Pith Number

pith:FPJIHIJK

pith:2026:FPJIHIJKYXM2T7FECBVCEI2NXG

not attested not anchored not stored refs resolved

Ranking-Aware Calibration for Reliable Multimodal Reinforcement Learning

Boyao Yang, Jun Zhu, Peng Cui

Ranking signals from group-based RL can supervise confidence to improve calibration in vision-language models.

arxiv:2605.16999 v1 · 2026-05-16 · cs.LG

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{FPJIHIJKYXM2T7FECBVCEI2NXG}

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

Their combination achieves the best calibration across all tested backbones while improving accuracy in the majority of settings.

C2weakest assumption

That the ranking signals already produced by group-based RL directly reflect reasoning quality and can be used to supervise confidence without introducing new biases or requiring validation against external correctness measures.

C3one line summary

RAC adds ranking-aware group loss and clean-corrupted pairwise loss to RL post-training to boost both accuracy and calibration in multimodal reasoning without extra annotations.

References

52 extracted · 52 resolved · 0 Pith anchors

[1] Learning transferable visual models from natural language supervision 2021

[2] Flamingo: a visual language model for few-shot learning 2022

[3] Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models 2023

[4] Visual instruction tuning 2023

[5] Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond 2023

Receipt and verification

First computed	2026-05-20T00:03:35.254348Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

2bd283a12ac5d9a9fca4106a22234db98cfdb9f2c082b0574f71a469333f5381

Aliases

arxiv: 2605.16999 · arxiv_version: 2605.16999v1 · doi: 10.48550/arxiv.2605.16999 · pith_short_12: FPJIHIJKYXM2 · pith_short_16: FPJIHIJKYXM2T7FE · pith_short_8: FPJIHIJK

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/FPJIHIJKYXM2T7FECBVCEI2NXG \
  | 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: 2bd283a12ac5d9a9fca4106a22234db98cfdb9f2c082b0574f71a469333f5381

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "eb0e4e4bdacd9da5a7a856c499f1db0b6bd86661fdeef57d58e75cf673cff972",
    "cross_cats_sorted": [],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-16T13:51:29Z",
    "title_canon_sha256": "b2feb1e35fc4fa7b0e1e2be760927bb4c072e5a54fd9b4284f5a4543a178af59"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16999",
    "kind": "arxiv",
    "version": 1
  }
}