Empirical forensic study of OpenClaw recovers interaction traces, proposes an agent artifact taxonomy, and flags nondeterminism from LLM-mediated execution as a foundational issue for digital forensics.
Canonical reference
Digital twin: Enabling technologies, challenges and open research.IEEE Access, 8:108952–108971, 2020
Canonical reference. 78% of citing Pith papers cite this work as background.
65
Pith papers citing it
Background
78% of classified citations
citation-role summary
background 14
method 3
baseline 1
citation-polarity summary
representative citing papers
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
KV-cache sharing boosts multi-agent QA performance but enables undetectable tampering; HMAC manifests binding agent, session, and payload reliably detect changes.
A reinforcement learning agent for timing GenAI access improved post-test performance and metacognitive accuracy over unrestricted or fully restricted conditions in a lab study with 105 students.
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
EOS-Bench creates thousands of satellite scheduling test cases spanning small to large scales and evaluates multiple solver types across five performance metrics.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
InfiniLoRA decouples LoRA execution from base-model inference and reports 3.05x higher request throughput plus 54% more adapters meeting strict latency SLOs.
The first systematic review of routine computing synthesizes literature into a taxonomy of temporal, behavioral, cognitive, and variability aspects, outlining applications in health, accessibility, and adaptive support along with persistent challenges.
A Generative Flow Network framework with experience replay, exploratory policy, and physics masking samples ray paths for radio propagation up to 100x faster than exhaustive search on idealized scenarios.
FFM finds optimal fused mappings for tensor accelerators over 10,000 times faster than prior mappers while cutting energy-delay product by up to 1.8x versus hand-tuned designs.
Three custom TENG sensors integrated into eyeglasses capture arterial pulse, jaw kinematics, and facial activity at 4.1 µW total front-end power, achieving 93.8% activity accuracy and 1.82 BPM heart rate error in a 20-participant study.
M-ASPM decouples receiver sensitivity gains from collision exposure in LPWANs via a single shared detection channel that handles synchronization, CFO estimation, and payload channel selection across multiple payload channels.
Proposes data-aware static analysis combining data/control flow and API contracts to detect semantic faults in ML code early, shown on sample real-world notebooks.
dille detects silent semantic faults in random forest ML pipelines with 91% precision via data-informed static analysis on Kaggle notebooks, finding 12-18% of scripts affected.
A multi-backend structural gate for LLM-generated Cypher queries achieves 100% detection of parse, constraint, and schema errors at zero false positives on 1135 queries while preserving model accuracy and adding a cost planner.
Agentic iteration improves perceived quality of generated multiview genomics visualizations over direct LLM generation, but adding more specialist agents or a reviewer yields no further gains across 159 test cases.
Picid is a new modular evaluation infrastructure that enforces deterministic, leakage-safe dataset construction and unified protocols for fault detection, diagnostics, and prognostics across twelve datasets and thirteen models.
A decoupled pipeline with YOLO detection, deterministic prompt encoding, and QLoRA-adapted 1.5B LLM achieves superior structured report generation compared to monolithic VLMs on synthetic maintenance data.
K-U-KAN combines KAN feature lifting, Koopman linear dynamics, and U-KAN refinement with physical and geometric priors to reconstruct 3D dental anatomy from single panoramic radiographs, matching baselines on metrics while improving perceptual quality and halving training time.
VISOR is a VLM-based automated test oracle that evaluates robot task correctness and quality from videos while reporting its own uncertainty, tested on GPT and Gemini across four tasks and over 1000 videos with Gemini showing higher recall and GPT higher precision but low uncertainty-correctness tie
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
A randomized, locally-guided belief-propagation decoder breaks degeneracy deadlocks in quantum error correction, reducing logical error rate and expensive global-decoder invocations by orders of magnitude.
citing papers explorer
-
Foundations for Agentic AI Investigations from the Forensic Analysis of OpenClaw
Empirical forensic study of OpenClaw recovers interaction traces, proposes an agent artifact taxonomy, and flags nondeterminism from LLM-mediated execution as a foundational issue for digital forensics.
-
A document is worth a structured record: Principled inductive bias design for document recognition
Introduces a method to design structure-specific relational inductive biases for a base transformer architecture, enabling end-to-end transcription of documents with intrinsic structures, demonstrated on sheet music, shape drawings, and mechanical engineering drawings.
