Pith Number

pith:V3ZJZ7OW

pith:2026:V3ZJZ7OWJFPG7DNYIMHOFOYKQQ

not attested not anchored not stored refs resolved

Predictive but Not Plannable: RC-aux for Latent World Models

Guang Li, Keisuke Maeda, Miki Haseyama, Takahiro Ogawa, Wenyuan Li

Latent world models need explicit reachability supervision to support planning beyond accurate short-term prediction.

arxiv:2605.07278 v1 · 2026-05-08 · cs.LG · cs.AI · 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{V3ZJZ7OWJFPG7DNYIMHOFOYKQQ}

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

These results suggest that planning with latent world models depends not only on predictive accuracy, but also on whether the learned representation encodes the temporal and geometric structure required by downstream search.

C2weakest assumption

That the added budget-conditioned reachability supervision and temporal hard negatives will produce a latent space whose geometry aligns with actual finite-horizon reachability in the evaluated goal-conditioned tasks, rather than merely fitting the auxiliary labels.

C3one line summary

RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.

References

48 extracted · 48 resolved · 17 Pith anchors

[1] Self-supervised learning from images with a joint- embedding predictive architecture 2023

[2] V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning 2025 · arXiv:2506.09985

[3] Tldr: Unsupervised goal-conditioned rl via temporal distance-aware representations 2024

[4] LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics 2025 · arXiv:2511.08544

[5] Revisiting Feature Prediction for Learning Visual Representations from Video 2024 · arXiv:2404.08471

Cited by

1 paper in Pith

Beyond Euclidean Proximity: Repairing Latent World Models with Horizon-Matched Trajectory Reachability Metrics

Receipt and verification

First computed	2026-05-18T15:04:06.698559Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aef29cfdd6495e6f8db8430ee2bb0a840947468a8155f4567b280fa5539abdbb

Aliases

arxiv: 2605.07278 · arxiv_version: 2605.07278v1 · doi: 10.48550/arxiv.2605.07278 · pith_short_12: V3ZJZ7OWJFPG · pith_short_16: V3ZJZ7OWJFPG7DNY · pith_short_8: V3ZJZ7OW

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/V3ZJZ7OWJFPG7DNYIMHOFOYKQQ \
  | 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: aef29cfdd6495e6f8db8430ee2bb0a840947468a8155f4567b280fa5539abdbb

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "87e5531c45b00beaff3e730db95d52b0062b1971b2cb88cafc80882412f6bf77",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-08T05:43:33Z",
    "title_canon_sha256": "b456c0e5f2ee74e24ab08a6dfc1366873cc18fc4a54b48b53cbd105661d6a85f"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.07278",
    "kind": "arxiv",
    "version": 1
  }
}