Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-03
Score updated: 2026-04-03
Score fresh until: 2026-05-03
References: 0
Source count: 0
Coverage: 33%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition | Route /signal-canvas/light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition",
    "query_text": "Summarize Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition",
  "normalized_query": "2604.01903",
  "route": "/signal-canvas/light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition",
  "paper_ref": "light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

PDF: https://arxiv.org/pdf/2604.01903v1

Source count: Pending verification

Coverage: 33%

Last proof check: 2026-04-03T20:50:40.576Z

Signal Canvas receipt window

Watch and verify: Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

/buildability/light-reskan-a-parameter-sharing-lightweight-kan-with-gram-polynomials-for-efficient-sar-image-recognition

Watchwatch

Subject: Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

Verdict

Watch

Verdict is Watch because viability or proof quality is intermediate and should be re-evaluated before execution.

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
Our model achieves 99.09%, 93.01%, and 97.26% accuracy on MSTAR, FUSAR-Ship, and SAR-ACD datasets, respectively.
Implicationpartial
Directly stated in abstract with specific numeric result
Verificationpartial
partial
Evidencepartial
Experiments on MSTAR resized to $1024 \times 1024$ show that compared to VGG16, our model reduces FLOPs by $82.90 \times$ and parameters by $163.78 \times$.
Implicationpartial
Directly stated in abstract with specific numeric comparison
Verificationpartial
partial
Evidencepartial
Experiments on MSTAR resized to $1024 \times 1024$ show that compared to VGG16, our model reduces FLOPs by $82.90 \times$ and parameters by $163.78 \times$.
Implicationpartial
Directly stated in abstract with specific numeric comparison
Verificationpartial
partial
Evidencepartial
Second, we use Gram Polynomials as activations, which are well-suited for SAR data to capture complex non-linear relationships.
Implicationpartial
Directly stated in abstract as a core method component
Verificationpartial
partial
Evidencepartial
Third, we employ a parameter-sharing strategy: each kernel shares parameters per channel, preserving unique features while reducing parameters and FLOPs.
Implicationpartial
Directly stated in abstract as a core method component
Verificationpartial
partial
Evidencepartial
First, Light-ResKAN modifies ResNet by replacing convolutions with KAN convolutions, enabling adaptive feature extraction for SAR images.
Implicationpartial
Directly stated in abstract as a core method component
Verificationpartial
partial
Evidencepartial
Our model achieves 99.09%, 93.01%, and 97.26% accuracy on MSTAR, FUSAR-Ship, and SAR-ACD datasets, respectively.
Implicationpartial
Directly stated in abstract with specific numeric result
Verificationpartial
partial
Evidencepartial
Our model achieves 99.09%, 93.01%, and 97.26% accuracy on MSTAR, FUSAR-Ship, and SAR-ACD datasets, respectively.
Implicationpartial
Directly stated in abstract with specific numeric result
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Light-ResKAN: A Parameter-Sharing Lightweight KAN with Gram Polynomials for Efficient SAR Image Recognition

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface