{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:33FOMLXTLCQ2IXW67XYFOAXUYY","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":"3246aa99596efbab510353a7014614e06ce2f25cc2998b18c412d1240cb4f857","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-10T11:45:03Z","title_canon_sha256":"9d77e3e68132f173a281e06df366e0930ae22639386c2ee0967d8d914c726828"},"schema_version":"1.0","source":{"id":"2608.09476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.09476","created_at":"2026-08-11T02:24:18Z"},{"alias_kind":"arxiv_version","alias_value":"2608.09476v1","created_at":"2026-08-11T02:24:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.09476","created_at":"2026-08-11T02:24:18Z"},{"alias_kind":"pith_short_12","alias_value":"33FOMLXTLCQ2","created_at":"2026-08-11T02:24:18Z"},{"alias_kind":"pith_short_16","alias_value":"33FOMLXTLCQ2IXW6","created_at":"2026-08-11T02:24:18Z"},{"alias_kind":"pith_short_8","alias_value":"33FOMLXT","created_at":"2026-08-11T02:24:18Z"}],"graph_snapshots":[{"event_id":"sha256:218a9c0d1afcd38d4f2bf9b7e9ec3cae1456eb14c93145b93e7af028f909730d","target":"graph","created_at":"2026-08-11T02:24:18Z","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/2608.09476/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and ","authors_text":"Cong Wang, Hongwei Yao, Jieling Chen, Kui Ren, Meihui Chen, Wangze Ni, Yiling He, Yiming Liu, Zikun Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-10T11:45:03Z","title":"ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.09476","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":"sha256:40a681dcd0d3c78c6897b524d43c9125baec4e8789b9735709e1dd14c6ed2a53","target":"record","created_at":"2026-08-11T02:24:18Z","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":"3246aa99596efbab510353a7014614e06ce2f25cc2998b18c412d1240cb4f857","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-08-10T11:45:03Z","title_canon_sha256":"9d77e3e68132f173a281e06df366e0930ae22639386c2ee0967d8d914c726828"},"schema_version":"1.0","source":{"id":"2608.09476","kind":"arxiv","version":1}},"canonical_sha256":"decae62ef358a1a45edefdf05702f4c61f1cec36ecc93aa87587f164e6f767c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"decae62ef358a1a45edefdf05702f4c61f1cec36ecc93aa87587f164e6f767c4","first_computed_at":"2026-08-11T02:24:18.215852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T02:24:18.215852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"COMA4bSlIBUflbemyQ+KuJsNjGNXOJwbTEGn9keMTeyfDC5Fvj/Lun715G0o9ukfszdxzBHF1n/F1uu2JP3TCA==","signature_status":"signed_v1","signed_at":"2026-08-11T02:24:18.217447Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.09476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a681dcd0d3c78c6897b524d43c9125baec4e8789b9735709e1dd14c6ed2a53","sha256:218a9c0d1afcd38d4f2bf9b7e9ec3cae1456eb14c93145b93e7af028f909730d"],"state_sha256":"9f9a06965ce22619ef77852f378795f2db18286ba1959571faba398e1627d182"}