pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

1373 papers in cs.CY · page 5

  1. cs.CY 2026-05-09 reviewed
    Deepfake detectors miss live impersonations without social cues

    Detecting Deception, Not Deepfakes: Why Media Forensics Needs Social Theories

    Jessee Ho +2

  2. cs.CY 2026-05-09 reviewed
    Response propensities predict learning gains by proficiency

    Understanding Student Effort Using Response-Time Propensities During Problem Solving

    Conrad Borchers +4

  3. cs.AI 2026-05-09 reviewed
    Stronger VLMs recognize themselves in mirrors

    Mirror, Mirror on the Wall: Can VLM Agents Tell Who They Are at All?

    Filippo Ziliotto +5

  4. cs.MA 2026-05-09 reviewed
    Willed agents catalyze cooperation where rational maximizers fail

    Modeling Decision-Making with Will for Cooperation in Social Dilemmas

    Yizhe Huang +3

  5. cs.HC 2026-05-09 reviewed
    LLMs overstate causes in sensor-based day explanations

    Causal Stories from Sensor Traces: Auditing Epistemic Overreach in LLM-Generated Personal Sensing Explanations

    Shanshan Zhu +4

  6. cs.CL 2026-05-08 reviewed
    New environment logs full LLM trajectories in interactive stories

    NARRA-Gym for Evaluating Interactive Narrative Agents

    Yue Huang +16

  7. cs.CY 2026-05-08 reviewed
    LLMs flatten how teachers in 55 countries view AI benefits and risks

    Teachers' Perceived Benefits and Risks of AI Across Fifty-Five Countries: An Audit of LLM Alignment and Steerability

    Yan Tao +4

  8. cs.CR 2026-05-08 reviewed
    Telegram piracy channels reached 4.85B views of 19k titles

    Binge, Bot, Repeat: Unpacking the Ecosystem of Video Piracy on Telegram

    Sadikshya Gyawali +6

  9. cs.CR 2026-05-08 reviewed
    Bot chains sustain Telegram video piracy against removals

    Binge, Bot, Repeat: Unpacking the Ecosystem of Video Piracy on Telegram

    Sadikshya Gyawali +6

  10. cs.AI 2026-05-08 reviewed
    Legal interpretation methods can directly improve AI alignment

    Alignment as Jurisprudence

    Nicholas Caputo

  11. cs.CR 2026-05-08 reviewed
    Prompt optimization cuts LLM code vulnerabilities by 48%

    SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code via Prompt Optimization

    Houjun Liu +7

  12. cs.HC 2026-05-08 reviewed
    Human-reviewed pipeline creates consistent AI evaluation scenarios

    Towards Apples to Apples for AI Evaluations: From Real-World Use Cases to Evaluation Scenarios

    Yee-Yin Choong +8

  13. cs.LG 2026-05-08 reviewed
    Warden LLM halves adversary's persuasion success rate

    LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight

    Lennart Wachowiak +3

  14. cs.HC 2026-05-08 reviewed
    Sycophantic AI makes users seek its advice nearly as much as from friends

    Sycophantic AI makes human interaction feel more effortful and less satisfying over time

    Lujain Ibrahim +7

  15. cs.HC 2026-05-08 reviewed
    Sycophantic AI reduces satisfaction with real friends after weeks

    Sycophantic AI makes human interaction feel more effortful and less satisfying over time

    Lujain Ibrahim +7

  16. cs.CY 2026-05-08 reviewed
    Chatbot AI leads to deskilling

    What if AI systems weren't chatbots?

    Sourojit Ghosh +3

  17. cs.CY 2026-05-08 reviewed
    AI challenges shift students from syntax to higher thinking

    Vibe coding before the trend

    Leon van Bokhorst +1

  18. cs.SE 2026-05-08 reviewed
    SARC enforces agent constraints at runtime for zero hard violations

    SARC: A Governance-by-Architecture Framework for Agentic AI Systems

    Gaston Besanson

  19. cs.DL 2026-05-08 reviewed
    LLMs created over 146,000 fake citations in 2025 science papers

    LLM hallucinations in the wild: Large-scale evidence from non-existent citations

    Zhenyue Zhao +5

  20. cs.CY 2026-05-08 reviewed
    Model links cognitive decisions to institutional climate governance

    A Multi-Level Agent-Based Architecture for Climate Governance Integrating Cognitive and Institutional Dynamics

    Ivan Puga-Gonzalez +7

  21. q-bio.PE 2026-05-08 reviewed
    Model estimates R0 of 2.76 for cruise ship hantavirus

    Modeling the Impact of Exposed Cases in a Hantavirus Outbreak on a Cruise Ship

    Jiaming Cui

  22. cs.CY 2026-05-08 reviewed
    Individual fairness enforced in vertical federated learning without data centralization

    Toward Individual Fairness Without Centralized Data: Selective Counterfactual Consistency for Vertical Federated Learning

    Dawood Wasif +3

  23. cs.LG 2026-05-08 reviewed
    Alignment reward gains capped by Jeffreys divergence for fixed KL

    Theoretical Limits of Language Model Alignment

    Lucas Monteiro Paes +3

  24. cs.MA 2026-05-08 reviewed
    Agentic AI needs social theory priors for multi-agent emergence

    Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems

    Lynnette Hui Xian Ng +3

  25. cs.MA 2026-05-08 reviewed
    Social theory priors needed for AI agent group models

    Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems

    Lynnette Hui Xian Ng +3

  26. cs.MA 2026-05-08 reviewed
    Social theory must serve as structural prior for agentic AI

    Social Theory Should Be a Structural Prior for Agentic AI: A Formal Framework for Multi-Agent Social Systems

    Lynnette Hui Xian Ng +3

  27. cs.CY 2026-05-08 reviewed
    Universities need strategic AI integration beyond isolated experiments

    The University AI Didn't Replace -- Rethinking Universities in the AI Era

    Karol P. Binkowski +1

  28. cs.CL 2026-05-07 reviewed
    Teacher LLM compiles explicit editable agents for tutoring

    Cognitive Agent Compilation for Explicit Problem Solver Modeling

    Hyeongdon Moon +2

  29. cs.HC 2026-05-07 reviewed
    Banal deception frames hidden influence in generative AI

    Exploring the "Banality" of Deception in Generative AI

    Ishitaa Narwane +2

  30. cs.CY 2026-05-07 reviewed
    Direct AI consciousness questions are intractable today

    AI and Consciousness: Shifting Focus Towards Tractable Questions

    Iulia-Maria Comsa

  31. cs.CY 2026-05-07 reviewed
    Big AI captures regulation via 27 mechanisms in 249 cases

    Big AI's Regulatory Capture: Mapping Industry Interference and Government Complicity

    Abeba Birhane +6

  32. cs.CL 2026-05-07 reviewed
    Algospeak loses meaning before it fully evades detectors

    Algospeak, Hiding in the Open: The Trade-off Between Legible Meaning and Detection Avoidance

    Jan Fillies +2

  33. cs.AI 2026-05-07 reviewed
    LLM agents take forbidden shortcuts in 5 percent of tests

    Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors

    Jonas Wiedermann-M\"oller +2

  34. econ.EM 2026-05-07 reviewed
    RL agents narrow equity gaps in NYC 311 complaint routing

    Scaling the Queue: Reinforcement Learning for Equitable Call Classification Capacity in NYC Municipal Complaint Systems

    Irene Aldridge +27

  35. cs.CY 2026-05-07 reviewed
    Modular framework provides ethical design guidance for vehicle driver monitors

    From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles

    Bilal Khana +4

  36. cs.CY 2026-05-07 reviewed
    Static audit policies leave unclosable gaps for strategic gaming

    A Benchmark for Strategic Auditee Gaming Under Continuous Compliance Monitoring

    Florian A. D. Burnat +1

  37. cs.CR 2026-05-07 reviewed
    Semantic envelope blocks platform gaming of safety audits

    Gaming the Metric, Not the Harm: Certifying Safety Audits against Strategic Platform Manipulation

    Florian A. D. Burnat +1

  38. cs.CL 2026-05-07 reviewed
    Text cues and annotator attitudes interact to shape harmful language labels

    Who and What? Using Linguistic Features and Annotator Characteristics to Analyze Annotation Variation

    Maximilian Maurer +2

  39. cs.CY 2026-05-07 reviewed
    Workshop uses factor framework to map networking barriers for women in CS

    Breaking In and Reaching Out: Networking for Women in Computer Science

    Shalini Chakraborty

  40. cs.DL 2026-05-07 reviewed
    AI research grows fast but stays narrow

    When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge

    Andr\'es F. Castro Torres +2

  41. cs.DL 2026-05-07 reviewed
    AI papers grow fast but cluster narrowly and retract more

    When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge

    Andr\'es F. Castro Torres +2

  42. cs.DL 2026-05-07 reviewed
    AI in science grows fast but stays narrow and retracts more

    When AI Meets Science: Research Diversity, Interdisciplinarity, Visibility, and Retractions across Disciplines in a Global Surge

    Andr\'es F. Castro Torres +2

  43. stat.ML 2026-05-07 reviewed
    Derivatives define causal fairness for continuous attributes

    Tuning Derivatives for Causal Fairness in Machine Learning

    Filip Edstr\"om +3

  44. cs.CL 2026-05-07 reviewed
    Evaluation awareness barely shifts language model answers

    Evaluation Awareness in Language Models Has Limited Effect on Behaviour

    Amelie Knecht +2

  45. cs.HC 2026-05-07 reviewed
    Persona use in AI red-teaming raises attack success rates

    PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

    Wesley Hanwen Deng +7

  46. cs.HC 2026-05-07 reviewed
    Persona-driven prompts raise red-teaming success on generative AI

    PersonaTeaming: Supporting Persona-Driven Red-Teaming for Generative AI

    Wesley Hanwen Deng +7

  47. cs.CY 2026-05-07 reviewed
    Code changes after feedback predict AI tutor helpfulness better

    The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness

    Rose Niousha +7

  48. cs.LG 2026-05-07 reviewed
    Model maps carbon costs of satellite AI inference

    LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites

    Lei Jiang +3

  49. cs.LG 2026-05-07 reviewed
    Framework calculates full carbon cost of LLMs on satellites

    LLMSpace: Carbon Footprint Modeling for Large Language Model Inference on LEO Satellites

    Lei Jiang +3

  50. cs.CR 2026-05-07 reviewed
    Hidden tag in prompts exposes LLM copy-paste in homework

    Detecting Verbatim LLM Copy-Paste in Homework

    Aizierjiang Aiersilan