Pith Number

pith:VL3WXSYJ

pith:2016:VL3WXSYJ2FP34EL2QPKVVPYFNS

not attested not anchored not stored refs resolved

Gaussian Error Linear Units (GELUs)

Dan Hendrycks, Kevin Gimpel

The GELU activation xΦ(x) outperforms ReLU and ELU on computer vision, natural language processing, and speech tasks.

arxiv:1606.08415 v5 · 2016-06-27 · 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{VL3WXSYJ2FP34EL2QPKVVPYFNS}

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

We perform an empirical evaluation of the GELU nonlinearity against the ReLU and ELU activations and find performance improvements across all considered computer vision, natural language processing, and speech tasks.

C2weakest assumption

That the observed gains on the specific tasks and models tested will generalize to other architectures, datasets, and training regimes without further tuning.

C3one line summary

GELU activation xΦ(x) outperforms ReLU and ELU on computer vision, NLP, and speech tasks by weighting inputs by value rather than gating by sign.

References

50 extracted · 50 resolved · 0 Pith anchors

[1] Adaptive dropout for training deep neural networks , year =

[2] Learning with pseudo-ensembles , year =

[3] International Conference on Learning Representations , title =

[4] A Simple Approximation to the Area Under Standard Normal Curve , year =

[5] Natural Neural Networks , year =

Formal links

2 machine-checked theorem links

Cited by

385 papers in Pith

Steadily moving semi-infinite fracture in plane poroelasticity

Hierarchical Graph Learning for Calendar Spread Strategies in Commodity Futures Markets

FunPiQ: A New Benchmark for Pixel-Level Quality Assessment in Fundus Images

Slay the Shear: A Unified Statistical Framework for Weak Gravitational Lensing Shear Estimation

Quantization Inflates Reasoning: Token Inflation as a Hidden Cost of Low-Bit Reasoning Models

Receipt and verification

First computed	2026-07-05T06:17:34.981584Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

aaf76bcb09d15fbe117a83d55abf056cb9df80b525c95ee008319469da7d0539

Aliases

arxiv: 1606.08415 · arxiv_version: 1606.08415v5 · doi: 10.48550/arxiv.1606.08415 · pith_short_12: VL3WXSYJ2FP3 · pith_short_16: VL3WXSYJ2FP34EL2 · pith_short_8: VL3WXSYJ

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/VL3WXSYJ2FP34EL2QPKVVPYFNS \
  | 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: aaf76bcb09d15fbe117a83d55abf056cb9df80b525c95ee008319469da7d0539

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "d19ddc86b6f6af403cdb4ea404a16d8076ee7f391816001e4b01a7e10ab54c37",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2016-06-27T19:20:40Z",
    "title_canon_sha256": "a5ca717da6d88c1aba68c34fa663664c69d6046b7244dcf0f983783d2d9824e9"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1606.08415",
    "kind": "arxiv",
    "version": 5
  }
}