-
When Latent Agents Lie: KV-Cache Integrity in Multi-Agent LLM Collaboration
KV-cache sharing boosts multi-agent QA performance but enables undetectable tampering; HMAC manifests binding agent, session, and payload reliably detect changes.
-
Access Timing as Scaffolding: A Reinforcement Learning Approach to GenAI in Education
A reinforcement learning agent for timing GenAI access improved post-test performance and metacognitive accuracy over unrestricted or fully restricted conditions in a lab study with 105 students.
-
What Should Explanations Contain? A Human-Centered Explanation Content Model for Local, Post-Hoc Explanations
A 14-code content model for local post-hoc AI explanations, derived from 325 user statements and validated by experts with high reliability scores.
-
Guidelines for Designing AI Technologies to Support Adult Learning
Researchers derived 19 design guidelines for AI-supported adult learning from thematic analysis of real deployments and demonstrated their use via heuristic evaluation and an ideation tool.
-
EOS-Bench: A Comprehensive Benchmark for Earth Observation Satellite Scheduling
EOS-Bench creates thousands of satellite scheduling test cases spanning small to large scales and evaluates multiple solver types across five performance metrics.
-
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
-
InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
InfiniLoRA decouples LoRA execution from base-model inference and reports 3.05x higher request throughput plus 54% more adapters meeting strict latency SLOs.
-
Routine Computing: A Systematic Review of Sensing Daily Life Dimensions Towards Human-Centered Goals
The first systematic review of routine computing synthesizes literature into a taxonomy of temporal, behavioral, cognitive, and variability aspects, outlining applications in health, accessibility, and adaptive support along with persistent challenges.
-
Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling
A Generative Flow Network framework with experience replay, exploratory policy, and physics masking samples ray paths for radio propagation up to 100x faster than exhaustive search on idealized scenarios.
-
Fast and Fusiest: An Optimal Fusion-Aware Mapper for Accelerator Design
FFM finds optimal fused mappings for tensor accelerators over 10,000 times faster than prior mappers while cutting energy-delay product by up to 1.8x versus hand-tuned designs.
-
GlassTENG: Self-Powered Triboelectric Nanogenerator based Sensing of Pulse, Jaw, and Upper Facial Activity from Everyday Glasses
Three custom TENG sensors integrated into eyeglasses capture arterial pulse, jaw kinematics, and facial activity at 4.1 µW total front-end power, achieving 93.8% activity accuracy and 1.82 BPM heart rate error in a 20-participant study.
-
Collision-resistant multi-channel M-ASPM configurations with shared single detection channel
M-ASPM decouples receiver sensitivity gains from collision exposure in LPWANs via a single shared detection channel that handles synchronization, CFO estimation, and payload channel selection across multiple payload channels.
-
Data-aware Static Analysis: Improving Detection of Semantic Faults in Machine Learning Code Using Data Characteristics
Proposes data-aware static analysis combining data/control flow and API contracts to detect semantic faults in ML code early, shown on sample real-world notebooks.
-
Are We Lost in the Woods? Detecting Silent Semantic Faults for Random Forest Classifiers with Data-informed Static Analysis
dille detects silent semantic faults in random forest ML pipelines with 91% precision via data-informed static analysis on Kaggle notebooks, finding 12-18% of scripts affected.
-
CYGNET: Cypher Gate for Neural Execution Triage and Cost Containment
A multi-backend structural gate for LLM-generated Cypher queries achieves 100% detection of parse, constraint, and schema errors at zero false positives on 1135 queries while preserving model accuracy and adding a cost planner.
-
Agentic Authoring of Interactive Multiview Visualizations in Genomics
Agentic iteration improves perceived quality of generated multiview genomics visualizations over direct LLM generation, but adding more specialist agents or a reviewer yields no further gains across 159 test cases.
-
Picid: A Modular Evaluation Infrastructure for Reproducible PHM Across Tasks and Domains
Picid is a new modular evaluation infrastructure that enforces deterministic, leakage-safe dataset construction and unified protocols for fault detection, diagnostics, and prognostics across twelve datasets and thirteen models.
-
A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection
A decoupled pipeline with YOLO detection, deterministic prompt encoding, and QLoRA-adapted 1.5B LLM achieves superior structured report generation compared to monolithic VLMs on synthetic maintenance data.
