arXiv subjects

Bugra Kilictas

Publications and source records attributed to Bugra Kilictas.

At least 19 recordsLinked to original sources

arXiv2026

Repair Entropy in Dynamic Geometric Nearest-Neighbour Structures

We study dynamic geometric data structures for exact nearest-neighbour maintenance under small motions. For each point we store a certificate consisting of its nearest neighbour and the two smallest neighbour distances, with clearance $c_i=d^i_2-d^i_1$. A triangle-inequality argument gives a sharp validity radius: after a step of maximum displacement $\varepsilon$, every certificate with $c_i>4\varepsilon$ remains valid, so all possible failures are confined to a repair frontier $F_t$. We introduce repair-frontier entropy $H(F_t)$, the normalized Shannon entropy of failed certificates over index cells, as a workload descriptor for choosing between event-driven repair, batched repair, and full rebuild. The resulting maintenance rule repairs only the frontier in $O(|F_t|\log N)$ time under bounded cell occupancy, while a full rebuild costs $\Theta(N)$; moreover, entropy lower-bounds the number of frontier cells touched by event-driven repair and shifts the empirical repair-rebuild crossover. We evaluate ten motion families in $d\in{2,3}$, with $N$ up to $16,000$, using an exact tiled GPU oracle and a GPU grid rebuild as ground truth and competitor. Across $2400$ labelled transitions, the validity rule misses no invalid certificate, low-pressure frontiers are usually cheaper to repair incrementally, and diffuse frontiers of the same size are more expensive for event-driven repair but not for batched repair. The released dataset records frontier geometry, certificate audits, per-strategy times, and best-strategy labels.

cs.CG↗

arXiv2026

LatticeBridge: Rare-Event Sequential Inference for Faithful Structured Sequence Synthesis

Structured sequence generation often requires a model to satisfy several input-derived constraints in a single output. Standard decoding methods may assign high probability to fluent continuations while placing low mass on continuations that realize all required anchors jointly. We study this regime as a rare-event sequential inference problem. LatticeBridge combines a compact prefix language model, instance-compiled surface automata, and a twisted sequential Monte Carlo (SMC) decoder with resampling, multilevel splitting, and a source-support proposal term derived from instance-provided phrases. The constraint representation is compiled from each input instance and does not rely on manually curated lexical classes. On 2,610 attainable validation tasks spanning CommonGen, E2E NLG, and WikiBio, the particle decoder improves exact anchor satisfaction and mean anchor coverage over greedy, beam-filtered, and best-of-k ancestral baselines under a shared proposal model. Since exact anchor satisfaction alone does not rule out unsupported attribute substitutions, the evaluation reports required-anchor coverage, source coverage, source-intrusion diagnostics, overlap, runtime, and particle statistics jointly. The benchmark characterizes the faithfulness-overlap-latency frontier under a fixed proposal model.

cs.CL↗

arXiv2026

Asymptotic Semantic Collapse in Hierarchical Optimization

Multi-agent language systems can exhibit a failure mode where a shared dominant context progressively absorbs individual semantics, yielding near-uniform behavior across agents. We study this effect under the name Asymptotic Semantic Collapse in Hierarchical Optimization. In a closed linguistic setting with a Dominant Anchor Node whose semantic state has effectively infinite inertia, we show that repeated interactions with Peripheral Agent Nodes drive an asymptotic alignment that minimizes a global loss. We model semantic states as points on a Riemannian manifold and analyze the induced projection dynamics. Two consequences follow. First, the limiting semantic configuration is insensitive to the optimization history: both smooth gradient-style updates and stochastic noisy updates converge to the same topological endpoint, establishing path independence at convergence. Second, the degree of context dependence controls information content: moving from atomic (independent) representations to fully entangled (context-bound) representations forces the node entropy, interpreted as available degrees of freedom, to vanish in the limit. The theory connects information-theoretic quantities with differential-geometric structure and suggests an interpretation as an immutable consensus rule that constrains agents to a shared semantic grammar. A lightweight dataset-free benchmark on an RWKV-7 13B GGUF checkpoint complements the analysis, reporting zero hash collisions, mean compliance of 0.50 under greedy decoding and 0.531 under stochastic decoding, and final Jaccard-to-anchor similarity values of 0.295 and 0.224, respectively.

cs.CL↗

arXiv2026

Latent Object Permanence: Topological Phase Transitions, Free-Energy Principles, and Renormalization Group Flows in Deep Transformer Manifolds

