Pith Number

pith:ZV7FHROV

pith:2025:ZV7FHROVIGLZ42Q2BSPDA74PRW

not attested not anchored not stored refs resolved

Prismatic World Model: Learning Compositional Dynamics for Planning in Hybrid Systems

Chengwei Yang, Mingwei Li, Xiaoyuan Zhang, Yaodong Yang, Zilong Zheng

A context-aware mixture of experts decomposes hybrid robot dynamics into distinct modes to reduce rollout drift.

arxiv:2512.08411 v2 · 2025-12-09 · cs.AI · 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{ZV7FHROVIGLZ42Q2BSPDA74PRW}

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

By modeling the mode transitions in system dynamics, PRISM-WM reduces rollout drift. Experiments on continuous control benchmarks, including high-dimensional humanoids and multi-task settings, demonstrate that PRISM-WM provides a high-fidelity substrate for trajectory optimization algorithms (e.g., TD-MPC).

C2weakest assumption

That an implicit gating mechanism can reliably identify distinct physical modes from context alone and that the latent orthogonalization objective will prevent mode collapse without explicit mode labels or additional regularization.

C3one line summary

PRISM-WM uses a context-aware MoE with latent orthogonalization to model hybrid dynamics and reduce rollout drift for model-based planning.

References

5 extracted · 5 resolved · 2 Pith anchors

[1] Soft Actor-Critic Algorithms and Applications 1912 · arXiv:1812.05905

[2] InAdvances in Neural Information Pro- cessing Systems, volume 28, 2944–2952 2023

[3] Probabilistic mixture-of-experts for efficient deep reinforcement learning 2019

[4] Hu- manoidbench: Simulated humanoid benchmark for whole-body locomotion and manipulation 2018

[5] ST-MoE: Designing Stable and Transferable Sparse Expert Models 2022 · arXiv:2202.08906

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-18T03:09:32.819407Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

cd7e53c5d541979e6a1a0c9e307f8f8d9fcef6599f12290b7823034a90d5405c

Aliases

arxiv: 2512.08411 · arxiv_version: 2512.08411v2 · doi: 10.48550/arxiv.2512.08411 · pith_short_12: ZV7FHROVIGLZ · pith_short_16: ZV7FHROVIGLZ42Q2 · pith_short_8: ZV7FHROV

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/ZV7FHROVIGLZ42Q2BSPDA74PRW \
  | 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: cd7e53c5d541979e6a1a0c9e307f8f8d9fcef6599f12290b7823034a90d5405c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "aad09edb7162d3d9d6b40df9c65ed20ae693136d53aa694ac2adff0c6805ac1b",
    "cross_cats_sorted": [
      "cs.RO"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-12-09T09:40:34Z",
    "title_canon_sha256": "71a3a12074de99e943f0c9c2a39afc268ef536170aa4ca267e7cb4b8b76781b2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2512.08411",
    "kind": "arxiv",
    "version": 2
  }
}