Pith Number

pith:YMZEST75

pith:2026:YMZEST75XYRK4QDK6EJDPNEQ3A

not attested not anchored not stored refs resolved

Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation

Tao Jin, Yongbo He, Zirun Guo

Decoupling each modality adapter into stable and plastic parts, activated asymmetrically by feature redundancy, lets models adapt to new domains without negative transfer or forgetting.

arxiv:2603.00574 v2 · 2026-02-28 · cs.CV · 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{YMZEST75XYRK4QDK6EJDPNEQ3A}

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

This asymmetric design enables the model to adapt flexibly to new domains while preserving generalizable knowledge.

C2weakest assumption

The assumption that higher interdimensional redundancy reliably identifies the biased modality and that the decoupled stable/plastic split plus KL regularization will prevent negative transfer without introducing new failure modes.

C3one line summary

DASP decouples each modality adapter into stable and plastic parts and uses asymmetric updates—plastic for biased modalities, regularized stable for unbiased ones—to balance adaptation and knowledge preservation.

References

40 extracted · 40 resolved · 0 Pith anchors

[1] Multimodal machine learning: A survey and tax- onomy.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019 2019

[2] Vlmo: Unified vision-language pre-training with mixture-of-modality-experts 2022

[3] Vggsound: A large-scale audio-visual dataset 2020

[4] Test-time selective adaptation for uni-modal distribu- tion shift in multi-modal data 2025

[5] Domain generalization via model-agnostic learning of semantic features 2019

Receipt and verification

First computed	2026-05-17T23:38:59.819638Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

c332494ffdbe22ae406af11237b490d818f00ea4c3947df69728911c79d55920

Aliases

arxiv: 2603.00574 · arxiv_version: 2603.00574v2 · doi: 10.48550/arxiv.2603.00574 · pith_short_12: YMZEST75XYRK · pith_short_16: YMZEST75XYRK4QDK · pith_short_8: YMZEST75

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/YMZEST75XYRK4QDK6EJDPNEQ3A \
  | 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: c332494ffdbe22ae406af11237b490d818f00ea4c3947df69728911c79d55920

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "6c95445959cd4980cd9156efa2e663e433435707e7021556db0e9496b2f9c5d0",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-02-28T09:46:58Z",
    "title_canon_sha256": "74c3a6365b986b4853e9c1a94c1a46ff1c0b96393fdcce720c2f1c5a7bc90bb6"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2603.00574",
    "kind": "arxiv",
    "version": 2
  }
}