Pith Number

pith:QX4EMMWD

pith:2026:QX4EMMWD57QKEA3ZLJ5ACDRG3V

not attested not anchored not stored refs resolved

Collaborating in Multi-Armed Bandits with Strategic Agents

Idan Barnea, Ofir Schlisselberg, Yishay Mansour

CAOS mechanism sustains collaboration as a Nash equilibrium in strategic multi-agent bandits via information sharing rules.

arxiv:2605.13145 v1 · 2026-05-13 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{QX4EMMWD57QKEA3ZLJ5ACDRG3V}

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 CAOS, a mechanism that sustains collaboration as a Nash equilibrium while achieving strong regret guarantees.

C2weakest assumption

The setting assumes persistent agents that participate across multiple time periods and that the only incentives come from information sharing rules, with agents playing according to Nash equilibrium.

C3one line summary

CAOS sustains collaboration as a Nash equilibrium among persistent strategic agents in Bayesian multi-armed bandits via information sharing, with strong regret guarantees.

References

32 extracted · 32 resolved · 2 Pith anchors

[1] P. Auer, N. Cesa-Bianchi, Y. Freund, and R. E. Schapire. The nonstochastic multiarmed bandit problem.SIAM J. Comput., 2002 2002

[2] K. Banihashem, N. Collina, and A. Slivkins. Bandit social learning with exploration episodes,

[3] URLhttps://arxiv.org/abs/2602.05835

[4] Y. Bar-On and Y. Mansour. Individual regret in cooperative nonstochastic multi-armed bandits. Advances in Neural Information Processing Systems, 2019 2019

[5] The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration 2026 · arXiv:2602.01453

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:08:57.316635Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

85f84632c3efe0a203795a7a010e26dd66135c2a3229c6fafeedb305115d3b5f

Aliases

arxiv: 2605.13145 · arxiv_version: 2605.13145v1 · doi: 10.48550/arxiv.2605.13145 · pith_short_12: QX4EMMWD57QK · pith_short_16: QX4EMMWD57QKEA3Z · pith_short_8: QX4EMMWD

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/QX4EMMWD57QKEA3ZLJ5ACDRG3V \
  | 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: 85f84632c3efe0a203795a7a010e26dd66135c2a3229c6fafeedb305115d3b5f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "8a811d4a5c6cec83e31e2fec7dd496b58db5cf34240362f4e11fc1b85a28f0a2",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T08:10:36Z",
    "title_canon_sha256": "66aea708a1a3d2139e2f755160c248da0d44433ba44e897b2bdcc478d308a435"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13145",
    "kind": "arxiv",
    "version": 1
  }
}