Pith Number

pith:W4TMZISD

pith:2026:W4TMZISDYX6ORWOXVNOFXJHHEP

not attested not anchored not stored refs resolved

GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment

Chen Min, Dzmitry Tsetserukou, Shuo Wang, Sifa Zheng, Xuefeng Zhang, Yixiao Zhou, Ziang Guo, Zufeng Zhang

A 3D Gaussian Splatting environment probes multiple candidate futures to supply dense rewards that refine end-to-end driving policies.

arxiv:2604.28111 v3 · 2026-04-30 · cs.RO

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{W4TMZISDYX6ORWOXVNOFXJHHEP}

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

Evaluated on the reconstructed nuScenes dataset, our method outperforms other simulation-based RL approaches in closed-loop experiments.

C2weakest assumption

The 3D Gaussian Splatting environment provides sufficiently accurate and differentiable simulation of future vehicle dynamics and interactions to produce useful dense shaping rewards that transfer to real-world policy improvement.

C3one line summary

GSDrive combines IL priors with RL feedback by probing multi-mode futures inside a 3D Gaussian Splatting simulator to supply dense rewards for closed-loop driving policy improvement on nuScenes.

References

31 extracted · 31 resolved · 6 Pith anchors

[1] End- to-end autonomous driving: Challenges and frontiers, 2024

[2] The era of end-to-end autonomy: Transitioning from rule-based driving to large driving models 2026

[3] Iterative label refinement matters more than preference optimization under weak supervision 2025

[4] End-to-end driving with online trajectory evaluation via bev world model, 2025

[5] arXiv preprint arXiv:2503.11650 (2025) 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:00:40.020230Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b726cca243c5fce8d9d7ab5c5ba4e723ef79f6f947300bfe7710be410e11f9aa

Aliases

arxiv: 2604.28111 · arxiv_version: 2604.28111v3 · doi: 10.48550/arxiv.2604.28111 · pith_short_12: W4TMZISDYX6O · pith_short_16: W4TMZISDYX6ORWOX · pith_short_8: W4TMZISD

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/W4TMZISDYX6ORWOXVNOFXJHHEP \
  | 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: b726cca243c5fce8d9d7ab5c5ba4e723ef79f6f947300bfe7710be410e11f9aa

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "17bd67d47ad2d196eae1dc38fc521caafe3df3643ca962a72a09347e804e71df",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2026-04-30T16:59:07Z",
    "title_canon_sha256": "5c67a6ebe7eabd6892c9172c34f806be3108bda550ebad88c37707cbfdc928c8"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2604.28111",
    "kind": "arxiv",
    "version": 3
  }
}