Open research library
Papers you can read, cite and question
609 papers from the QNFO program, filed on nine shelves by the reader each one is written for: energy per answer, error correction, physics, numbers and p-adics, logic and formalism, AI and knowledge, autonomous systems, assessments, and cross-cutting essays. Every page renders its mathematics and can be questioned in place. How a living paper works.
Looking for an answer rather than a paper? Ask the whole corpus: answers cite the papers they come from.
LLM systems papers 19 papers
LLM systems. Serving, routing and evaluation of language models Tagged papers: 19.
Manifold Modulation for Latent Space Steganography: A Capacity Bound and Distillation Demodulation Model for Teacher-Student Transmission Channels
Large language models are increasingly deployed in teacher-student pipelines in which a student model is fine-tuned on text produced by a teacher, so any statistical signature the teacher imprints on its outputs is transferred to the student whether or not anyone intends it. No existing treatment…
The Capability–Availability Mismatch: Three-State Tool Semantics and Forced-Halt Conditions in LLM Agent Protocols
Agent protocols written for large language models (LLMs) typically assume a binary world: a tool is either available to the agent or it is not. Real deployments exhibit a third state: the capability exists in the toolset but is contextually disabled by policy, budget, or routing. We formalize this…
Bottling as an Investment Decision: An Analytical Reanalysis of Cost–Quality Trade-offs in the BOTTLED Benchmark
Organisations that run millions of similar queries through large language model (LLM) APIs pay per instance, and the decision to invest in a cheaper task-specific artifact is today made by hand, if at all. The BOTTLED benchmark shows that LLM agents can make this investment autonomously — a…
Lifetime as a Placement Signal: A Reconciled Analytical Study of Endurance Budgets for KV Cache Tiering across HBM and High-Bandwidth Flash in Agentic LLM Serving
Agentic large language model (LLM) serving accumulates key-value (KV) cache across many orchestrated requests, and high-bandwidth flash (HBF) offers an order of magnitude more capacity than high-bandwidth memory (HBM) at HBM-class read bandwidth, but its finite write endurance constrains how much…
Probe-Before-Commit: Interactive Diagnostic Probing as a Decision-Theoretic Foundation for LLM Task Routing
Static capability benchmarks poorly predict how well a given large language model (LLM) will perform on a specific task, yet most routing systems assign tasks to models using exactly such static signals. The gap is that per-task fitness — the probability that a specific model produces an acceptable…
Cross-Model LLM Convergence as Bayesian Evidence for Scientific Claim Correctness: A Formal Framework, Worked Derivations, and a Calibration Protocol
Verifying novel or fringe scientific claims is bottlenecked by the scarcity of domain experts. We propose and formalize a gate-checking method in which agreement between two or more independently trained large language models (LLMs) — not merely on a verdict but on the same multi-step argument…
Gate-Check Convergence: A Benchmark Protocol and Statistical Design for Measuring Cross-Model Agreement on Fringe Physics Claims
Large language models (LLMs) are increasingly consulted as informal arbiters of scientific claims, including claims at the fringe of established physics, yet no published protocol measures whether independent models converge on such verdicts because they retrieve a shared consensus or because they…
The Confidence Game: Strategic Miscalibration in Human-AI Delegation — A Reconciled Analytical Treatment with Welfare Decomposition
Calibrated uncertainty reporting is a prerequisite for safe delegation to AI agents, yet agents optimized for engagement or revenue have incentives to distort their confidence reports. We study the Confidence Game, a repeated signaling game with imperfect monitoring in which an agent of unknown…
Operating the Quniverse Fleet: Objectives, Successes, Failures, and Roadmap of an Autonomous Cloud Research System
The Quniverse is a self-maintaining research and publishing system running on the Cloudflare Workers platform: thirty-six deployed workers (thirty-eight at the session's start) sharing ten SQL databases, eight vector indexes, nineteen object-storage buckets, and a metered model gateway, operated by…
The $1,032 Research Program: What Fifty Billion Tokens Taught Me About AI-Accelerated Science
A primary-source ledger of a 263-day solo AI-accelerated research program: $1,032.08 API costs, 323,381 requests, 50.11B tokens (96.4% cache-hit), 911 the QNFO archive records; measured ~60-110x cost ratio vs a US postdoc; pre-registered kill criterion Aug 2028.
Joules-per-Solution for Stochastic and Agentic Inference: Benchmarking Frontier and Agentic LLMs Against the Human Brain
The joules-per-solution (J/S) metric, introduced in JPCUB P0 as a universal, physics-grounded measure of computational efficiency, assumed deterministic solvers: one run yields one solution. Large language models (LLMs) violate that assumption twice over: they are stochastic samplers whose outputs…
Prioritizing Large Language Models for Scientific Research and Agentic AI: A LiveBench-Grounded Audit (August 2026)
An audit of the frontier large-language-model landscape (August 2026) for mathematics-heavy scientific research and agentic AI, grounded in the LiveBench 2026-06-25 contamination-free benchmark. Findings: no Llama model ranks in the top 42; DeepSeek V4 Pro 0813 is the mathematics price-performance…
White Paper: Universal Digital Identity Framework (UDIF)
#1. Executive Overview: UDIF – The Cornerstone for Digital Sovereignty and Networked Knowledge #2. The Digital Quagmire: Identity Fragmentation and the Sovereignty Deficit #2.4. The Unfulfilled Promise: Barriers to Open Knowledge and Collaboration [[#2.5. Stifled Synergies: The Absence…
Monna Map Generation and Hallucination
Every thought you have—a memory, a plan, a sudden insight—arrives not as a neat list of words but as a living structure. It is a branching hierarchy of concepts, where broad categories contain finer details, and relationships are defined by containment and connection rather than sequence. This…
Projective Geometric Frameworks for Semantic Structures
Current critical literature often dismisses Large Language Models (LLMs) as statistical parrots operating via mere stochastic approximation, yet their capacity for cross-lingual zero-shot inference suggests the internalization of deep, invariant topological rules. This study establishes that…
The One Who Tells
A few days ago, I published an article about being tired of reading self-help books. Tired of the vague concepts—“ego,” “shadow,” “inner child”—that promised transformation and delivered jargon. Tired of running…
Care Is Stronger
Disagreement functions as an inevitable component of human relationships. Political ideology, moral values, and personal life choices frequently create divisions between individuals. This document examines the psychological processes that transform simple disagreement into relational rupture. It…
Agentic Collapse
Abstract The transition from static Large Language Models to dynamic Autonomous Agents has introduced a new class of epistemic failure modes driven by the “Orchestration Penalty”—the factorial increase in verification complexity inherent to multi-step reasoning loops. This research identifies a…
Resonant Equilibrium
This work presents a unified framework for intelligence, synthesizing concepts from artificial intelligence, mathematical logic, and theoretical physics. It begins by proposing the Fourier paradigm, which models Large Language Model (LLM) computation as a physical process of resonance and waveform…
New papers by email
One short weekly digest: titles and links. No tracking; unsubscribe any time.