Pith Number

pith:2JQYCD7N

pith:2026:2JQYCD7NVITUJLHM2CCQEZWXSW

not attested not anchored not stored refs resolved

ArcGate: Adaptive Arctangent Gated Activation

Alejandro C. Frery, Avik Bhattacharya, Biplab Banerjee, Siddhant Dnyanesh Gole, Subhasis Chaudhuri

ArcGate uses seven learnable parameters per layer to let networks adapt activation shape to data, improving accuracy on remote sensing classification especially under noise.

arxiv:2605.14518 v1 · 2026-05-14 · cs.CV · 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{2JQYCD7NVITUJLHM2CCQEZWXSW}

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

ArcGate consistently outperforms standard baselines, achieving a peak overall accuracy of 99.67% on PatternNet. Most notably, ArcGate exhibits superior structural resilience in noisy environments, maintaining a 26.65% performance lead over ReLU under moderate Gaussian noise (standard deviation 0.1).

C2weakest assumption

The seven learnable parameters per layer can be stably optimized during training without causing overfitting, instability, or excessive computational overhead, and that the observed performance gains are due to the adaptive shape rather than the increased parameter count.

C3one line summary

ArcGate is an adaptive activation with seven learnable parameters that outperforms ReLU and other fixed activations on remote sensing benchmarks, reaching 99.67% accuracy on PatternNet and showing strong noise resilience.

References

12 extracted · 12 resolved · 5 Pith anchors

[1] T. Mitchell,Machine Learning. McGraw Hill, 1997. [Online]. Available: /bib/mitchell/Mitchell1997/MachineLearning-TomMitchell.pdf 1997

[2] A more general electromagnetic inverse scattering method based on physics- informed neural network, 2023

[3] BiophyNet: A regression network for joint estimation of plant area index and wet biomass from SAR data, 2021

[4] Convolutional au- toencoder for Spectral–Spatial hyperspectral unmixing, 2021

[5] Meta-learning classi- fication network for few-shot polarimetric SAR images, 2025

Formal links

1 machine-checked theorem link

Receipt and verification

First computed	2026-05-17T23:39:06.100364Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a

Aliases

arxiv: 2605.14518 · arxiv_version: 2605.14518v1 · doi: 10.48550/arxiv.2605.14518 · pith_short_12: 2JQYCD7NVITU · pith_short_16: 2JQYCD7NVITUJLHM · pith_short_8: 2JQYCD7N

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/2JQYCD7NVITUJLHM2CCQEZWXSW \
  | 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: d261810fedaa2744acecd0850266d795a7d19a331a6e5b79c400e062ac1fbf6a

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "622bd21337b22f422840a2d46fe54ad3f41d87c5da4744953c1cd854d7824ff7",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T08:00:46Z",
    "title_canon_sha256": "6cab28e6644b8e08cf1af335e2b82401435cf5de5daef8d97ebd6aea2fb4a4cd"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14518",
    "kind": "arxiv",
    "version": 1
  }
}