Pith Number

pith:6QMA4A2C

pith:2026:6QMA4A2C2BQXRCR2YXE2VXO7DQ

not attested not anchored not stored refs resolved

Beyond Partner Diversity: An Influence-Based Team Steering Framework for Zero-Shot Human-Machine Teaming

Rohan Paleja, Wei Sheng

Influence-Based Team Steering lets AI discover and guide toward effective coordination patterns instead of relying only on varied simulated partners.

arxiv:2605.15400 v1 · 2026-05-14 · 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{6QMA4A2C2BQXRCR2YXE2VXO7DQ}

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

IBTS improves team performance against competing baselines across simulated partners, synthetic variations, and the first 30-subject Overcooked-AI human-machine teaming study with two humans and one machine.

C2weakest assumption

That influence shaping can reliably discover diverse high-performing coordination modes and steer trajectories toward them in a way that transfers from simulated to real human partners and from dyadic to three-agent settings.

C3one line summary

IBTS framework uses influence shaping to improve zero-shot human-machine teaming beyond partner diversity alone, with gains shown in Overcooked-AI simulations and a 30-subject human study.

References

55 extracted · 55 resolved · 3 Pith anchors

[1] An introduction to centralized training for decentralized execution in cooperative multi-agent reinforcement learning 2024

[2] Mind the gaps: How ai shortcomings and human concerns may disrupt team cognition in human-ai teams (hats) 2025

[3] Human–robot collaboration: a survey.Interna- tional Journal of Humanoid Robotics, 5(01):47–66, 2008 2008

[4] The complexity of decentralized control of markov decision processes.Mathematics of operations research, 27: 819–840, 2002 2002

[5] On the utility of learning about humans for human-ai coordination.Advances in Neural Information Processing Systems, 32, 2019 2019

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:56.704310Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

f4180e0342d061788a3ac5c9aadddf1c3612885c30e8588e0af8e120ba458393

Aliases

arxiv: 2605.15400 · arxiv_version: 2605.15400v1 · doi: 10.48550/arxiv.2605.15400 · pith_short_12: 6QMA4A2C2BQX · pith_short_16: 6QMA4A2C2BQXRCR2 · pith_short_8: 6QMA4A2C

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/6QMA4A2C2BQXRCR2YXE2VXO7DQ \
  | 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: f4180e0342d061788a3ac5c9aadddf1c3612885c30e8588e0af8e120ba458393

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "71fc51560056ff0bc9e53d07993447a1586bf7530e8aa72abdd88e5db303b4be",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-14T20:34:16Z",
    "title_canon_sha256": "b33c7ac81857c6d4560660c74dcc34f6fee6cafc0131ab1d3e465e159c467c5b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15400",
    "kind": "arxiv",
    "version": 1
  }
}