Clear contributions. Evidence in view.
The study asks how often merged AI-agent PRs receive follow-up fixes, who authors those fixes, and how merge-time signals differ between agent PRs with and without a later fix.
Software Engineering · Empirical
The central argument is that a present record, authentic execution trace, passing test, or successful tool result does not establish satisfaction of current requirements, legitimate caller authority, or correspondence between a later consequential action and the reviewed artifact; observation and evaluation outputs remain candidate evidence whose usable properties depend on trusted producer capabilities.
AI & Agents · Position / Conceptual
The paper asks whether an agent can assemble the resources and procedures a scientific task requires into a system that remains invocable after construction ends, shifting attention from development actions or a single answer to capabilities retained in the delivered artifact.
AI & Agents · System Artifact
The paper formulates EIP-II as posterior inference for an observation y when both the prior and the forward model are unknown, using training data and a new observation set Y drawn under the same forward model.
Machine Learning · Empirical
Latest Research · Browse by domain and research kind.
30 articles
The authors introduce SVGLM, a framework that uses SVG primitives to connect text and images in reasoning, using SVG both as an image description and as text instructions.
Machine Learning · Empirical
The authors present ARGUS, a source-grounded, role-aware pipeline for constructing document-level Event Knowledge Graphs (EKGs) from U.S. employment-discrimination complaints, representing events with participants, temporal relations, and causal relations.
Machine Learning · System Artifact
LIFT is a force-aware post-training framework for pretrained VLA policies that adds contact reactivity while aiming to preserve the pretrained manipulation prior.
Machine Learning · Empirical
The authors introduce GraphStar sets, which extend Star sets to represent uncertainty in node and edge features, and implement them in GNNV to support reachability analysis for GCN and GINE architectures.
Machine Learning · System Artifact
The study asks how often merged AI-agent PRs receive follow-up fixes, who authors those fixes, and how merge-time signals differ between agent PRs with and without a later fix.
Software Engineering · Empirical
The central argument is that a present record, authentic execution trace, passing test, or successful tool result does not establish satisfaction of current requirements, legitimate caller authority, or correspondence between a later consequential action and the reviewed artifact; observation and evaluation outputs remain candidate evidence whose usable properties depend on trusted producer capabilities.
AI & Agents · Position / Conceptual
The paper asks whether an agent can assemble the resources and procedures a scientific task requires into a system that remains invocable after construction ends, shifting attention from development actions or a single answer to capabilities retained in the delivered artifact.
AI & Agents · System Artifact
The authors contribute an approach that pairs LLM-generated taint flow models with a soundness checker, rather than constructing every model through inter-procedural taint analysis.
Security · System Artifact
The paper formulates EIP-II as posterior inference for an observation y when both the prior and the forward model are unknown, using training data and a new observation set Y drawn under the same forward model.
Machine Learning · Empirical
DualRes combines aligned spectral resolutions with normalized selective oscillatory updates; the paper’s evaluation contribution uses recording-level splits and explicit duration accounting to distinguish labelled exposure, recording coverage, and operating-condition shift.
Machine Learning · Empirical
The paper targets the lack of explicit social-knowledge representations and protocol-governed coordination in many LLM multi-agent systems. It proposes EPLA, a neuro-symbolic coordination architecture, and epistemic lottery gossip models that add agent-indexed lottery weights to call histories. Its announced Guard-decidability scope is an explicit modal-depth-one source fragment, not unrestricted epistemic reasoning.
AI & Agents · Position / Conceptual
The proposed decoding strategy reuses a preserved pre-adaptation language model to guide a speech-recognition model during inference.
Machine Learning · System Artifact
The work introduces a legally grounded hierarchy that combines free-form descriptions of disputed matters with structured legal categories.
Machine Learning · Empirical
The proposed defense combines protected evidence selection with regulated source use to address malicious optimization across the search-to-generation pipeline.
Security · Empirical
The work proposes a model-based deployment methodology that automates application adaptation for phased execution.
Software Engineering · System Artifact
The inquiry distinguishes repeated success, distinct coverage, accepted evidence, resource use, service capacity, and operational protection when evaluating added inference effort.
Security · Theoretical
The proposed alternative invokes skill packages through delegated agents instead of placing their instructions in the primary agent context.
AI & Agents · Empirical
The study asks whether estimating both location and scale in time-series forecasting can improve point-estimate accuracy.
Machine Learning · Empirical
The work systematically evaluates inference-time token merging across a multilingual speech-recognition model family and examines its interaction with parameter-efficient adaptation in lower-resource settings.
Machine Learning · Empirical
The evaluated cost structure is amortizing because substantial deployment expenditure is paid per hired trainer only at setup, while recurring expenditure is markedly smaller and becomes diluted over the federation lifetime.
Systems & Cloud · Empirical
The proposed contribution is a generalist-oriented prompting method that uses qualitative codebooks to detect cybercrime incidents in consumer narratives with pretrained language models.
Machine Learning · Empirical
A provider-neutral systems-security framework for constraining autonomous AI agents through capability assessment, effective authority, bounded reach, exposure-path analysis, and runtime trajectory assurance.
Research
A decision model for multi-account AWS security: trust boundaries, identity, preventive and detective controls, evidence, containment, and recovery.
Research
A vendor-neutral threat model for AI agents that separates model behavior from authorization and maps threats to controls, evidence, tests, and residual risk.
Research
A practical method for turning system boundaries and abuse paths into owned controls, observable evidence, and repeatable tests.
Research
Provenance turns a security claim into a traceable record of source, transformation, review, and intended use—without pretending lineage alone guarantees truth.
Research
NIST's current incident-response guidance integrates preparation, response, recovery, and continuous improvement across the six CSF 2.0 Functions.
Research
OPA lets you centralize policy decisions (Rego) for authz and compliance across microservices, Kubernetes, CI, and more.
Research
Sigma is a detection-rule format that lets you write once and translate to multiple SIEM backends (Splunk, Sentinel, etc.).
Research
SLSA is a maturity model for build provenance and tamper resistance. The real value is disciplined build pipelines and signed attestations.
Research