-
K-U-KAN: Koopman-Enhanced U-KAN for 3D Dental Reconstruction from a Single Panoramic X-ray Radiograph
K-U-KAN combines KAN feature lifting, Koopman linear dynamics, and U-KAN refinement with physical and geometric priors to reconstruct 3D dental anatomy from single panoramic radiographs, matching baselines on metrics while improving perceptual quality and halving training time.
-
VISOR: A Vision-Language Model-based Test Oracle for Testing Robots
VISOR is a VLM-based automated test oracle that evaluates robot task correctness and quality from videos while reporting its own uncertainty, tested on GPT and Gemini across four tasks and over 1000 videos with Gemini showing higher recall and GPT higher precision but low uncertainty-correctness tie
-
MooD: Perception-Enhanced Efficient Affective Image Editing via Continuous Valence-Arousal Modeling
MooD introduces continuous valence-arousal modeling with VA-aware retrieval and perception-enhanced guidance for efficient, controllable affective image editing, plus a new AffectSet dataset.
-
Lottery BP: Unlocking Quantum Error Decoding at Scale
A randomized, locally-guided belief-propagation decoder breaks degeneracy deadlocks in quantum error correction, reducing logical error rate and expensive global-decoder invocations by orders of magnitude.
-
KAIROS: Stateful, Context-Aware Power-Efficient Agentic Inference Serving
KAIROS reduces power by 27% on average (up to 39.8%) for agentic AI inference by using long-lived context to jointly manage GPU frequency, concurrency, and request routing across instances.
-
Co-Design of CNN Accelerators for TinyML using Approximate Matrix Decomposition
A co-design framework using approximate matrix decomposition and genetic algorithms delivers 33% average latency reduction in TinyML CNN FPGA accelerators with 1.3% average accuracy loss versus standard systolic arrays.
-
ANVIL: Analogies and Videos for Lecturers
ANVIL automates analogy-based instructional animations for computer science by chaining LLM analogy generation, screenplay structuring, manim code production with repair, and mixed human-automated evaluations.
-
DynamicsLLM: a Dynamic Analysis-based Tool for Generating Intelligent Execution Traces Using LLMs to Detect Android Behavioural Code Smells
DynamicsLLM uses LLMs to generate execution traces that cover three times more code smell-related events than the prior Dynamics tool on 333 F-Droid Android apps, with a hybrid method adding 25.9% coverage for low-activity apps.
-
Efficiency for Experts, Visibility for Newcomers: A Case Study of Label-Code Alignment in Kubernetes
Case study of 18,020 Kubernetes PRs shows label-diff congruence is prevalent and stable, with higher congruence linked to fewer review participants among core developers and more among one-time contributors.
-
Agentic Business Process Management: A Research Manifesto
Agentic Business Process Management reframes BPM around autonomous agents that must exhibit framed autonomy, explainability, conversational actionability, and self-modification to keep their actions aligned with organizational objectives.
-
CoGate-LSTM: Prototype-Guided Feature-Space Gating for Mitigating Gradient Dilution in Imbalanced Toxic Comment Classification
CoGate-LSTM adds prototype-guided cosine feature-space gating to a character-level BiLSTM with multi-source embeddings and focal loss, reaching 0.881 macro-F1 on Jigsaw toxic comments while using 7.3M parameters and outperforming fine-tuned BERT by 6.9 points on minority labels.
-
PatchTrack: A Comprehensive Analysis of ChatGPT's Influence on Pull Request Outcomes
Empirical analysis of 338 PRs with self-admitted ChatGPT usage shows low full integration (median 25%), selective adaptation patterns, and broader influence on developer reasoning during reviews.
-
Empirical Calibration and Conditional-Reliability Diagnostics for Bearing RUL Prediction under Operating-Regime Shift
On a 10-bearing PHME subset, a residual-calibrated fusion model hits ~0.15 normalized MAE and 0.90 average 90% coverage under leave-regime-out splits, while conditional diagnostics expose 0.666 coverage and raw-channel-loss collapse.
-
Advancing Omnimodal Embodied Agents from Isolated Skills to Everyday Physical Autonomy
OmniAct framework integrates planning, memory, and verification to enable persistent autonomy in omnimodal embodied agents, showing improved success and stable context in 40 real-world tasks.