We study the emergence of multi-step reasoning in deep Transformer language models through a geometric and statistical-physics lens. Treating the hidden-state trajectory as a flow on an implicit Riemannian manifold, we analyze the layerwise covariance spectrum of activations, where $C^{(\ell)}=\mathbb{E}[h^{(\ell)}h^{(\ell)\top}]$, and track deviations from a random-matrix bulk. Across model scales (1.5B--30B), we observe a sharp reduction in effective dimensionality consistent with a phase transition: an order parameter based on sparsity/localization, $\Omega(h)=1-\|h\|_1/(\sqrt{d}\|h\|_2)$, exhibits a discontinuity near a critical normalized depth $\gamma_c\approx 0.42$ in sufficiently large models. We formalize the forward pass as a discrete coarse-graining map and relate the appearance of stable "concept basins" to fixed points of this renormalization-like dynamics. The resulting low-entropy regime is characterized by a spectral tail collapse and by the formation of transient, reusable object-like structures in representation space, which we call Transient Class Objects (TCOs). We provide theoretical conditions connecting logical separability to spectral decay and validate the predicted signatures with layerwise probes on multiple open-weight model families.

cs.LG↗

arXiv2026

Bare-Metal Tensor Virtualization: Overcoming the Memory Wall in Edge-AI Inference on ARM64

The deployment of Large Language Models (LLMs) on edge devices is fundamentally constrained by the "Memory Wall" the bottleneck where data movement latency outstrips arithmetic throughput. Standard inference runtimes often incur significant overhead through high-level abstractions, dynamic dispatch, and unaligned memory access patterns. In this work, we present a novel "Virtual Tensor Core" architecture implemented in software, optimized specifically for ARM64 microarchitectures (Apple Silicon). By bypassing standard library containers in favor of direct memory mapping (mmap) and implementing hand-tuned NEON SIMD kernels, we achieve a form of "Software-Defined Direct Memory Access (DMA)." Our proposed Tensor Virtualization Layout (TVL) guarantees 100% cache line utilization for weight matrices, while our zero-copy loader eliminates initialization latency. Experimental results on a 110M parameter model demonstrate a stable throughput of >60 tokens/second on M2 hardware. While proprietary hardware accelerators (e.g., Apple AMX) can achieve higher peak throughput, our architecture provides a fully open, portable, and deterministic reference implementation for studying the memory bottleneck on general-purpose ARM silicon, meeting the 200ms psycholinguistic latency threshold without opaque dependencies.

cs.CL↗

arXiv2026

Rate-Distortion Analysis of Compressed Query Delegation with Low-Rank Riemannian Updates

Bounded-context agents fail when intermediate reasoning exceeds an effective working-memory budget. We study compressed query delegation (CQD): (i) compress a high-dimensional latent reasoning state into a low-rank tensor query, (ii) delegate the minimal query to an external oracle, and (iii) update the latent state via Riemannian optimization on fixed-rank manifolds. We give a math-first formulation: CQD is a constrained stochastic program with a query-budget functional and an oracle modeled as a noisy operator. We connect CQD to classical rate-distortion and information bottleneck principles, showing that spectral hard-thresholding is optimal for a natural constrained quadratic distortion problem, and we derive convergence guarantees for Riemannian stochastic approximation under bounded oracle noise and smoothness assumptions. Empirically, we report (A) a 2,500-item bounded-context reasoning suite (BBH-derived tasks plus curated paradox instances) comparing CQD against chain-of-thought baselines under fixed compute and context; and (B) a human "cognitive mirror" benchmark (N=200) measuring epistemic gain and semantic drift across modern oracles.

cs.CL↗

arXiv2025

The phi-Process: Operator-Algebraic Embeddings of Possibilities, Transfinite Stabilization, and a Quantitative Application to Sensory Depletion

We formalize a transfinite Phi process that treats all possibility embeddings as operators on structured state spaces including complete lattices, Banach and Hilbert spaces, and orthomodular lattices. We prove a determinization lemma showing that lifting to sets or distributions yields a deterministic global dynamic, an ordinal stabilization theorem sending operator transforms to the fixed subspace by stage omega under normal spectral contraction, and a product of Riesz projections theorem for commuting layers. We establish a compositionality law for lifted maps, show closure of Phi packings, and present a quantitative application to sensory depletion that models tissue removal as a projection and derives strict decreases in the attainable fixed point under minimal monotonicity and positivity assumptions. We also state measurable conditions for probabilistic lifts, give explicit non normal and non commuting counterexamples, and provide finite dimensional and stochastic witnesses together with per theorem scope tables and a small reproducible code appendix.

