{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UN6S3554337PHGRE37RU4QTKV6","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":"562be3f450e747eb225948c34fce90135d5a4cde19512c60fd91f4dbe64e7cb0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-03T01:21:59Z","title_canon_sha256":"eb7caf708bf4a32cac154ef9ae25d41ca812cff1ce8be4a4e020e270179c8d70"},"schema_version":"1.0","source":{"id":"2606.05233","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05233","created_at":"2026-06-05T00:13:49Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05233v1","created_at":"2026-06-05T00:13:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05233","created_at":"2026-06-05T00:13:49Z"},{"alias_kind":"pith_short_12","alias_value":"UN6S3554337P","created_at":"2026-06-05T00:13:49Z"},{"alias_kind":"pith_short_16","alias_value":"UN6S3554337PHGRE","created_at":"2026-06-05T00:13:49Z"},{"alias_kind":"pith_short_8","alias_value":"UN6S3554","created_at":"2026-06-05T00:13:49Z"}],"graph_snapshots":[{"event_id":"sha256:defea2c7c258926b7aee08f2d18adfe8e23069a51ae049d0ee7220841f280a39","target":"graph","created_at":"2026-06-05T00:13:49Z","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/2606.05233/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent computer-using-agent (CUA) red-teaming papers report prompt-injection attack success rates (ASR) of 42-98%, but these headline numbers cluster on retired models and on the most-vulnerable model in each paper's panel. We ask whether those techniques, reproduced as hand-crafted templates, still work against current frontier CUAs. We release CUA-HandCrafted, a public benchmark of 793 episodes spanning 24 multi-step web tasks, 56 attack templates, 8 attack families, and 4 system-prompt configurations. Against Claude Sonnet 4.6 and GPT-5.4 we measure 0/140 multi-step attack success (Clopper-","authors_text":"Nicholas Saban","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-03T01:21:59Z","title":"Domain-Conditioned Safety in Frontier Computer-Using Agents: A 793-Episode Browser Benchmark, a Coding-Domain Cross-Reference, and a Reproducibility Audit of Recent Red-Teaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05233","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":"sha256:449cca79f74c26ff76b9f9c11321c63c30c7e46b5418531201d1ca21cadcfbc2","target":"record","created_at":"2026-06-05T00:13:49Z","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":"562be3f450e747eb225948c34fce90135d5a4cde19512c60fd91f4dbe64e7cb0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-03T01:21:59Z","title_canon_sha256":"eb7caf708bf4a32cac154ef9ae25d41ca812cff1ce8be4a4e020e270179c8d70"},"schema_version":"1.0","source":{"id":"2606.05233","kind":"arxiv","version":1}},"canonical_sha256":"a37d2df7bcdefef39a24dfe34e426aaf86375ccd1f8335b6ec1209cdcd0aefe0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a37d2df7bcdefef39a24dfe34e426aaf86375ccd1f8335b6ec1209cdcd0aefe0","first_computed_at":"2026-06-05T00:13:49.554225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T00:13:49.554225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"daTMAEF4XLDvOXcJoO/sLZm/WKLoVPFuAXqIaIuvXSA81Ha+iuIHkp0O1MM4dKNfhklDY2rRjorhAwFmSAq+BA==","signature_status":"signed_v1","signed_at":"2026-06-05T00:13:49.554713Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05233","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:449cca79f74c26ff76b9f9c11321c63c30c7e46b5418531201d1ca21cadcfbc2","sha256:defea2c7c258926b7aee08f2d18adfe8e23069a51ae049d0ee7220841f280a39"],"state_sha256":"b05cc5e4435ad95efc7e13f3b044f46cecf922e5cee6c9d78b9a112983bc79f6"}