A pragmatic classification of AI incident trajectories

• URL: http://arxiv.org/abs/2604.21412v1
• Date: Thu, 23 Apr 2026 08:24:14 GMT
• Title: A pragmatic classification of AI incident trajectories
• Abstract summary: Public AI incident database counts conflate changes in reporting propensity, deployment growth, and shifts in harm frequency per unit of exposure.<n>We propose a simple framework that establishes clear points of inquiry, separately estimates exposure from harm-rate trends, and then classifies into meaningful trajectory categories for governance decisions.
• Score: 3.660810844382496
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Public AI incident database counts conflate changes in reporting propensity, deployment growth, and shifts in harm frequency per unit of exposure. These issues introduce significant uncertainties challenging public and corporate policy frameworks centred on realized risks. We propose a simple framework that establishes clear points of inquiry, separately estimates exposure from harm-rate trends, and then classifies into meaningful trajectory categories for governance decisions. The framework combines a structured monitoring question format (SORT) to clarify coverage decisions, a tiered estimation procedure calibrated to available evidence, and LLM-assisted incident matching against public databases. Applied to various monitoring questions, we draw conclusions regarding the monitoring ecosystem more broadly: Providing an essential interpretative classification, determining what can and cannot be claimed, and establishing that exposure estimation is required as AI deployments become increasingly common.

Related papers

• CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement [50.91045324738942]
  CLAIM is an uncertainty-driven framework for active clarification learning in open-domain settings.<n>We propose an entropy-driven synthetic data generation pipeline that integrates uncertainty estimation with semantic clustering and reasoning-based judgments.<n> Experimental results demonstrate that CLAIM can learn stable and generalizable clarification strategies without relying on manually labeled data.
  arXiv  Detail & Related papers  (2026-08-12T04:27:45Z)
• Conformal Changepoint Localization and Root Cause Analysis with Corrupted Observations [55.76952683833966]
  This paper proposes weighted CONCH (W-CONCH) and weighted CROC (W-CROC) to reduce confidence set size when data may be corrupted.<n>Experiments on image-based and real-world changepoint and root-cause benchmarks show that uncertainty-based weighting substantially reduces confidence set size.
  arXiv  Detail & Related papers  (2026-07-29T05:16:59Z)
• Human-Centred Risk Mitigation for AI-Mediated Information Manipulation: A SOCMINT Framework Based on Information Manipulation Sets [0.0]
  This paper proposes a SOCMINT framework based on Information Manipulation Sets (IMS)<n>Building on the VIGINUM/EEAS use of IMS in counter-FIMI analysis, the framework treats manipulation as a coherent process involving narratives, accounts, infrastructures, temporal patterns, cross-platform migration, synthetic amplification, and cognitive targeting.<n>The paper also proposes a tabletop evaluation protocol to assess decision quality, confidence calibration, and mitigation proportionality.
  arXiv  Detail & Related papers  (2026-06-08T17:12:11Z)
• Position: Anthropomorphic Misalignment Research Needs Stronger Evidence [52.76826423649968]
  We show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors.<n>This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR.
  arXiv  Detail & Related papers  (2026-05-29T16:38:53Z)
• Imbalanced Classification under Capacity Constraints [0.5156484100374058]
  Class of primary interest is underrepresented in classification settings, leading to imbalanced data problems.<n>We propose a framework that explicitly controls the rate of positive predictions.<n>We show that incorporating capacity constraints leads to substantial improvements over classical approaches.
  arXiv  Detail & Related papers  (2026-05-05T02:21:01Z)
• Designing escalation criteria for international AI incident response: criteria, triggers, and thresholds [0.0]
  No operational criteria exist for determining when a detected AI incident warrants escalation beyond national handling to international coordination.<n>This paper proposes an escalation framework to address this gap, intended as a common reference point across jurisdictions.
  arXiv  Detail & Related papers  (2026-04-25T07:31:58Z)
• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• Dual-Stage LLM Framework for Scenario-Centric Semantic Interpretation in Driving Assistance [3.7098231493739764]
  This paper presents a scenario-centric framework for reproducible auditing of risk reasoning in urban driving contexts.<n>Findings highlight the importance of scenario-centric auditing and explicit ambiguity management when integrating LLM-based reasoning into safety-aligned driver assistance systems.
  arXiv  Detail & Related papers  (2026-03-29T06:20:08Z)
• From Linear Risk to Emergent Harm: Complexity as the Missing Core of AI Governance [0.0]
  Risk-based AI regulation promises proportional controls aligned with anticipated harms.<n>This paper argues that such frameworks often fail for structural reasons.<n>We propose a complexity-based framework for AI governance that treats regulation as intervention rather than control.
  arXiv  Detail & Related papers  (2025-12-14T14:19:21Z)
• A Unified and Stable Risk Minimization Framework for Weakly Supervised Learning with Theoretical Guarantees [33.15955234458642]
  Weakly supervised learning has emerged as a practical alternative to fully supervised learning when complete and accurate labels are costly or infeasible to acquire.<n>We propose a principled, unified framework that bypasses such post-hoc adjustments by formulating a stable surrogate risk grounded in the structure of weakly supervised data.
  arXiv  Detail & Related papers  (2025-11-28T00:57:04Z)
• SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models [60.8821834954637]
  We present SafeRBench, the first benchmark that assesses LRM safety end-to-end.<n>We pioneer the incorporation of risk categories and levels into input design.<n>We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units.
  arXiv  Detail & Related papers  (2025-11-19T06:46:33Z)
• Variance-Bounded Evaluation of Entity-Centric AI Systems Without Ground Truth: Theory and Measurement [0.0]
  We introduce VB-Score, a variance-bounded evaluation framework for entity-centric AI systems.<n> VB-Score enumerates plausible interpretations through constraint relaxation and Monte Carlo sampling.<n>It then evaluates system outputs by their expected success across interpretations, penalized by variance to assess robustness of the system.
  arXiv  Detail & Related papers  (2025-09-26T07:54:38Z)
• MARBLE: A Multi-Agent Rule-Based LLM Reasoning Engine for Accident Severity Prediction [1.3102025155414727]
  Accident severity prediction plays a critical role in transportation safety systems.<n>Existing methods often rely on monolithic models or black box prompting.<n>We propose a multiagent rule based LLM engine that decomposes the severity prediction task across a team of specialized reasoning agents.
  arXiv  Detail & Related papers  (2025-07-07T11:27:49Z)
• On Continuous Monitoring of Risk Violations under Unknown Shift [46.65571623109494]
  We propose a general framework for the real-time monitoring of risk violations in evolving data streams.<n>Our method operates under minimal assumptions on the nature of encountered shifts.<n>We illustrate the effectiveness of our approach by monitoring risks in outlier detection and set prediction under a variety of shifts.
  arXiv  Detail & Related papers  (2025-06-19T15:52:24Z)
• Few-shot Policy (de)composition in Conversational Question Answering [54.259440408606515]
  We propose a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting.<n>We show that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies.<n>We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning.
  arXiv  Detail & Related papers  (2025-01-20T08:40:15Z)
• Stateful Offline Contextual Policy Evaluation and Learning [88.9134799076718]
  We study off-policy evaluation and learning from sequential data. We formalize the relevant causal structure of problems such as dynamic personalized pricing. We show improved out-of-sample policy performance in this class of relevant problems.
  arXiv  Detail & Related papers  (2021-10-19T16:15:56Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.