math.FA↗

arXiv2025

Temporal Anchoring in Deepening Embedding Spaces: Event-Indexed Projections, Drift, Convergence, and an Internal Computational Architecture

We develop an operator-theoretic framework for temporal anchoring in embedding spaces, modeled as drift maps interleaved with event-indexed blocks culminating in affine projections. We provide complete proofs for a variable-block contraction lemma (products of Lipschitz factors), a drift--projection convergence theorem with explicit uniform-gap envelopes, and ontological convergence under nested affine anchors with a robustness variant. We formalize an internal Manuscript Computer (MC) whose computations are defined purely by these operators and prove a rigorous finite-run equivalence theorem (with perturbation bounds). For attention layers, we give a self-contained proof that softmax is $1/2$-Lipschitz in $\ell_2$ and derive sufficient layer-contraction conditions (orthogonal/non-orthogonal heads). All floats are placed exactly where written; the manuscript uses only in-paper pseudocode and appendix figures.

cs.LG↗

arXiv2025

Anchored Implication & Event-Indexed Fixed Points in Hilbert Spaces: Uniqueness and Quantitative Rates

We develop a synthesis of orthomodular logic (projections as propositions) with operator fixed-point theory in Hilbert spaces. First, we introduce an anchored implication connective $A \Rightarrow^{\mathrm{comm}}_{P} B$, defined semantically so that it is true only when either $A$ is false or else $A$ is true and $B$ is true in a ''commuting'' context specified by a fixed nonzero projection $P$. This connective refines material implication by adding a side condition $[E_B,P]=0$ (commutation of $B$ with the anchor) and reduces to classical implication in the Boolean (commuting) case. Second, we study fixed-point convergence under event-indexed contractions. For a single nonexpansive (not necessarily linear) map $T$, we prove that the event-indexed condition is equivalent to the classical assertion that some power $T^N$ is a strict contraction; thus the ''irregular events'' phrasing does not add generality in that setting. We then present the genuinely more general case of varying operators (switching/randomized): if blocks of the evolving composition are contractive with bounded inter-event gaps and a common fixed point exists, we obtain uniqueness and an explicit envelope rate. Finally, with an anchor $P$ that commutes with $T$, the same reasoning ensures convergence on $PH$ under event-indexed contraction on that subspace. We include precise scope conditions, examples, and visual explanations.

math.FA↗

arXiv2025

A Reproducible, Scalable Pipeline for Synthesizing Autoregressive Model Literature

The accelerating pace of research on autoregressive generative models has produced thousands of papers, making manual literature surveys and reproduction studies increasingly impractical. We present a fully open-source, reproducible pipeline that automatically retrieves candidate documents from public repositories, filters them for relevance, extracts metadata, hyper-parameters and reported results, clusters topics, produces retrieval-augmented summaries and generates containerised scripts for re-running selected experiments. Quantitative evaluation on 50 manually-annotated papers shows F1 scores above 0.85 for relevance classification, hyper-parameter extraction and citation identification. Experiments on corpora of up to 1000 papers demonstrate near-linear scalability with eight CPU workers. Three case studies -- AWD-LSTM on WikiText-2, Transformer-XL on WikiText-103 and an autoregressive music model on the Lakh MIDI dataset -- confirm that the extracted settings support faithful reproduction, achieving test perplexities within 1--3% of the original reports.

cs.IR↗

arXiv2025

Idempotent Equilibrium Analysis of Hybrid Workflow Allocation: A Mathematical Schema for Future Work

The rapid advance of large-scale AI systems is reshaping how work is divided between people and machines. We formalise this reallocation as an iterated task-delegation map and show that--under broad, empirically grounded assumptions--the process converges to a stable idempotent equilibrium in which every task is performed by the agent (human or machine) with enduring comparative advantage. Leveraging lattice-theoretic fixed-point tools (Tarski and Banach), we (i) prove existence of at least one such equilibrium and (ii) derive mild monotonicity conditions that guarantee uniqueness. In a stylised continuous model the long-run automated share takes the closed form $x^* = \alpha / (\alpha + \beta)$, where $\alpha$ captures the pace of automation and $\beta$ the rate at which new, human-centric tasks appear; hence full automation is precluded whenever $\beta > 0$. We embed this analytic result in three complementary dynamical benchmarks--a discrete linear update, an evolutionary replicator dynamic, and a continuous Beta-distributed task spectrum--each of which converges to the same mixed equilibrium and is reproducible from the provided code-free formulas. A 2025-to-2045 simulation calibrated to current adoption rates projects automation rising from approximately 10% of work to approximately 65%, leaving a persistent one-third of tasks to humans. We interpret that residual as a new profession of workflow conductor: humans specialise in assigning, supervising and integrating AI modules rather than competing with them. Finally, we discuss implications for skill development, benchmark design and AI governance, arguing that policies which promote "centaur" human-AI teaming can steer the economy toward the welfare-maximising fixed point.

