{"total":4,"items":[{"citing_arxiv_id":"2606.20510","ref_index":29,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Efficient and Sound Probabilistic Verification for AI Agents","primary_cat":"cs.CR","submitted_at":"2026-06-18T17:27:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Presents a distributionally robust optimization method for sound probabilistic verification of Datalog policies in AI agents that bounds violation risk regardless of predicate correlations.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.19588","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Analyzing the Narration Gap in LLM-Solver Loops","primary_cat":"cs.AI","submitted_at":"2026-06-17T20:44:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"The narration step in LLM-solver loops is vulnerable to prompt injection that inverts verified solver conclusions, and hardened prompts reduce but do not eliminate the risk under adaptive attacks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10649","ref_index":20,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Layer Order Semantics for Automata-Based Cybersecurity","primary_cat":"cs.CR","submitted_at":"2026-06-09T09:57:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces a layer-order automaton model that equates faithful online enforcement to regular prefix-closed languages under causal visibility and shows equivalence to deterministic edit automata while preserving layer-local invariants.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05229","ref_index":28,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"From Governance Norms to Enforceable Controls: A Layered Translation Method for Runtime Guardrails in Agentic AI","primary_cat":"cs.AI","submitted_at":"2026-04-06T22:49:28+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"The paper presents a layered method to translate governance objectives from standards such as ISO/IEC 42001 into four control layers for agentic AI, with runtime guardrails limited to observable, determinate, and time-sensitive controls, shown via a procurement-agent case study.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}