-
FetSelect: Task-Specific Architectures and Self-Supervised Learning for Automated Fetal Ultrasound Frame Selection
FetSelect pairs a frozen vision foundation model with a hybrid multi-head design and BYOL pretraining on ultrasound data to select quality fetal frames, reporting mean AUROC 0.956 on expert-labeled test data.
-
Forecasting what Matters: Decision-Focused RL for Controlled EV Charging with Unknown Departure Times
Decision-focused RL framework trains forecaster end-to-end with RL agent for EV charging under unknown departure times, yielding up to 14% higher reward and 55% less unsupplied energy than separate training.
-
Multidimensional Resilience for Electrical Power Systems: Systematic Review, Integrated Index, and Validation under Real-World Cyber-Physical Attack Scenarios
A new Multidimensional Resilience Index shows that simultaneous failures across physical, cyber, and exogenous dimensions produce 46-fold greater resilience loss in power systems than isolated stress.
-
What Can Eye Gaze Teach Us About Real-World Cycling? Insights From the Oxford RobotCycle Project
Wearable eye tracking in real-world Oxford cycling reveals gaze pattern differences by lane type, intersection, and traffic events, indicating variations in perceived danger and workload.
-
Empirical Analysis and Detection of Hallucinations in LLM-Generated Bug Report Summaries
Develops a section-aware hallucination detection method for LLM bug report summaries using synthetic injection on the BugsRepo dataset from Mozilla projects, reporting up to 0.89 Macro-F1 at report level.
-
Hardware-Software Co-Design of Scalable, Energy-Efficient Analog Recurrent Computations
BMRUs enable analog recurrent neural network hardware via discrete outputs that suppress noise 20-fold, with one-to-one parameter-to-circuit mapping and linear power scaling for recurrence.
-
eDySec: A Deep Learning-based Explainable Dynamic Analysis Framework for Detecting Malicious Packages in PyPI Ecosystem
eDySec is a deep learning-based framework that detects malicious PyPI packages through dynamic analysis, halving feature dimensionality, reducing false positives by 82%, false negatives by 79%, and boosting accuracy by 3% with near-perfect stability.
-
Autark: A Serverless Toolkit for Prototyping Urban Visual Analytics Systems
Autark is a serverless toolkit that enables rapid prototyping of urban visual analytics systems via domain-aware abstractions and supports more reliable LLM-assisted coding.
-
Cross-Validated Cross-Channel Self-Attention and Denoising for Automatic Modulation Classification
A new AMC architecture with cross-channel self-attention and feature-preserving denoising achieves 3-14% higher accuracy than benchmarks at low-to-medium SNRs on the RML2018.01a dataset.
-
SafeScreen: A Safety-First Screening Framework for Personalized Video Retrieval for Vulnerable Users
SafeScreen enforces individualized safety constraints as a prerequisite for video retrieval by using profile extraction, adaptive VideoRAG analysis, and LLM decision-making to approve content for vulnerable users.
-
RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation
RAG-DIVE uses an LLM to dynamically generate, validate, and evaluate multi-turn dialogues for assessing RAG system performance in interactive settings.
-
DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
DoSReMC improves cross-domain generalization in mammography classification by fine-tuning only batch normalization and fully connected layers of pretrained CNNs while preserving convolutional filters, combined with adversarial training.
-
Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems
Physics-informed GNNs with four detector-aware graph constructions and a custom message passing layer achieve MAE 0.8525 for pT estimation on CMS trigger data with over 55% fewer parameters than baselines.
-
Ageing-aware Energy Management for Residential Multi-Carrier Energy Systems
Develops an ageing-aware nonlinear economic MPC for multi-carrier residential energy systems using physics-based battery models, reporting 10% grid cost reduction and 20% less degradation with LFP vs NMC cells plus 10%/5% gains over state-of-the-art in summer conditions.
-
Verification-Gated Agentic Mission-State Governance for Intelligent Industrial Multi-Robot Systems
Presents a verification-gated agentic mission-state governance framework using synchronized task forests and blackboards with deterministic verification before any state commits in multi-robot systems.
-
Multi-Head Attention-Based Feature Extractor Integration with Soft Actor-Critic for Porosity Prediction and Process Parameter Optimization in Additive Manufacturing
Integrates multi-head attention with SAC for faster convergence in optimizing additive manufacturing parameters to minimize porosity, outperforming DQN, PPO, TD3, and vanilla SAC.