Pith Number

pith:V6FO5VMU

pith:2026:V6FO5VMUUFJSHSFRGJMOFIG3ZP

not attested not anchored not stored refs resolved

SURGE: Surrogate Gradient Adaptation in Binary Neural Networks

Baochang Zhang, Boyu Liu, Canyu Chen, Haoyu Huang, Linlin Yang, Xuhui Liu, Yanjing Li, Yuguang Yang, Zhongqian Fu

Binary neural networks train more accurately when a learnable surrogate gradient uses an auxiliary full-precision branch to reduce mismatch.

arxiv:2605.10989 v2 · 2026-05-09 · cs.LG · cs.AI

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{V6FO5VMUUFJSHSFRGJMOFIG3ZP}

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

Experiments on image classification, object detection, and language understanding tasks demonstrate that SURGE performs best over state-of-the-art methods.

C2weakest assumption

The full-precision auxiliary branch in DPGC provides bias-reduced gradient estimates beyond the first-order STE approximation without introducing new mismatches or instabilities during training.

C3one line summary

SURGE introduces a dual-path gradient compensator and adaptive scaler to improve surrogate gradient estimation in binarized neural network training.

References

129 extracted · 129 resolved · 11 Pith anchors

[1] Scaling Learning Algorithms Towards

[2] Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation · arXiv:1308.3432

[3] Learning sparse neural networks through L\_0 regularization , author=

[4] Differentiable soft quantization: Bridging full-precision and low-bit neural networks , author=

[5] Binaryconnect: Training deep neural networks with binary weights during propagations , author=

Receipt and verification

First computed	2026-05-20T00:00:42.650092Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

af8aeed594a15323c8b13258e2a0dbcbf282fef13b828e8611a498acd564b864

Aliases

arxiv: 2605.10989 · arxiv_version: 2605.10989v2 · doi: 10.48550/arxiv.2605.10989 · pith_short_12: V6FO5VMUUFJS · pith_short_16: V6FO5VMUUFJSHSFR · pith_short_8: V6FO5VMU

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/V6FO5VMUUFJSHSFRGJMOFIG3ZP \
  | 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: af8aeed594a15323c8b13258e2a0dbcbf282fef13b828e8611a498acd564b864

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "2d08372d9a4c7b48dbc14e28644d640bf9ae342b1f3921f992fd13232fc40b07",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-09T09:52:38Z",
    "title_canon_sha256": "1b015046d7a5cfebfacbfb405d8f00f88db4ab80a6a8aef77987b0e9b4c4f95e"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.10989",
    "kind": "arxiv",
    "version": 2
  }
}