Paper Library

Add Paper
Showing 9 papers.

Revisiting the Stanford Prison Experiment: A Case Study in Organized Skepticism

Authors: Teresa C. Kulig, Travis C. Pratt and Francis T. Cullen

Source: Upload Revisiting_the_Stanford_Prison_Experiment_A_Case_Study_in_Organized_Skepticism.pdf

Actionable Steps Encourage greater use of organized skepticism and critical analysis in criminology and criminal justice scholarship. Prioritize replication studies of classic experiments, especially those considered foundational, like the ...

Details View Paper
2026-03-30

Evaluating the Criticisms of the Stanford Prison Experiment

Authors: Psychology Review

Source: Upload Evaluating-the-Criticisms-of-the-Stanford-Prison-Experiment.pdf

Actionable Steps Separate the roles of prison superintendent from principal researcher in simulated environment studies to reduce bias. Assign day-to-day oversight of participant wellbeing to an independent safeguarding panel during simulat...

Details View Paper
2026-03-30

Constrained Control of Depth of Hypnosis During Induction Phase

Authors: Mehdi Hosseinzadeh, Guy A. Dumont, Emanuele Garone

Source: arXiv 1812.01432

Actionable Steps Reformulate anesthesia induction phase control as a constrained control problem. Employ Explicit Reference Governor (ERG) as an active set-point prefilter to guarantee constraint satisfaction (prevent overdosing). Use a rob...

Details View Paper
2026-03-27

Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models

Authors: Yongjiang Liu, Haoxi Li, Xiaosong Ma, Jie Zhang, Song Guo

Source: arXiv 2507.02663

Key Findings Overthinking in LRMs: Large Reasoning Models (LRMs) tend to "overthink," frequently producing needlessly long and redundant reasoning chains, especially failing to calibrate their depth of reasoning to match task difficulty. Co...

Details View Paper
2026-03-09

LLM Hypno v2

Authors: Almog Hilel

Source: Upload 2507.02850v2.pdf

Key Findings A vulnerability exists in LLMs trained with user feedback: a single user can inject persistent, unauthorized knowledge or behaviors into the model solely by selecting prompts and upvoting/downvoting outputs. The LLM can be mani...

Details View Paper
2026-03-09

Beyond Anatomy: Explainable ASD Classification from rs-fMRI via Functional Parcellation and Graph Attention Networks

Authors: Syeda Hareem Madani, Noureen Bibi, Adam Rafiq Jeraj, Sumra Khan, Anas Zafar, Rizwan Qureshi

Source: arXiv 2603.02518

Key Findings Functional parcellation (MSDL atlas) in resting-state fMRI (rs-fMRI) data provides a 10.7% accuracy gain (from 73.3% to 84.0%) for Autism Spectrum Disorder (ASD) classification compared to traditional anatomical (AAL) atlases, ...

Details View Paper
2026-03-06

Neuro-Symbolic Decoding of Neural Activity

Authors: Yanchen Wang, Joy Hsu, Ehsan Adeli, Jiajun Wu

Source: arXiv 2603.03343

Here’s a practitioner-focused summary and takeaways for the paper “Neuro-Symbolic Decoding of Neural Activity” (Wang et al., ICLR 2026), based on a thorough reading of the entire document. -- Key Findings Neuro-symbolic decoding with struct...

Details View Paper
2026-03-06

A systematic approach to answering the easy problems of consciousness based on an executable cognitive system

Authors: Qi Zhang

Source: arXiv 2603.04440

Consciousness encompasses fundamental cognitive properties termed the "easy problems," including discrimination, categorization, reaction to stimuli, information integration, reportability, information access, attention, deliberate control,...

Details View Paper
2026-03-06

Automatic Minds: Cognitive Parallels Between Hypnotic States and Large Language Model Processing

Authors: Giuseppe Riva, Brenda K. Wiederhold, Fabrizia Mantovani

Source: arXiv 2511.01363

OpenAI summary failed: { "error": { "message": "You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors."...

Details View Paper
2026-03-06