오픈뉴스백과
둘러보기비교AI 브리핑뉴스
회사용어사전커뮤니티피드 제보
...

오픈뉴스백과

집단지성 기반 뉴스 검증 플랫폼. 다양한 시각으로 뉴스를 이해합니다.

서비스

세계의 오늘한국의 오늘뉴스정부과학학술용어사전소개

법적 고지

개인정보처리방침이용약관콘텐츠 이용 안내

문의

이메일 문의

본 플랫폼에서 제공하는 뉴스 콘텐츠의 저작권은 각 언론사에 있으며, 무단 복제 및 배포를 금지합니다.

RSS 피드를 통해 수집된 콘텐츠는 각 원저작자의 라이선스 조건을 따릅니다. 오픈 라이선스(CC-BY 등) 콘텐츠는 해당 라이선스에 따라 출처를 표기합니다.

오픈뉴스백과는 뉴스 집계 및 검증 플랫폼으로, 개별 기사의 내용에 대한 책임은 해당 언론사에 있습니다.

이용자가 작성한 피드백, 팩트체크, 독자 제보 등의 콘텐츠에 대한 책임은 해당 작성자에게 있습니다.

콘텐츠 제거 요청: contact@opennewspedia.com

© 2026 오픈뉴스백과 (OpenNewsPedia). All rights reserved.

뉴스 목록
미디어 커버리지1건1개 미디어
arXiv CS.AI
학술
기타

Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence

arXiv CS.AI
조회 0
CC BY
이 매체는 공공·자유 라이선스로 본문을 직접 표시합니다.
Computer Science > Software Engineering [Submitted on 15 Jun 2026] Title:Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence View PDF HTML (experimental)Abstract:Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench debugging agents (Modgil 2026). A post-release audit found the engine received dt=0 between actions, so its exponential decay never operated: the published trap is a pure-accumulator result. We correct the record (erratum, v2) and treat the flaw as an experiment. The key variable it exposes is whether a monitor's dynamics are calibrated in sample time (per observation, as in CUSUM) or wall-clock time (half-lives in seconds, as in affect models and EMA baselines). On fixed-rate streams these coincide; on agent streams, where inter-action time varies by orders of magnitude, they do not. A pre-registered sweep over uniform intervals (dt in {0..600}s) on 20 trajectories shows the wall-clock level trigger has two regimes: at dt<=1s a constant alarm (20/20; median 18 firings); at dt>=60s silent. Every critical dt lies in (1,30]s. Real agent runs measure latency at median 1.53s (p90 2.33s); real coding cadence sits inside the trap regime, vindicating the empirical finding under a corrected mechanism. The structure is a property of the calibration class, not the engine: a minimal wall-clock accumulator over the raw error stream reproduces the same cliff, while a sample-time CUSUM over the identical stream is exactly dt-invariant (20/20). A rising-edge trigger with hysteresis fires 0-3 times per trajectory in every condition. We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams; transition detection escapes the trap at every cadence, but does not recover human intervention timing. Current browse context: cs.SE References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer (What is the Explorer?) Connected Papers (What is Connected Papers?) Litmaps (What is Litmaps?) scite Smart Citations (What are Smart Citations?) Code, Data and Media Associated with this Article alphaXiv (What is alphaXiv?) CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub (What is DagsHub?) Gotit.pub (What is GotitPub?) Hugging Face (What is Huggingface?) ScienceCast (What is ScienceCast?) Demos Recommenders and Search Tools Influence Flower (What are Influence Flowers?) CORE Recommender (What is CORE?) arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
전문 보기

이 뉴스, 독자들은 어떻게 느꼈나요?

첫 반응을 남겨보세요

로그인하면 감정 반응에 참여할 수 있어요.

관련 뉴스

관련 뉴스 제보는 로그인 후 가능합니다.

'research' 카테고리 뉴스

Deontic Policies for Runtime Governance of Agentic AI Systems

arXiv CS.AI

Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023

arXiv CS.AI

Diffusion Language Models: An Experimental Analysis

arXiv CS.AI

arXiv의 다른 기사

LLM Doesn't Know What It Doesn't Know: Detecting Epistemic Blind Spots via Cross-Model Attribution Divergence on Clinical Tabular Data

arXiv CS.AI

REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk

arXiv CS.AI

Emergent Alignment

arXiv CS.AI

피드백

피드백을 남기려면 로그인해 주세요.