{"total":20,"rows":[{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2509.08592","title":"Interpretability as Alignment: Making Internal Understanding a Design Principle","created":"2025-09-10","cited_by_count":3,"area":null},{"id":"2510.06107","title":"Distributional Semantics Tracing: A Framework for Explaining Hallucinations in Large Language Models","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2603.01879","title":"Diagnosing Generalization Failures from Representational Geometry Markers","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2607.18921","title":"Circuit Claims Depend on What Is Extracted and How It Is Compared","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2512.22240","title":"EvoXplain: When Machine Learning Models Agree on Predictions but Disagree on Why -- Measuring Mechanistic Multiplicity Across Training Runs","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2602.22600","title":"Transformers converge to invariant algorithmic cores","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.23821","title":"Perturbation: A simple and efficient adversarial tracer for representation learning in language models","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2605.02234","title":"Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.16023","title":"Judge Circuits Explain Format-Induced Inconsistency in LLM-as-a-Judge","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2601.15029","title":"Emergent, not Immanent: A Baradian Reading of Explainable AI","created":"2026-01-21","cited_by_count":0,"area":null},{"id":"2602.20152","title":"Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2603.17019","title":"Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.18712","title":"Probing for Reading Times","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2605.27033","title":"Tracing Computation Density in LLMs","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.03634","title":"The Role of Rigor in Artificial Intelligence","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2608.24460","title":"Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution","created":"2026-08-25","cited_by_count":0,"area":null},{"id":"2610.09620","title":"The Identifiability and Observability of Deep Normalized Attention","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13018","title":"FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13520","title":"Causal Effect Identifiability in Causal Abstractions: A Strict Hierarchy of Criteria","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}