Pith Number

pith:QV3YXPL6

pith:2025:QV3YXPL67TCNOQA2XFIYFLX6AY

not attested not anchored not stored refs pending

TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance

Chuan Wen, Dinesh Jayaraman, Yang Gao, Yihang Hu, Yuyang Liu

Modeling temporal distances between frames in passive videos yields step-wise proxy rewards that let reinforcement learning succeed on most Meta-World tasks with far fewer interactions than sparse or hand-designed rewards.

arxiv:2509.26627 v3 · 2025-09-30 · cs.AI · cs.LG · 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{QV3YXPL67TCNOQA2XFIYFLX6AY}

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

TimeRewarder supplies step-wise proxy rewards from passive videos that enable nearly perfect success in 9/10 Meta-World tasks with only 200,000 interactions per task, outperforming both prior methods and manually designed environment dense rewards.

C2weakest assumption

That modeling temporal distances between frame pairs in passive videos (robot demos or human videos) produces a reliable proxy for task progress that generalizes to guide RL without additional supervision or task-specific tuning.

C3one line summary

TimeRewarder derives progress-based dense rewards from passive videos via frame-wise temporal distance modeling and uses them as proxy rewards to boost RL success on Meta-World tasks.

Receipt and verification

First computed	2026-05-21T01:05:10.196001Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

85778bbd7efcc4d7401ab95182aefe0622e68648cdd0f433b253135bd5c3f71e

Aliases

arxiv: 2509.26627 · arxiv_version: 2509.26627v3 · doi: 10.48550/arxiv.2509.26627 · pith_short_12: QV3YXPL67TCN · pith_short_16: QV3YXPL67TCNOQA2 · pith_short_8: QV3YXPL6

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/QV3YXPL67TCNOQA2XFIYFLX6AY \
  | 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: 85778bbd7efcc4d7401ab95182aefe0622e68648cdd0f433b253135bd5c3f71e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "c9d9a9c42031db5545492f30d1bbabce9fbeadbaf91422eb03a1d09b6662a63d",
    "cross_cats_sorted": [
      "cs.LG",
      "cs.RO"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2025-09-30T17:58:20Z",
    "title_canon_sha256": "205e080e3732218b51c38aefd0c15dc79ff876deab59b3e83ec591ba644593e2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2509.26627",
    "kind": "arxiv",
    "version": 3
  }
}