pith. sign in
Pith Number

pith:DS6RY4OG

pith:2026:DS6RY4OGKW7UNDDE2PZC72EHUY
not attested not anchored not stored refs pending

SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning

James Zachary Hare, Jesse Milzman, Nikunj Gupta, Rajgopal Kannan, Viktor Prasanna

Graph transformer convolutions on coordination graphs integrate receiver-sensitive teammate signals to overcome partial observation bottlenecks in cooperative multi-agent reinforcement learning.

arxiv:2605.08391 v2 · 2026-05-08 · cs.LG

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{DS6RY4OGKW7UNDDE2PZC72EHUY}

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

SACHI consistently matches or outperforms the best baseline on every task, and rigorous aggregate statistical analyses, including normalized metrics with bootstrap confidence intervals, Friedman ranking, and performance profiling, confirm that this advantage is statistically significant, robust across environments, and not attributable to increased model capacity.

C2weakest assumption

That a coordination graph can be defined such that graph transformer convolutions reliably extract and deliver the precise receiver-sensitive, content-dependent signals needed to overcome the partial-observation information bottleneck without introducing new scalability or training instabilities.

C3one line summary

SACHI uses graph transformer convolutions on inter-agent coordination graphs to enrich partial-observation agents with content-dependent teammate information, yielding statistically significant gains over baselines in five cooperative tasks.

Receipt and verification
First computed 2026-05-20T01:05:16.004300Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

1cbd1c71c655bf468c64d3f22fe887a62f3ba9b37c2ca694bd185637fe0fe0b7

Aliases

arxiv: 2605.08391 · arxiv_version: 2605.08391v2 · doi: 10.48550/arxiv.2605.08391 · pith_short_12: DS6RY4OGKW7U · pith_short_16: DS6RY4OGKW7UNDDE · pith_short_8: DS6RY4OG
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/DS6RY4OGKW7UNDDE2PZC72EHUY \
  | 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: 1cbd1c71c655bf468c64d3f22fe887a62f3ba9b37c2ca694bd185637fe0fe0b7
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "88825b46e5784bc90f35d150c0249edf9b885e8b05c0aba6b9d714410735662e",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-08T19:00:34Z",
    "title_canon_sha256": "43146b64f5f98a2b8feba99c2f7ea1e0aef7c81604b1ed9da40a9907e38b75c7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.08391",
    "kind": "arxiv",
    "version": 2
  }
}