Pith Number

pith:ZIFM76DF

pith:2026:ZIFM76DFXLXTDHOYAZG4X3VJ3F

not attested not anchored not stored refs resolved

Learning with Conflicts of Interest

Ali Vakilian, Arash Termehchy, Marianne Winslett, Nischal Aryal

A game-theoretic framework enables users to extract useful information from ML systems while shielding themselves from biased and manipulative outputs even when system owners have conflicting goals.

arxiv:2605.15504 v1 · 2026-05-15 · cs.LG · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{ZIFM76DFXLXTDHOYAZG4X3VJ3F}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp

2 Internet Archive

3 Author claim open · sign in to claim

4 Citations open

5 Replications open

✓ Portable graph bundle live · download bundle · merged state

The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We propose a game-theoretic framework that models the interaction between ML systems and users with conflicts of interest. We present scalable algorithms with theoretical guarantees that maximize the amount of desired information and actions and minimize the amount of biased and manipulative actions in interaction with ML systems.

C2weakest assumption

That real-world conflicts of interest between ML owners and users can be accurately captured by a game-theoretic model and that scalable algorithms with theoretical guarantees can be developed to protect users without needing cooperation from the ML system owners.

C3one line summary

A game-theoretic framework and algorithms are introduced to maximize beneficial information from ML systems while minimizing biased influences arising from conflicts of interest.

References

33 extracted · 33 resolved · 2 Pith anchors

[1] Information discrepancy in strategic learning 2022

[2] UCI Machine Learning Repository (1996) 1996 · doi:10.24432/c5xw20

[3] Poisoning attacks against support vector machines 2012

[4] Persuade me if you can: A framework for evaluating persuasion effectiveness and susceptibility among large language models, 2025 2025

[5] Bayesian strategic classification 2024

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:02.074320Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ca0acff865baef319dd8064dcbeea9d9605e7728ddd277693201ed5b19e381bd

Aliases

arxiv: 2605.15504 · arxiv_version: 2605.15504v1 · doi: 10.48550/arxiv.2605.15504 · pith_short_12: ZIFM76DFXLXT · pith_short_16: ZIFM76DFXLXTDHOY · pith_short_8: ZIFM76DF

Agent API

Resolver JSON Graph JSON Events JSON Schema Signing key

Verify this Pith Number yourself

curl -sH 'Accept: application/ld+json' https://pith.science/pith/ZIFM76DFXLXTDHOYAZG4X3VJ3F \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: ca0acff865baef319dd8064dcbeea9d9605e7728ddd277693201ed5b19e381bd

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "e7ea75fd89b10444d2635ec8ae08ee598bfb7dc103cb52acbd3b4b12aef0dbff",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-15T00:52:46Z",
    "title_canon_sha256": "c6687e5a7c3c28a1c336a51895f205900398dcb1dd3eb8c9b1b08fccebd51066"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15504",
    "kind": "arxiv",
    "version": 1
  }
}