pith. sign in
Pith Number

pith:B52XMRC2

pith:2026:B52XMRC2IMI2K2OL32EPWQ3R65
not attested not anchored not stored refs pending

General-purpose LLMs as Models of Human Driver Behavior: The Case of Simplified Merging

Arkady Zgonnikov, Samir H.A. Mohammad, Wouter Mooi

General-purpose LLMs can serve as standalone models of human merging behavior in simplified scenarios.

arxiv:2604.09609 v2 · 2026-03-11 · cs.AI · cs.RO

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{B52XMRC2IMI2K2OL32EPWQ3R65}

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

general-purpose LLMs could potentially serve as standalone, ready-to-use human behavior models in AV evaluation pipelines

C2weakest assumption

The simplified one-dimensional merging scenario is sufficient to evaluate whether LLMs capture core aspects of human driver behavior for valid comparison to real data.

C3one line summary

General-purpose LLMs reproduce some human-like merging behaviors such as spatial cue responses but fail to consistently handle dynamic velocity cues and show divergent safety performance across models.

Receipt and verification
First computed 2026-05-20T00:04:31.252046Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0f7576445a4311a569cbde88fb4371f760594e559cb72f6cf56b75d8f72235f1

Aliases

arxiv: 2604.09609 · arxiv_version: 2604.09609v2 · doi: 10.48550/arxiv.2604.09609 · pith_short_12: B52XMRC2IMI2 · pith_short_16: B52XMRC2IMI2K2OL · pith_short_8: B52XMRC2
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/B52XMRC2IMI2K2OL32EPWQ3R65 \
  | 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: 0f7576445a4311a569cbde88fb4371f760594e559cb72f6cf56b75d8f72235f1
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "ccf46d90c795c501d9a8663ea59fd8c9ac3ba209d19a51e72573bd446663ed5b",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-03-11T16:24:32Z",
    "title_canon_sha256": "366532b760a0820e2186532680003c232966fcf141d0a2c6817cb3be39859285"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.09609",
    "kind": "arxiv",
    "version": 2
  }
}