Pith Number

pith:WV4JHJDG

pith:2026:WV4JHJDGDHCP4RJJFNGAJT53HW

not attested not anchored not stored refs resolved

EgoExo-WM: Unlocking Exo Video for Ego World Models

Danny Tran, Kristen Grauman, Roberto Mart\'in-Mart\'in

Converting exocentric videos into egocentric views via body pose extraction allows training of more capable action-conditioned world models.

arxiv:2605.15477 v1 · 2026-05-14 · 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{WV4JHJDGDHCP4RJJFNGAJT53HW}

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

training whole-body action-conditioned egocentric world models with our converted data significantly improves both prediction quality and downstream planning performance, where we infer the sequence of body poses needed to achieve a visual goal state.

C2weakest assumption

The exocentric-to-egocentric video transformation, informed by a human kinematics prior, produces training data whose action representation and visual statistics remain sufficiently faithful to real egocentric observations that downstream world-model training and planning gains are not artifacts of the conversion process.

C3one line summary

Converting exocentric video to egocentric format via body-pose extraction and kinematics prior enables training of action-conditioned egocentric world models that improve prediction quality and goal-directed planning.

References

84 extracted · 84 resolved · 12 Pith anchors

[1] GPT-4 Technical Report 2023 · arXiv:2303.08774

[2] Cosmos-transfer1: Conditional world generation with adaptive multimodal control 2025

[3] Fiction: 4d future interaction prediction from video 2025

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

[5] Safemimic: Towards safe and autonomous human-to-robot imitation for mobile manipulation 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:01:00.613441Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b57893a46619c4fe45292b4c04cfbb3d973179f5e76182f3d967260db12446c0

Aliases

arxiv: 2605.15477 · arxiv_version: 2605.15477v1 · doi: 10.48550/arxiv.2605.15477 · pith_short_12: WV4JHJDGDHCP · pith_short_16: WV4JHJDGDHCP4RJJ · pith_short_8: WV4JHJDG

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/WV4JHJDGDHCP4RJJFNGAJT53HW \
  | 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: b57893a46619c4fe45292b4c04cfbb3d973179f5e76182f3d967260db12446c0

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "4b369f3408f675104d157b77023414f44239dac8b2b2a6ae6d5950575340b8be",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T23:35:54Z",
    "title_canon_sha256": "899deb79d3bf1d6a3350d96bfca6c87dca3762fe822fec8e7705abb7135b011d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.15477",
    "kind": "arxiv",
    "version": 1
  }
}