Pith Number

pith:PNJWVCVU

pith:2026:PNJWVCVUQVC23U7427HTLMJI6U

not attested not anchored not stored refs resolved

Not All Timesteps Matter Equally: Selective Alignment Knowledge Distillation for Spiking Neural Networks

Benjamin Smith, Guowei Zhang, Kai Sun, Levin Kuhlmann, Nanxu Gong, Peibo Duan, Yongsheng Huang

Spiking neural networks gain accuracy when distillation corrects only erroneous timesteps instead of aligning every one uniformly.

arxiv:2605.14252 v1 · 2026-05-14 · 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{PNJWVCVUQVC23U7427HTLMJI6U}

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

Extensive experiments on static image and neuromorphic event-based datasets demonstrate consistent improvements over existing distillation methods.

C2weakest assumption

That erroneous timesteps can be reliably identified from the student's own outputs without introducing new hyperparameters that themselves require extensive tuning or that the reweighting scheme based on confidence and similarity is robust across datasets.

C3one line summary

SeAl-KD improves SNN accuracy by equalizing competing logits at erroneous timesteps and reweighting temporal alignment using confidence and inter-timestep similarity.

References

30 extracted · 30 resolved · 0 Pith anchors

[1] Long short-term memory and learning-to-learn in net- works of spiking neurons.Advances in neural information processing systems, 31, 2018

[2] Imagenet: A large-scale hierarchical image database 2009

[3] Temporal efficient training of spiking neural network via gradient re-weighting 2022

[4] Temporal effective batch normalization in spiking neural networks.Advances in Neural Information Processing Systems, 35:34377– 34390, 2022

[5] In- corporating learnable membrane time constant to enhance learning of spiking neural networks 2021

Formal links

2 machine-checked theorem links

Receipt and verification

First computed	2026-05-17T23:39:10.556516Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

7b536a8ab48545add3fcd7cf35b128f50be79be4936b1df295b55b9bffb3333e

Aliases

arxiv: 2605.14252 · arxiv_version: 2605.14252v1 · doi: 10.48550/arxiv.2605.14252 · pith_short_12: PNJWVCVUQVC2 · pith_short_16: PNJWVCVUQVC23U74 · pith_short_8: PNJWVCVU

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/PNJWVCVUQVC23U7427HTLMJI6U \
  | 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: 7b536a8ab48545add3fcd7cf35b128f50be79be4936b1df295b55b9bffb3333e

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "3a618e38a7c34a476a855760bc7067fef1052a6bf211434949ced69d1493d0ea",
    "cross_cats_sorted": [
      "cs.AI"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2026-05-14T01:39:14Z",
    "title_canon_sha256": "cac011e9bf399d63f81ec4ffa36ff93585db30e28a2df00d5889cfbbb6be4d92"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14252",
    "kind": "arxiv",
    "version": 1
  }
}