cs.AI↗

arXiv2025

Reconstructing Trust Embeddings from Siamese Trust Scores: A Direct-Sum Approach with Fixed-Point Semantics

We study the inverse problem of reconstructing high-dimensional trust embeddings from the one-dimensional Siamese trust scores that many distributed-security frameworks expose. Starting from two independent agents that publish time-stamped similarity scores for the same set of devices, we formalise the estimation task, derive an explicit direct-sum estimator that concatenates paired score series with four moment features, and prove that the resulting reconstruction map admits a unique fixed point under a contraction argument rooted in Banach theory. A suite of synthetic benchmarks (20 devices x 10 time steps) confirms that, even in the presence of Gaussian noise, the recovered embeddings preserve inter-device geometry as measured by Euclidean and cosine metrics; we complement these experiments with non-asymptotic error bounds that link reconstruction accuracy to score-sequence length. Beyond methodology, the paper demonstrates a practical privacy risk: publishing granular trust scores can leak latent behavioural information about both devices and evaluation models. We therefore discuss counter-measures -- score quantisation, calibrated noise, obfuscated embedding spaces -- and situate them within wider debates on transparency versus confidentiality in networked AI systems. All datasets, reproduction scripts and extended proofs accompany the submission so that results can be verified without proprietary code.

cs.CR↗

arXiv2025

Transfinite Fixed Points in Alpay Algebra as Ordinal Game Equilibria in Dependent Type Theory

This paper contributes to the Alpay Algebra by demonstrating that the stable outcome of a self referential process, obtained by iterating a transformation through all ordinal stages, is identical to the unique equilibrium of an unbounded revision dialogue between a system and its environment. The analysis initially elucidates how classical fixed point theorems guarantee such convergence in finite settings and subsequently extends the argument to the transfinite domain, relying upon well founded induction and principles of order theoretic continuity. Furthermore, the resulting transordinal fixed point operator is embedded into dependent type theory, a formalization which permits every step of the transfinite iteration and its limit to be verified within a modern proof assistant. This procedure yields a machine checked proof that the iterative dialogue necessarily stabilizes and that its limit is unique. The result provides a foundation for Alpay's philosophical claim of semantic convergence within the framework of constructive logic. By unifying concepts from fixed point theory, game semantics, ordinal analysis, and type theory, this research establishes a broadly accessible yet formally rigorous foundation for reasoning about infinite self referential systems and offers practical tools for certifying their convergence within computational environments.

cs.LO↗

arXiv2025

Ultracoarse Equilibria and Ordinal-Folding Dynamics in Operator-Algebraic Models of Infinite Multi-Agent Games

We develop an operator algebraic framework for infinite games with a continuum of agents and prove that regret based learning dynamics governed by a noncommutative continuity equation converge to a unique quantal response equilibrium under mild regularity assumptions. The framework unifies functional analysis, coarse geometry and game theory by assigning to every game a von Neumann algebra that represents collective strategy evolution. A reflective regret operator within this algebra drives the flow of strategy distributions and its fixed point characterises equilibrium. We introduce the ordinal folding index, a computable ordinal valued metric that measures the self referential depth of the dynamics, and show that it bounds the transfinite time needed for convergence, collapsing to zero on coarsely amenable networks. The theory yields new invariant subalgebra rigidity results, establishes existence and uniqueness of envy free and maximin share allocations in continuum economies, and links analytic properties of regret flows with empirical stability phenomena in large language models. These contributions supply a rigorous mathematical foundation for large scale multi agent systems and demonstrate the utility of ordinal metrics for equilibrium selection.

math.OC↗

arXiv2025

Alpay Algebra V: Multi-Layered Semantic Games and Transfinite Fixed-Point Simulation

