Md. Amir Khusru Akhtar

Evidence-preserving temporal geography and a village-level Census backbone for Jharkhand, India

Village-level research in India is constrained by a subtle infrastructure problem: authoritative datasets often describe the same named places through different identifiers, administrative hierarchies, time points, and publication systems. We present the Jharkhand Life Atlas (JLA...

Higher-Order Conditional Attainability: Opacity, Observation Order, and Decision Guarantees Beyond Local Views

Local measurements are often treated as if enough of them must eventually reveal a system’s global capability. That inference can fail even when every bounded-order view is known exactly. We develop Higher-Order Conditional Attainability (HCAT), a mathematical framework that turn...

Beyond Causal Identifiability: Order-Indexed Ambiguity, Decision Sufficiency, and Consequence-Directed Intervention Design

Causal discovery often stops when the remaining graphs form an observational or interventional equivalence class, yet class size alone does not measure how consequentially different the surviving models are. We introduce Order-Indexed Causal Ambiguity, a Higher-Order Conditional...

OBLIVION TextLM: A Query-Relative Control Plane for Efficient Generative Language-Model Inference

Long-context language models can ingest far more information than a particular query actually requires, yet retaining every represented distinction is neither equivalent to using it well nor automatically computationally efficient. We present OBLIVION TextLM, a model-agnostic que...

OBLIVION TextLM: A Query-Relative Control Plane for Efficient Generative Language-Model Inference

Long-context language models can ingest far more information than a particular query actually requires, yet retaining every represented distinction is neither equivalent to using it well nor automatically computationally efficient. We present OBLIVION TextLM, a model-agnostic que...

OBLIVION: Query-Relative Neural Computation by Verified Semantic Obligation Retirement

Neural sequence models allocate computation to represented context even when a query requires a subset of distinctions. We introduce OBLIVION, a query-relative neural computation architecture whose active state represents unresolved obligations. Obligations may be born when inter...

OBLIVION: Query-Relative Neural Computation by Verified Semantic Obligation Retirement

Neural sequence models allocate computation to represented context even when a query requires a subset of distinctions. We introduce OBLIVION, a query-relative neural computation architecture whose active state represents unresolved obligations. Obligations may be born when inter...

When Can a Computation Forget? Semantic Lifetime Width and Query-Relative State Retirement

Algorithms are usually analyzed by how much state they store, how wide their dependency graph is, or how many subproblems they retain. These measures are largely query independent: they describe the computation that exists, not the distinctions that still matter to the answer bei...

Semantic Hardness Conservation: An Operational Normal Form for Exact Reasoning After Compression

Exact semantic computation can shrink dramatically when a task ignores distinctions preserved by reusable representations, yet smaller representations need not make reasoning easier. We develop Semantic Hardness Conservation, a normal-form theory that identifies where computation...

Beyond Complete Compilation: Task-Semantic Images and the Complexity of Computing Only What a Query Can See

Knowledge compilation transforms Boolean theories into reusable representations that support many downstream queries, but this generality can preserve distinctions a particular task will never observe. We introduce Task-Semantic Images (TSIs), the exact images of model sets under...

Beyond Fixed Information: Endogenous Construction of Inquiry Interfaces

Artificial intelligence selects actions, tools, hypotheses, and experiments, yet within an information interface whose sensors, measurements, queries, and interventions are executable from the outset. We study a stricter problem: reliable inference may require evidence that becom...

Problem Frames as Computational States: A Theory of Endogenous Inquiry

Most intelligent systems are evaluated after a problem has been specified: variables, goals, actions, evaluation rules, and hypothesis language are fixed. We study the case in which those commitments can be computational states. A problem frame is a tuple of variables, relations,...

Discovery–Closure Adaptive Search: Cost-Normalized Structural Resource Allocation for Constrained Black-Box Optimization

Constrained black-box optimization increasingly combines feasibility management, adaptive search, and learned operator scheduling, making simple hybridization an insufficient novelty claim. This paper develops Discovery–Closure Adaptive Search (DCAS), which treats optimization as...

Learning as Minimum Structural Repair: A Variational Principle for Adaptive Systems

Learning systems are described by the error they reduce, yet post-training adaptation is often governed by a different quantity: how much of a useful system must change before a new requirement becomes true. We formalize this quantity as repair complexity, the minimum admissible...

Discovery–Closure Adaptive Search: Cost-Normalized Structural Resource Allocation for Constrained Black-Box Optimization

Constrained black-box optimization increasingly combines feasibility management, adaptive search, and learned operator scheduling, making simple hybridization an insufficient novelty claim. This paper develops Discovery–Closure Adaptive Search (DCAS), which treats optimization as...