Pith Number

pith:KZQQ3R6M

pith:2014:KZQQ3R6MQZLMDEPSWUDJX22IMT

not attested not anchored not stored refs pending

FitNets: Hints for Thin Deep Nets

Adriana Romero, Antoine Chassang, Carlo Gatta, Nicolas Ballas, Samira Ebrahimi Kahou, Yoshua Bengio

A deeper but much thinner student network can outperform its larger teacher by using intermediate layer hints during training.

arxiv:1412.6550 v4 · 2014-12-19 · cs.LG · cs.NE

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{KZQQ3R6MQZLMDEPSWUDJX22IMT}

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

For example, on CIFAR-10, a deep student network with almost 10.4 times less parameters outperforms a larger, state-of-the-art teacher network.

C2weakest assumption

That the added mapping parameters can reliably transfer useful intermediate knowledge from teacher to a much smaller student layer without the extra capacity causing overfitting or unstable training.

C3one line summary

FitNets trains deeper thinner students using teacher intermediate representations as hints plus mapping parameters, yielding a CIFAR-10 student with 10.4x fewer parameters that beats the teacher.

Formal links

2 machine-checked theorem links

Cited by

38 papers in Pith

GAN-Knowledge Distillation for one-stage Object Detection

NetTailor: Tuning the Architecture, Not Just the Weights

Graph-based Knowledge Distillation by Multi-head Attention Network

Co-Evolutionary Compression for Unpaired Image Translation

Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix

Receipt and verification

First computed	2026-05-18T02:48:56.381163Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862

Aliases

arxiv: 1412.6550 · arxiv_version: 1412.6550v4 · doi: 10.48550/arxiv.1412.6550 · pith_short_12: KZQQ3R6MQZLM · pith_short_16: KZQQ3R6MQZLMDEPS · pith_short_8: KZQQ3R6M

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/KZQQ3R6MQZLMDEPSWUDJX22IMT \
  | 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: 56610dc7cc8656c191f2b5069beb4864c29131d16aca960b08833884d43ee862

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "b5c36af2ae418d3cbb6cb525c0fd90318369ba1593e5468e6d797db8d6eb1e00",
    "cross_cats_sorted": [
      "cs.NE"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2014-12-19T22:40:51Z",
    "title_canon_sha256": "c3bc2e609ab2b30436e11b3b9d743c43e32d29b3d00eab409106a628206b534c"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1412.6550",
    "kind": "arxiv",
    "version": 4
  }
}