Pith Number

pith:WESESZC7

pith:2023:WESESZC76S2IZRCQOCTFLFKWSQ

not attested not anchored not stored refs resolved

Any-point Trajectory Modeling for Policy Learning

Chuan Wen, John So, Kai Chen, Pieter Abbeel, Qi Dou, Xingyu Lin, Yang Gao

Pre-training a model to predict future trajectories of arbitrary points in videos supplies control guidance that lets robots learn policies from minimal action-labeled data.

arxiv:2401.00025 v3 · 2023-12-28 · cs.RO · 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{WESESZC76S2IZRCQOCTFLFKWSQ}

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

Across over 130 language-conditioned tasks we evaluated in both simulation and the real world, ATM outperforms strong video pre-training baselines by 80% on average.

C2weakest assumption

That predicted trajectories of arbitrary points supply sufficiently accurate and transferable control guidance to enable robust policy learning from only minimal action-labeled data.

C3one line summary

ATM pre-trains models to predict trajectories of any points in videos, then uses those predictions to learn strong visuomotor policies from minimal action labels, beating baselines by 80% on 130+ tasks.

References

56 extracted · 56 resolved · 6 Pith anchors

[1] Trajectory- tracking and path-following of underactuated au- tonomous vehicles with parametric modeling uncertainty 2007

[2] Affordances from human videos 417 as a versatile rep- resentation for robotics 2023

[3] Video pretraining (vpt): Learning to act by watching unlabeled online videos 2022

[4] Zero-shot robot manipu- lation from passive human videos 2023

[5] Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models 2023 · arXiv:2310.10639

Formal links

2 machine-checked theorem links

Cited by

32 papers in Pith

Point Tracking Improves World Action Models

Physically Interpretable World Models via Weakly Supervised Representation Learning

EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control

Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations

AwareVLN: Reasoning with Self-awareness for Vision-Language Navigation

Receipt and verification

First computed	2026-05-17T23:38:46.231720Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c

Aliases

arxiv: 2401.00025 · arxiv_version: 2401.00025v3 · doi: 10.48550/arxiv.2401.00025 · pith_short_12: WESESZC76S2I · pith_short_16: WESESZC76S2IZRCQ · pith_short_8: WESESZC7

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/WESESZC76S2IZRCQOCTFLFKWSQ \
  | 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: b12449645ff4b48cc45070a65595569429ecdd104e6a61100e3deadf960e4d7c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "207d057b618a3ca7c114531026d9aaa973945c29387380ab0067e268a7bfe3da",
    "cross_cats_sorted": [
      "cs.CV"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.RO",
    "submitted_at": "2023-12-28T23:34:43Z",
    "title_canon_sha256": "f0e6f867bde371defd2e2692b35013ad6027c83dc67b96b6714e4c89521c4b2d"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2401.00025",
    "kind": "arxiv",
    "version": 3
  }
}