{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PXA545SFQJGHE42BT2WA4EPDYA","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":"aa5f19f22d8b34d4be73d596c4ddf6dfe4c1e89225cd07262d4a1a205ef9606f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T07:08:26Z","title_canon_sha256":"809033c12e5750bd761d73d095c920823ecf2ca55c09d42e7fe55a794cc98e64"},"schema_version":"1.0","source":{"id":"2607.01793","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01793","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01793v1","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01793","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_12","alias_value":"PXA545SFQJGH","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_16","alias_value":"PXA545SFQJGHE42B","created_at":"2026-07-03T01:17:30Z"},{"alias_kind":"pith_short_8","alias_value":"PXA545SF","created_at":"2026-07-03T01:17:30Z"}],"graph_snapshots":[{"event_id":"sha256:25bc38d3ced1c4769884058b8207443c58e97ee979a7b50c91ecb27265adf359","target":"graph","created_at":"2026-07-03T01:17:30Z","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/2607.01793/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents increasingly perform autonomous actions through external tools, leading to complex and evolving safety risks. However, existing safety testing targets expert-designed safety violations, and the corresponding outcomes are evaluated by hard-coded rules, making them costly to extend as agents evolve. To this end, we present Vera, an end-to-end automated safety testing framework that instantiates software engineering testing principles for non-deterministic agents through a three-stage, self-reinforcing pipeline. First, a literature-driven exploration continuously discovers and structur","authors_text":"Jialuo Chen, Jianan Ma, Ming Wen, Qinqin He, Ruixiao Lin, Xiaohu Du, Xingjun Ma, Xinhao Deng, Yanming Guo, Yifan Ding, Yunhao Chen, Yunhao Feng, Yutao Wu, Zhuoer Xu, Zixing Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T07:08:26Z","title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01793","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":"sha256:751c05c3719ee9ddfa7a58382073bd86f1bea9fdc732c703da8010145b432a83","target":"record","created_at":"2026-07-03T01:17:30Z","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":"aa5f19f22d8b34d4be73d596c4ddf6dfe4c1e89225cd07262d4a1a205ef9606f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T07:08:26Z","title_canon_sha256":"809033c12e5750bd761d73d095c920823ecf2ca55c09d42e7fe55a794cc98e64"},"schema_version":"1.0","source":{"id":"2607.01793","kind":"arxiv","version":1}},"canonical_sha256":"7dc1de7645824c7273419eac0e11e3c01dde202a83a7c76faeebfffbda837c77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dc1de7645824c7273419eac0e11e3c01dde202a83a7c76faeebfffbda837c77","first_computed_at":"2026-07-03T01:17:30.054145Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:30.054145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HIVsGTqrbDs5ANTNjiIic178XhkQr+HCM/fKfI/XqqyntgGt8yL6lINg9AIN2wRQNf9Dhfx4lFpA3JfBlXJ+Cg==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:30.054589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01793","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751c05c3719ee9ddfa7a58382073bd86f1bea9fdc732c703da8010145b432a83","sha256:25bc38d3ced1c4769884058b8207443c58e97ee979a7b50c91ecb27265adf359"],"state_sha256":"4da3afe03e2e101c82e0ff8e22f4caeaa1c1377ad276154dd7b1902a63439c35"}