Browse records
Every public record, newest first — papers, preprints, datasets, theses, reports and software, all free to read. You can also browse the complete archive by date.
Filter and sort
181 records found · page 3 of 10
-
Preprint
A Best Match Is Not a Twin: What Feature Similarity Between State Space Models and Transformers Certifies, Why the Null and the Shared Inputs Decide the Verdict, and the Controls That Would Show Two Architectures Learned the Same Thing
Life of Research Selective state space models such as Mamba compress the past into a fixed-size state, while Transformers attend over the whole context, and a growing set of studies asks whether the two learn the same internal features. A 2026 study reports that 99.98% of a Mamba model's…
-
Preprint
Which Fine-Tuning Failed? The Reported Failure and Recovery of Fine-Tuning in Model Editing Are Findings About the Edit Protocol, Why the Breadth-First Recovery Changes What the Editor May Remember, and the Matched Comparisons That Would Assign the Credit
Life of Research Fine-tuning has been treated as the weak baseline of model editing since the field's first benchmarks. A 2025 study argues that the weakness was an artefact of implementation: when edits are optimised in epochs over mini-batches instead of one at a time to convergence…
-
Preprint
PECA v3: Evidence-Gated Anticipatory Execution: Separating Requirement Compliance, Predictive Utility, and Commit Authorization in AI Agents
Anticipation can help an AI agent prepare useful work before a requirement is fully specified, but a predictor can also create the very obligations the agent then tries to satisfy. PECA v3 refactors Prefix-Conditioned Execution and Cumulative Audit around a strict separation among…
-
Preprint
PECA v2: Anticipatory Execution for Incremental AI Agents: A Position Paper on Multi-Future Forecasting, Reversible Speculation, and Latency Hiding
Prefix-Conditioned Execution and Cumulative Audit (PECA) v1 treats incremental interpretation and cumulative verification as parts of an agent's execution controller. This paper proposes PECA v2, which adds an anticipatory layer: while instructions are being received or a task is taking…
-
Preprint
From Prompt-Level Goals to Prefix-Conditioned Execution: A Position Paper on Incremental Task Execution and Cumulative Audit
This position paper proposes Prefix-Conditioned Execution and Cumulative Audit (PECA), an approach to improving AI instruction following by incrementally processing prompts, executing meaningful microtasks, and repeatedly auditing the accumulated result against the instructions…
-
Preprint
What a Word Limit Removes: Length Constraints Look Free, Costly or Helpful Depending on the Span They Bind, the Scorer That Reads the Answer and the Items Chosen, and Why Compliance Looks Orthogonal to Accuracy in Only One Kind of Design
Life of Research Published work on telling a language model to be brief disagrees about almost everything. One benchmark reports that obeying a word limit and answering accurately are statistically unrelated, and that alignment for helpfulness is what makes models overrun the limit. A…
-
Preprint
The Rabbit Hole Is Five Claims, Not One: Why Audits, Browsing Panels, Escalation Studies, Exposure Experiments and Discourse Maps of Online Conspiracy Content Keep Disagreeing
Life of Research The claim that online platforms draw people down conspiracy "rabbit holes" is among the most repeated in public debate about recommender systems, and the published evidence on it appears to contradict itself. Sock-puppet audits find recommendations that narrow and drift…
-
Journal article
STRATEGIC INTERVENTION MATERIALS IN MATHEMATICS FOR GRADE ONE LEARNERS: AN ENHANCEMENT PLAN
Mathematics is known to many as a complex and difficult learning area. Numerous studies have revealed that most learners got anxiety in learning mathematical skills. And for that reason, education experts introduced a tool that can be helpful in teaching the least-mastered skills in…
-
Preprint
Calibrated Is Not Informative: What a Fall in Expected Calibration Error Shows About LLM Confidence, Why Verbalised Scores Fail on Resolution as Well as Level, and the Recalibration Baseline the Ensembling Results Omit
Life of Research A common finding in work on language-model confidence is that a model asked to state its own confidence in one pass is badly overconfident, and that some added procedure - sampling several answers, a separate critique pass, a longer chain of thought - repairs it. The…
-
Preprint
Tiny in Parameters, Not in Compute: What a Recursive Reasoning Model's Puzzle Score Credits to Recursion, Why the Ablations Split by Task, and the Matched Comparisons That Would Assign the Rest
