6 papers
From Errors to Proofs: Minimal-Core-Guided Repair for Neuro-Symbolic Constraint Solving
Dipankar Sarkar
Making language models solve constraint problems reliably often means having them translate the problem into a formal specification and delegating the search to a sound solver. But…
A Four-Axis Trustworthiness Benchmark for LLM-as-Judge in Principle-Based Regulation
Dipankar Sarkar
Principle-based regulation, with evaluative standards such as "fair, clear, and not misleading" or "deliver good outcomes", cannot be reduced to binary predicates, and LLM-as-judge…
Operator-Aware Mixed-Precision Tolerance Calibration for Tensor Kernels
Dipankar Sarkar
Most tensor-kernel correctness tests go through a fixed-shape all close-style check with hand-picked absolute and relative tolerances. The thresholds are copied across the corpus a…
Static PTX Metrics Track Structural Kernel Regressions but Miss Semantic Ones
Dipankar Sarkar
We pair each GPU kernel's static PTX metrics (registers, spills, instruction count) with CUDA-event-timed runtime on five GPU classes: RTX 3060, A10, L40S, A100 SXM4, and H100 NVL.…
The Correctness Illusion in LLM-Generated GPU Kernels
Dipankar Sarkar
Benchmarks for LLM-generated GPU kernels (KernelBench, TritonBench, GEAK) score correctness through fixed-shape, small-sample allclose-style checks. The number of inputs varies bet…
Before the Pull Request: Mining Multi-Agent Coordination
Dipankar Sarkar
Autonomous coding agents now open millions of pull requests, yet large-scale studies find their PRs are produced faster but accepted less often - a coordination and trust gap that…