Pith Number

pith:326UJHUX

pith:2026:326UJHUXTCOWMVMZ5J4RPBYW76

not attested not anchored not stored refs pending

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation

Conglang Zhang, Qian Zhang, Qingjie Wang, Weiqiang Ren, Wei Yin, Xiaoyang Guo, Yifan Zhan, Yinqiang Zheng, Yu Li, Zhanpeng Ouyang, Zhen Dong, Zhengqing Chen, Zihao Yang

A self-corrective training procedure allows autoregressive driving models to generate minute-scale simulations without drift.

arxiv:2605.11596 v2 · 2026-05-12 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{326UJHUXTCOWMVMZ5J4RPBYW76}

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

HorizonDrive natively supports minute-scale AR rollout under bounded memory; on nuScenes, HorizonDrive reduces FID by 52% and FVD by 37%, and lowers ARE and DTW by 21% and 9% relative to the strongest long-horizon streaming baselines, while remaining competitive with single-pass driving video generators.

C2weakest assumption

That training with scheduled rollout recovery produces a teacher model that remains stable and provides reliable supervision across long autoregressive rollouts without introducing new biases or artifacts not present in ground truth.

C3one line summary

HorizonDrive enables stable long-horizon autoregressive driving simulation via anti-drifting teacher training with scheduled rollout recovery and teacher rollout distillation.

Receipt and verification

First computed	2026-05-25T02:01:23.461727Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

debd449e97989d665599ea79178716ff83b0d826824c2e57112d811701cb4792

Aliases

arxiv: 2605.11596 · arxiv_version: 2605.11596v2 · doi: 10.48550/arxiv.2605.11596 · pith_short_12: 326UJHUXTCOW · pith_short_16: 326UJHUXTCOWMVMZ · pith_short_8: 326UJHUX

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/326UJHUXTCOWMVMZ5J4RPBYW76 \
  | 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: debd449e97989d665599ea79178716ff83b0d826824c2e57112d811701cb4792

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "ead24f09913ab77de5cd3b54efde69c3eb4e2c382a1e340ade73762b9f3e0957",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-12T06:22:16Z",
    "title_canon_sha256": "c4ad949a14b568f8083f9ad34e5d650ead12d3c2594543e4b8f93f1640895ef5"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.11596",
    "kind": "arxiv",
    "version": 2
  }
}