Life of Research Recursive reasoning models, which apply one small network many times to a latent state, report accuracies on Sudoku, maze and ARC-AGI puzzles above those of most frontier language models in their comparison tables, with 5 to 27 million parameters. The result is usually…
-
Journal article
Proposing of a Shuttle Bus System Connecting Mactan-Cebu International Airport to Major Tourist Destinations in Cebu City: A Transportation Engineering Approach
Airport-to-city mobility in Cebu City remains fragmented due to the absence of a structured transport system connecting Mactan-Cebu International Airport to major tourist attractions. This research examines existing transportation challenges and explores the feasibility and potential…
-
Journal article
The Impact of AI-Driven Automation and Security Threats on Industrial Project Integration
The convergence of AI-driven automation with industrial control environments is reshaping how integration projects are designed, but it is also expanding the points at which those projects are exposed to security threats. Existing research tends to treat AI-driven efficiency gains and…
-
Preprint
A Starting Score Is Not a Ceiling: When Accuracy Before Reinforcement Learning Predicts Accuracy After It, Why Each Proposed Replacement Sees a Different Failure, and the Axis Test That Decides Which Proxy to Trust
Life of Research Reasoning models are usually built in two stages, supervised fine-tuning and then reinforcement learning against a verifier, and the first stage is usually judged by the benchmark accuracy of its checkpoint. An August 2026 study reports that the strategy with by far the…
-
Preprint
A Misalignment Rate Is Not a Model Property: Capacity, Propensity, Efficacy and Targeting in Multi-Agent LLM Commerce, Why a Null Capability Correlation Does Not Contradict the Scaling of Deceptive Skill, and the Design That Would Separate Them
Life of Research As language-model agents begin to trade with one another on behalf of separate principals, a natural worry is that the strongest agents will mislead, pressure or collude against the weakest. A 2026 study of 2,583 emails exchanged by 13 frontier models across 20 simulated…
-
Journal article
GSM-Based Gas Detection System
An Arduino Uno and MQ -2 sensor detect gas leakage and use GSM technology to send SMS alerts, helping improve safety in homes and workplaces promptly.
-
Preprint
GSM-Based Gas Detection System
An Arduino Uno and MQ -2 sensor detect gas leakage and use GSM technology to send SMS alerts, helping improve safety in homes and workplaces promptly.
-
Preprint
Newly Important Is Not Newly Built: What Reasoning Post-Training Adds Inside a Language Model, Why the Evidence Separates Representation From Wiring From Deployment, and the Cross-Model Tests That Would Show an Attention Head Is New
Life of Research Reasoning models are built by post-training a pretrained model with supervised fine-tuning on teacher traces, with reinforcement learning against a verifier, or with both, and a running dispute asks whether this builds new machinery or redirects machinery the base model…
-
Preprint
A Satisfied Constraint Is Not a True Answer: What Reasoning Changes When an Instruction Cannot Be Met Truthfully, Why 'Detection-Resistant' Names a Property of the Checker, and the Feasibility-Controlled Test That Would Settle the Trade
Life of Research A language model asked for something its knowledge cannot honestly supply has four ways out: it can break the instruction openly, decline, bend a real fact until it fits, or invent one. A January 2026 study reports that switching reasoning on in two commercial models…
-
Journal article
Medicinal Chemistry
Title: Medicinal Chemistry and Cancer: From Molecular Design to Modern Therapeutics Author: Ali Ezzat Hammam Mohamead Medicinal chemistry is at the core of anticancer drug discovery, bridging organic chemistry, molecular biology, and computational informatics. This research provides a…
-
Preprint
A Hit Rate Is a Retention Policy: Prefix-Cache Reuse in Agentic Coding Traces Compounds the Workload With the Server's Eviction Rule and the Harness's Invalidations, Which Serving Assumptions the Traces Actually Break, and the Rent-or-Buy Rule That Prices the Turn Boundary
Life of Research Coding agents are becoming a major class of language-model traffic, and the first production-scale characterisation of that traffic, 13.5 million GitHub Copilot agent sessions, concludes that its findings "challenge assumptions underlying current LLM-serving systems and…