Abhinaba Basu

12 papers Journal 12

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Budget-Sensitive Discovery Scoring: A Formally Verified Framework for Evaluating AI-Guided Scientific Selection. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	Contextual StereoSet: Stress-Testing Bias Alignment Robustness in Large Language Models. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	Cross-Domain Uncertainty Quantification for Selective Prediction: A Comprehensive Bound Ablation with Transfer-Informed Betting. CoRR Abhinaba Basu
2026	J	`jnl`	ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	Proof-Carrying Materials: Falsifiable Safety Certificates for Machine-Learned Interatomic Potentials. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	Structural Sensitivity in Compressed Transformers: Error Propagation, Lyapunov Stability, and Formally Verified Bounds. CoRR Abhinaba Basu
2026	J	`jnl`	The Coordinate System Problem in Persistent Structural Memory for Neural Architectures. CoRR Abhinaba Basu
2026	J	`jnl`	Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents. CoRR Abhinaba Basu
2026	J	`jnl`	When AI Shows Its Work, Is It Actually Working? Step-Level Evaluation Reveals Frontier Language Models Frequently Bypass Their Own Reasoning. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	When Does Content-Based Routing Work? Representation Requirements for Selective Attention in Hybrid Sequence Models. CoRR Abhinaba Basu
2026	J	`jnl`	When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making. CoRR Abhinaba Basu, Pavan Chakraborty
2026	J	`jnl`	Why Agent Caching Fails and How to Fix It: Structured Intent Canonicalization with Few-Shot Learning. CoRR Abhinaba Basu

2025 Best paper conf

Assessing the Effectiveness of the Tigress Obfuscator Against MOPSA and BinaryNinja.

CheckMATE

Nicolò Altamura, Enrico Bragastini, Marco Campion, Mila Dalla Preda

2026 Best paper preprint

ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage.

arXiv

Chang Liu, Noah Fleischmann, Nicolò Altamura, Edward Raff, James Holt, Kristopher Micinski