac334eb55d1fd181d4a78fbd93c57c6b0e82fb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2025-10-01T18:38:20Z","title_canon_sha256":"69ab896ea1e4bf9c90702ddfe1a6637754d77e5f2725b81e1347548d87f0060d"},"schema_version":"1.0","source":{"id":"2510.01359","kind":"arxiv","version":2}},"canonical_sha256":"852b700a9dde02bbe625f9f104d955f4b94a43a7148bd7f26c3c0fd70364170c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"852b700a9dde02bbe625f9f104d955f4b94a43a7148bd7f26c3c0fd70364170c","first_computed_at":"2026-06-19T16:09:51.422744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:09:51.422744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/LapSRuv99cOTMyFe53wxNRqSN14Bqyq/oTqpLwzqlKrJiocjf0fdldcT/SCQ+sqyRzneapdvczIDZ/vOVy8Cw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:09:51.423142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01359","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5d7a4d403dbb11788a6d707f7e57141540c4ff7e98ba24f5c59ab6f74a16185","sha256:89b1c445d01fbb10f3292dd4a5f88f2d0d5dd02bfdbbbae00ca181d22049d04f"],"state_sha256":"fa19864d0acf82006662a75621580174f64da31acec29862687ee5cdf72bb3b8"}