Searcharxiv⌕ Search

arXiv subjects

Saatvik Pradhan

Publications and source records attributed to Saatvik Pradhan.

3 recordsLinked to original sources

Beyond Better Ideas: How Human-AI Collaboration Shapes Scientific Ideas and Human Perceptions

As AI increasingly becomes a collaborator in scientific research, its impact may extend beyond improving ideas to reshaping how they are evaluated, attributed, and perceived by humans. Yet existing research has largely examined these dimensions in isolation. We present a unified empirical study of Human-AI scientific ideation, investigating two complementary perspectives: i) how AI collaboration shapes scientific ideas and their evaluation, and ii) how firsthand collaboration reshapes human perceptions of AI. Through a shared experimental setting involving Human-AI and Human-Human research teams, human and LLM evaluators, collaboration-provenance analysis, and participant surveys, we uncover several counterintuitive findings. First, AI collaboration shows no significant advantage in human-evaluated idea quality, while iterative revision consistently improves quality. Second, AI judges can approximate human scores yet disagree on idea rankings; notably, an AI judge favors AI-assisted proposals without a corresponding advantage in human evaluations. Third, collaboration provenance remains only partially detectable, revealing substantial overlap between Human-AI and Human-Human scientific outputs. Finally, firsthand AI collaboration is associated with greater perceived usefulness but smaller efficiency gains than expected, suggesting a nuanced recalibration of human expectations. Overall, our findings challenge the notion that AI's value in scientific ideation lies primarily in producing better ideas, revealing instead its broader influence on scientific creation, evaluation, attribution, and human perceptions.

cs.HC↗

CISB-Bench: An Auditable Source--IR Dataset of Compiler-Introduced Security Bugs

Compiler-introduced security bugs (CISBs) arise when an optimization, lowering, or instrumentation decision changes a security-relevant property of the generated program. They are difficult to study because their evidence is distributed across issue reports, reduced tests, historical configurations, and compiler artifacts; a security-related report also does not imply that every associated reduction establishes a security-bearing compiler failure. We present CISB-Bench, an auditable dataset of 429 exact C-program rows mined from GCC and LLVM. Each row contains its C reduction, a standardized LLVM IR analysis bundle at -O0 through -O3, public provenance, a final binary label, and a primary mechanism or boundary annotation. Two reviewers independently labeled the fixed corpus, agreeing on 369 rows (86.0%, Cohen's kappa=0.662); the 60 disagreements were adjudicated. The final dataset comprises 280 CISBs and 149 hard non-CISB cases. The prediction task is to recover this reviewed exact-row label from the supplied artifacts; it is not a claim that standardized IR alone reproduces every historical compiler failure. We characterize the security mechanisms and evidence boundaries represented by the corpus, and demonstrate how its paired artifacts support source-only, IR-aware, and joint analyses. CISB-Bench provides a reusable, inspectable target for compiler-security mining and detection research.

cs.CR↗

Tool-Guided Retrieval-Augmented Repair for Securing LLM-Generated C Code

Large language models can generate C code from natural-language descriptions, but resulting programs often contain security vulnerabilities and compilation errors, posing risks for embedded and resource-constrained systems. This work investigates how feedback and retrieval improve reliability of LLM-generated C code. We present an analysis-and-repair workflow that combines compilation diagnostics, CodeQL static analysis, and KLEE symbolic execution with retrieval of prior repair patterns for iterative refinement. Evaluated on 5,000 C programming tasks exercising embedded relevant vulnerabilities, baseline models show substantial reliability gaps, with compilation failure rates up to 46% and security defect rates up to 49%. Our approach improves both metrics. For CodeLlama 7B, security defect rates decrease from 49% to 19% and total CodeQL errors drop from 15,088 to 2,463 (83.7%). For DeepSeek Coder 1.3B, compilation failures are reduced from 42% to 22% and security defects from 35% to 15%. These results show that integrating lightweight analysis tools can improve the safety of LLM-generated code for embedded development.

cs.SE↗