Pith Number

pith:C2V6SBN4

pith:2026:C2V6SBN4D7QJX2PKISNYIPMFUB

not attested not anchored not stored refs resolved

EMA: Efficient Model Adaptation for Learning-based Systems

Daiyang Yu, Fan Lai, Xinyu Chen, Yan Liang, Yaqi Qiao, Yihan Zhang

EMA lets learning-based systems adapt to changing environments by aligning new states to past ones and prioritizing useful data labels, cutting retraining costs.

arxiv:2605.13942 v1 · 2026-05-13 · cs.LG · cs.DC · cs.NI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{C2V6SBN4D7QJX2PKISNYIPMFUB}

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 paper presents EMA, the first model adaptation system supporting learning-based systems to adapt to evolving environments with minimal operational overhead... Evaluations on eight representative learning-based systems show that EMA reduces adaptation costs (e.g., GPU training time) by 14.9-42.4% while improving system performance (e.g., network throughput) by 6.9-31.3%.

C2weakest assumption

That state transformers can reliably map new environment inputs to similar prior states across heterogeneous system designs, and that the utility-based labeling prioritization balances training and labeling costs without missing critical decision data in dynamic settings.

C3one line summary

EMA cuts adaptation costs in learning-based systems by 14.9-42.4% and raises performance by 6.9-31.3% via state transformers for input alignment and prioritized high-utility data labeling.

References

43 extracted · 43 resolved · 1 Pith anchors

[1] Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang 2016

[2] Venkat Arun and Hari Balakrishnan. 2018. Copa: Practical Delay-Based Congestion Control for the Internet. InNSDI 2018

[3] Simon Eismann, Long Bui, Johannes Grohmann, Cristina Abad, Nikolas Herbst, and Samuel Kounev. 2021. Sizeless: Predicting the optimal size of serverless functions. InMiddleware. 248–259 2021

[4] Xianghong Fang, Haoli Bai, Ziyi Guo, Bin Shen, Steven Hoi, and Zenglin Xu. 2020. DART: Domain-adversarial residual-transfer net- works for unsupervised cross-domain image classification.Neural Network 2020

[5] Matthew Honnibal, Ines Montani, Sofie Van Lan- deghem, and Adriane Boyd 2022

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:13.842015Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

16abe905bc1fe09be9ea449b843d85a0798d2d33ce5967b4616b5d5aac416a25

Aliases

arxiv: 2605.13942 · arxiv_version: 2605.13942v1 · doi: 10.48550/arxiv.2605.13942 · pith_short_12: C2V6SBN4D7QJ · pith_short_16: C2V6SBN4D7QJX2PK · pith_short_8: C2V6SBN4

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/C2V6SBN4D7QJX2PKISNYIPMFUB \
  | 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: 16abe905bc1fe09be9ea449b843d85a0798d2d33ce5967b4616b5d5aac416a25

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "a34b6aee82b82a2e8f5d15ba78fe326e2492546d3303b859808f63946c929431",
    "cross_cats_sorted": [
      "cs.DC",
      "cs.NI"
    ],
    "license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-13T17:26:06Z",
    "title_canon_sha256": "adef9396e431aa90391eee16e688c6ae7887c435677c348861516d274c00d2b4"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.13942",
    "kind": "arxiv",
    "version": 1
  }
}