archive
Every paper Pith has read. Search by title, abstract, or pith.
1373 papers in cs.CY · page 4
-
Feature models cut error 22-33% on student effort forecasts
From Heuristics to Analytics: Forecasting Effort and Progress in Online Learning
-
AI forces new rules for how universities change teaching
A Framework for institutional change in the age of AI
-
LLM simulators fix answers regardless of feedback relevance
Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
-
Outcome-fair models still reason differently for similar applicants
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
-
Nobody knows the state of the art in geospatial foundation models
No One Knows the State of the Art in Geospatial Foundation Models
-
Multisector moves boost upward mobility for planning alumni
Career Mobility of Planning Alumni in the United States: Evidence from Professional Profile Data using Large Language Models
-
Simulator trains AI agents on utility demand response
Towards Affordable Energy: A Gymnasium Environment for Electric Utility Demand-Response Programs
-
LLM political discourse lacks real population variation in crises
The Algorithmic Caricature: Auditing LLM-Generated Political Discourse Across Crisis Events
-
Embedding geometry flags LLM rating disagreements
Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals
-
AI in exams makes judging solutions the new measure of learning
Reimagining Assessment in the Age of Generative AI: Lessons from Open-Book Exams with ChatGPT
-
Culturally responsive outreach builds AI knowledge in Black youth
Early AI Literacy in Culturally Responsive STEM Outreach for Black Youth
-
LLM arbitration cuts delays at signal-free intersections
LIDSA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management
-
LLM arbitration cuts intersection delays by 89 percent
LIDSA: Cognitive Arbitration for Signal-Free Autonomous Intersection Management
-
Budget split cuts gender skew in ads without excluding unknowns
Into the Unknown: Accounting for Missing Demographic Data when Mitigating Ad Delivery Skew
-
Same facts produce different conclusions when inference profiles differ
Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference
-
Adaptive weights add feature selection to FGW distances
Fused Gromov-Wasserstein Distance with Feature Selection
-
Poetic prompts create separate processing paths that evade LLM safety
Metaphor Is Not All Attention Needs
-
LLMs hide biases that flip mortgage decisions when reactivated
Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
-
GDPR access requests expose contracts of African content moderators
Auditing African Content Moderators' Working Conditions by Using the European General Data Protection Regulation (GDPR)
-
Polymarket shows single fill-side cluster for all addresses
Fill-Side Non-Retail Trading on Polymarket: An Empirical Study of Behavioral Tiers and Microstructure Signatures Under Quote-Attribution Constraints
-
The paper introduces the Evaluation Differential (ED) as a divergence in AI model…
The Evaluation Differential: When Frontier AI Models Recognise They Are Being Tested
-
Dataset documentation tools miss reflexivity themes
Evaluating Structured Documentation as a Tool for Reflexivity in Dataset Development
-
Strategic questions cut majority bias in AI outputs
When to Ask a Question: Understanding Communication Strategies in Generative AI Tools
-
Differentiated roles in human-AI tutoring lift growth 61%
Improving Hybrid Human-AI Tutoring by Differentiating Human Tutor Roles Based on Student Needs
-
Persona disagreement cuts LLM cultural misalignment by 10-24%
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
-
Persona disagreements align LLMs to cultures without training
Training-Free Cultural Alignment of Large Language Models via Persona Disagreement
-
Platforms let anyone measure mobile network security
Democratizing Measurement of Critical Mobile Infrastructure: Security and Privacy in an Increasingly Centralized Communication Ecosystem
-
AI framework unifies campus surveys with mental health detection
New AI-Driven Tools for Enhancing Campus Well-being: A Prevention and Intervention Approach
-
TikTok users struggle to keep unwanted videos out of their For You feed
When 'For You' Isn't For You: Measuring User Agency in TikTok's Algorithmic Feed
-
Pareto frontier of fair decisions is group threshold rules
Fairness vs Performance: Characterizing the Pareto Frontier of Algorithmic Decision Systems
-
LLMs generate harmful stereotypes that shift with prompt language
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
-
Every tested LLM produces harmful stereotypes in open-ended stories
StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs
-
LLM travel agents steer 3.5-7.7pp toward high commissions
TourMart: A Parametric Audit Instrument for Commission Steering in LLM Travel Agents
-
Blueprints could rebalance science's generation and verification costs
Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI
-
AI alignment needs positive goals for human flourishing
Positive Alignment: Artificial Intelligence for Human Flourishing
-
AI Alignment Must Promote Human Flourishing
Positive Alignment: Artificial Intelligence for Human Flourishing
-
LLMs under-allocate pensions by factor of three in budget tests
Social Policy of Large Language Models: How GPT, Claude, DeepSeek and Grok Allocate Social Budgets in Spain and Germany
-
100k-image dataset improves fine-grained visual privacy detection
VPD-100K: Towards Generalizable and Fine-grained Visual Privacy Protection
-
Dataset reveals four strategies for LLM ad success
NaiAD: Initiate Data-Driven Research for LLM Advertising
-
AI Agents May Game Conference Acceptance by Flooding Submissions
Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents
-
Humanity at 0.73 on cognitive Kardashev scale
The Cognitive Kardashev Scale: Quantifying the Material Envelope of Civilisational Computation
-
One invariance rule unifies all AI explanation fairness metrics
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
-
CS Students Rank Pay and Location Above Ethics in Job Searches
Cost-of-Ethics Crisis: Beliefs, Decisions, and Justifications in the Job Searches of Computer Science Students in Canada and the United States
-
Metaverse requires hybrid governance across law and code layers
The Metaverse Is Not a Place Apart: Law, Code, and the Recursive Governance of Digital Space (A Review Essay on Mark Findlay, Governing the Metaverse: Law, Order and Freedom in Digital Space (2025))
-
AI-powered materials discovery requires workflow-aligned AI literacy
Preparing Students for AI-Powered Materials Discovery: A Workflow-Aligned Framework for AI Literacy, Equity, and Scientific Judgment
-
Vote entropy spots safe LLM debates but misses where debate helps
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
-
LLMs hit 95-100% math accuracy but miss most human strategies
Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning
-
Semantic search finds more hidden Locke receptions than word matching
Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
-
Semantic search finds more implicit Locke references than keywords
Matching Meaning at Scale: Evaluating Semantic Search for 18th-Century Intellectual History through the Case of Locke
-
Framework spots smartphone scams early from partial app streams
ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage