{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PXA545SFQJGHE42BT2WA4EPDYA","short_pith_number":"pith:PXA545SF","schema_version":"1.0","canonical_sha256":"7dc1de7645824c7273419eac0e11e3c01dde202a83a7c76faeebfffbda837c77","source":{"kind":"arxiv","id":"2607.01793","version":1},"attestation_state":"computed","paper":{"title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-07-02T07:08:26Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.01793","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-02T07:08:26Z","cross_cats_sorted":[],"title_canon_sha256":"809033c12e5750bd761d73d095c920823ecf2ca55c09d42e7fe55a794cc98e64","abstract_canon_sha256":"aa5f19f22d8b34d4be73d596c4ddf6dfe4c1e89225cd07262d4a1a205ef9606f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:30.054589Z","signature_b64":"HIVsGTqrbDs5ANTNjiIic178XhkQr+HCM/fKfI/XqqyntgGt8yL6lINg9AIN2wRQNf9Dhfx4lFpA3JfBlXJ+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dc1de7645824c7273419eac0e11e3c01dde202a83a7c76faeebfffbda837c77","last_reissued_at":"2026-07-03T01:17:30.054145Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:30.054145Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-07-02T07:08:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01793","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.01793/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.01793","created_at":"2026-07-03T01:17:30.054207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01793v1","created_at":"2026-07-03T01:17:30.054207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01793","created_at":"2026-07-03T01:17:30.054207+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXA545SFQJGH","created_at":"2026-07-03T01:17:30.054207+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXA545SFQJGHE42B","created_at":"2026-07-03T01:17:30.054207+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXA545SF","created_at":"2026-07-03T01:17:30.054207+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA","json":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA.json","graph_json":"https://pith.science/api/pith-number/PXA545SFQJGHE42BT2WA4EPDYA/graph.json","events_json":"https://pith.science/api/pith-number/PXA545SFQJGHE42BT2WA4EPDYA/events.json","paper":"https://pith.science/paper/PXA545SF"},"agent_actions":{"view_html":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA","download_json":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA.json","view_paper":"https://pith.science/paper/PXA545SF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01793&json=true","fetch_graph":"https://pith.science/api/pith-number/PXA545SFQJGHE42BT2WA4EPDYA/graph.json","fetch_events":"https://pith.science/api/pith-number/PXA545SFQJGHE42BT2WA4EPDYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA/action/storage_attestation","attest_author":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA/action/author_attestation","sign_citation":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA/action/citation_signature","submit_replication":"https://pith.science/pith/PXA545SFQJGHE42BT2WA4EPDYA/action/replication_record"}},"created_at":"2026-07-03T01:17:30.054207+00:00","updated_at":"2026-07-03T01:17:30.054207+00:00"}