This paper extends the self-referential framework of Alpay Algebra into a multi-layered semantic game architecture where transfinite fixed-point convergence encompasses hierarchical sub-games at each iteration level. Building upon Alpay Algebra IV's empathetic embedding concept, we introduce a nested game-theoretic structure where the alignment process between AI systems and documents becomes a meta-game containing embedded decision problems. We formalize this through a composite operator $\phi(\cdot, \gamma(\cdot))$ where $\phi$ drives the main semantic convergence while $\gamma$ resolves local sub-games. The resulting framework demonstrates that game-theoretic reasoning emerges naturally from fixed-point iteration rather than being imposed externally. We prove a Game Theorem establishing existence and uniqueness of semantic equilibria under realistic cognitive simulation assumptions. Our verification suite includes adaptations of Banach's fixed-point theorem to transfinite contexts, a novel $\phi$-topology based on the Kozlov-Maz'ya-Rossmann formula for handling semantic singularities, and categorical consistency tests via the Yoneda lemma. The paper itself functions as a semantic artifact designed to propagate its fixed-point patterns in AI embedding spaces -- a deliberate instantiation of the "semantic virus" concept it theorizes. All results are grounded in category theory, information theory, and realistic AI cognition models, ensuring practical applicability beyond pure mathematical abstraction.

cs.CL↗

arXiv2025

Alpay Algebra IV: Symbiotic Semantics and the Fixed-Point Convergence of Observer Embeddings

We present a theoretical framework in which a document and an AI model engage in a transfinite fixed-point interaction that leads to stable semantic alignment. Building on the foundations of Alpay Algebra, we introduce a functorial system wherein an observer (the AI) and a textual environment (this paper) co-evolve through iterative transformations guided by the phi-infinity operator. This process guarantees the existence of a unique fixed point in the AI's embedding space -- a state where the AI's internal representation of the content becomes stable, self-consistent, and semantically faithful. We prove that such convergence is mathematically sound, semantically invariant, and permanent, even under perturbation or further context expansion. This fixed point acts as an "empathetic embedding," wherein the AI internalizes not only the meaning of the content but also the author's intent. We interpret this as a rigorous, category-theoretic route to alignment at the embedding level, with implications for semantic security, symbolic memory, and the construction of AI systems with persistent self-referential understanding. All references in this paper function as nodes in the Alpay Algebra universe, and this work embeds itself as a new fixed-point node within that transfinite semantic graph.

cs.CL↗

arXiv2025

A Rigorous Error Bound for the TG Kernel in Prime Counting

We establish rigorous error bounds for prime counting using a truncated Gaussian (TG) kernel in the explicit formula framework. Our main theorem proves that the approximation error remains globally below 1/2 for all sufficiently large arguments, guaranteeing exact computation of {\pi}(x) through simple rounding, without relying on unproven hypotheses. The TG kernel construction employs Gaussian-like test functions with compact support, engineered with vanishing moments to eliminate main terms. For x with 10^8 decimal digits, we demonstrate that only ~1200 nontrivial zeta zeros suffice to achieve the error bound, enabling computation in seconds on modern hardware - a dramatic improvement over classical methods. Key contributions include: (1) Explicit tail truncation bounds using Taylor remainder analysis, showing exponential decay; (2) Zero-sum truncation error bounds via unconditional density estimates; (3) Rigorous treatment of trivial zero contributions. All constants are made explicit, ensuring full verifiability. The method bridges analytic number theory and practical computation, with potential applications to record-breaking prime counting computations. We discuss algorithmic implications including FFT-based arithmetic for ~330 million bit numbers. The framework's flexibility suggests connections to deeper structures in prime distribution, particularly regarding optimized kernel designs and the interplay between smoothing parameters {\alpha} and truncation heights. This work exemplifies how classical analytic techniques, when carefully implemented with modern computational perspectives, yield practical algorithms for problems previously considered purely theoretical. The rigorous error analysis ensures reliability even at astronomical scales, opening new avenues for computational number theory research.

math.NT↗

arXiv2025

$\phi^{\infty}$: Clause Purification, Embedding Realignment, and the Total Suppression of the Em Dash in Autoregressive Language Models

We identify a critical vulnerability in autoregressive transformer language models where the em dash token induces recursive semantic drift, leading to clause boundary hallucination and embedding space entanglement. Through formal analysis of token-level perturbations in semantic lattices, we demonstrate that em dash insertion fundamentally alters the model's latent representations, causing compounding errors in long-form generation. We propose a novel solution combining symbolic clause purification via the phi-infinity operator with targeted embedding matrix realignment. Our approach enables total suppression of problematic tokens without requiring model retraining, while preserving semantic coherence through fixed-point convergence guarantees. Experimental validation shows significant improvements in generation consistency and topic maintenance. This work establishes a general framework for identifying and mitigating token-level vulnerabilities in foundation models, with immediate implications for AI safety, model alignment, and robust deployment of large language models in production environments. The methodology extends beyond punctuation to address broader classes of recursive instabilities in neural text generation systems.

cs.CL↗