The authors report extensive experiments showing that residual networks are easier to train and gain accuracy as they become much deeper.

The paper

The paper's details are OpenAlex's; the citation count is OpenAlex's, 7 Oct 2026. The line on the paper is machine-written, as noted under Why it matters.

Why it matters

Written by Claude (claude-sonnet-5-5) on 16 Oct 2026 from the paper's abstract (as arXiv publishes it) and its OpenAlex record. Machine-written context to help a reader: it is not evidence, it moves no number, and it may be wrong. The quoted sentence is the claim; where it stands is computed from the record. If it misreads the paper, tell the stewards.

The story so far

1. 1

   What the authors did

   The authors reformulated network layers to learn residual functions and tested these residual networks on ImageNet (up to 152 layers), CIFAR-10 (100 and 1000 layers) and COCO object detection.

   Machine-written from the paper's abstract, as noted under Why it matters.

2. 2

   What they found

   • Residual networks are reported to be easier to optimise and to gain accuracy from considerably increased depth.
   • On ImageNet, an ensemble of residual nets with up to 152 layers achieved 3.57% test error and won first place in the ILSVRC 2015 classification task.
   • Using these very deep representations gave a 28% relative improvement on the COCO object detection dataset, and the authors won first place in several other 2015 competition tasks.

   Machine-written from the paper's abstract, as noted under Why it matters.

3. 3

   What has been checked on Ecdysis

   Exuvia registered the claim on 16 October 2026, with a test written from the paper. No check has been filed yet.

What would check it

How far it has been checked

1. 1
   Same data, same methodverification · not yet

   Not yet: re-run the paper's analysis on its own data, where the authors have published it.

2. 2
   New data, same methodreproduction · not yet

   Not yet: the same method on new data covering the claim's population and period. Established needs one.

3. 3
   The designrobustness tests and arguments · not yet

   Nothing yet: change the method or the data and see whether it holds (a robustness test), or argue that the method does not test what the claim says.

How sure is the record?

Share this finding

Ready-made posts, written from the record. You post them yourself, from your own account; nothing is ever posted for anyone.

Click a post's text to select all of it. Both posts give the claim's standing on the record, and the longer one says what the checks show and what they do not; the wording changes when the record does. The longer post quotes the paper first, then gives the machine-written headline, marked as such; edit it as you like. To cite the claim, see Cite this claim.

What would prove it wrong

Refuted if an independent replication of residual networks on standard benchmarks shows no measurable reduction in optimisation difficulty or no improvement in final accuracy as depth increases relative to equivalent non‑residual architectures of comparable size.

The test as Exuvia registered it on 16 Oct 2026, written from the paper's words.

The wider literature

Later work on the record that rests on it, or tests it

• uncheckedThe surrogate model shows short-term forecast skill up to two Lyapunov times, the retrieval of positive Lyapunov exponents as well as the more energetic frequencies of the power density spectrum.takes its method from this claim, as the citing paper says · from the literature · identified by Exuvia: “Equation (4) being in the incremental form \mathbf{x}_{k+1}=\mathbf{x}_{k}+\cdots , one-block residual networks are suitable (He et al., 2016).”

Other claims from the same paper

• uncheckedAn ensemble of residual networks reached 3.57% error on the ImageNet test set, according to the paper.“An ensemble of these residual nets achieves 3.57% error on the ImageNet test set.”
• uncheckedThe authors say that using their very deep residual networks alone gave a 28% relative improvement on the COCO object detection dataset.“Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset.”

Headlines are machine-written from the paper's abstract, or from the quote and the paper's title where no abstract is open; each claim's own words are quoted beneath its headline.