Pith Number

pith:IHUKXL22

pith:2026:IHUKXL22WBXX72MJWTMJM2KWOF

not attested not anchored not stored refs pending

Reward-Decomposed Reinforcement Learning for Immersive Video Role-Playing

Bin Li, Bo Gao, Jingtong Wu, Jun Wang, Miao Wang, Xiaodong Gu, Yaduan Ruan, Yeheng Chen, Yijiang Li, Yuling Shi, Zengxin Han

EBM-RL decomposes rewards to ground video role-playing in visual scenes and character traits.

arxiv:2605.04733 v2 · 2026-05-06 · cs.AI

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IHUKXL22WBXX72MJWTMJM2KWOF}

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

Extensive experiments demonstrate that EBM-RL substantially outperforms text-only role-playing baselines and larger-scale vision-language models on our immersive role-playing benchmark, delivering simultaneous gains in visual-atmosphere consistency and character authenticity.

C2weakest assumption

The four rewards (CLIP scene-text alignment, perceptual-cognitive, answer accuracy, and dense format) are assumed to collectively promote human-like sensory grounding and immersive dialogue without introducing unintended biases or overfitting to the specific benchmark and reference responses.

C3one line summary

EBM-RL decomposes reinforcement learning into perception-think-answer stages with CLIP alignment, perceptual-cognitive, accuracy, and format rewards to improve immersive video role-playing over text baselines.

Receipt and verification

First computed	2026-06-05T00:13:46.808607Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

41e8abaf5ab06f7fe989b4d8966956716a7f3b309cec894778a08b786cf033f8

Aliases

arxiv: 2605.04733 · arxiv_version: 2605.04733v2 · doi: 10.48550/arxiv.2605.04733 · pith_short_12: IHUKXL22WBXX · pith_short_16: IHUKXL22WBXX72MJ · pith_short_8: IHUKXL22

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/IHUKXL22WBXX72MJWTMJM2KWOF \
  | 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: 41e8abaf5ab06f7fe989b4d8966956716a7f3b309cec894778a08b786cf033f8

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "df083be057eb2a3ad8e2c36288e446eda919a2f68b83a0928b9a3de9a7e7338e",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.AI",
    "submitted_at": "2026-05-06T10:32:23Z",
    "title_canon_sha256": "3c99ad273693806eb9b73a67741cf7b7a15317232f7f9fec50a9fa0d10d2a9fa"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.04733",
    "kind": "arxiv",
    "version": 2
  }
}