Pith Number

pith:IDAIXY2P

pith:2026:IDAIXY2P3HBLYFHQJNLZPRFUK5

not attested not anchored not stored refs resolved

Controlling Decision Drift in Multimodal Sentiment Analysis with Missing Modalities

Chenglizhao Chen, Guisheng Zhang, Mengke Song, Xiaomin Yu, Xinyu Liu, Yuchen Cao

A two-level reference alignment framework maintains stable sentiment predictions under missing modalities by anchoring both features and decisions to complete samples.

arxiv:2605.16889 v1 · 2026-05-16 · cs.CV

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{IDAIXY2P3HBLYFHQJNLZPRFUK5}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more

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

The framework maintains stable and reliable sentiment predictions under diverse missing-modality patterns, achieving state-of-the-art performance on CMU-MOSI and CMU-MOSEI with ACC of 86.28% and 85.88%, and F1 of 86.24% and 85.86% under full-modality input.

C2weakest assumption

That complete-modality samples provide sufficiently stable references to constrain representations and align different modality combinations into a shared sentiment space without introducing new distribution shifts.

C3one line summary

A two-level reference alignment framework uses complete-modality samples and prototype voting to reduce decision drift and improve robustness in multimodal sentiment analysis under missing modalities.

References

36 extracted · 36 resolved · 5 Pith anchors

[1] Gated Multimodal Units for Information Fusion 2017 · arXiv:1702.01992

[2] Openface: an open source facial behavior analysis toolkit 2016

[3] Multimodal ma- chine learning: A survey and taxonomy.IEEE TPAMI, 41(2):423–443, 2018

[4] Ucmib-pns: Balancing sufficiency and ne- cessity with probabilistic causality and cross-modal uncer- tainty in multimodal sentiment analysis.IEEE TAC, 2025

[5] Unbiased missing-modality mul- timodal learning 2025

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-20T00:03:28.537818Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

40c08be34fd9c2bc14f04b5797c4b457790b055695de415e10196d567cee5012

Aliases

arxiv: 2605.16889 · arxiv_version: 2605.16889v1 · doi: 10.48550/arxiv.2605.16889 · pith_short_12: IDAIXY2P3HBL · pith_short_16: IDAIXY2P3HBLYFHQ · pith_short_8: IDAIXY2P

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/IDAIXY2P3HBLYFHQJNLZPRFUK5 \
  | 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: 40c08be34fd9c2bc14f04b5797c4b457790b055695de415e10196d567cee5012

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "f8b58a6f628877e37c734900381d7d3d0fcfc4688b6e8314c5c2e43847add592",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-16T09:03:31Z",
    "title_canon_sha256": "e852d903a3cd969ef7979f5761b8b1bb2b12d14f0df5653012166d222a2499d2"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.16889",
    "kind": "arxiv",
    "version": 1
  }
}