Pith Number

pith:XTMPV52M

pith:2016:XTMPV52MWM2PJDBQXKLMDG7SUW

not attested not anchored not stored refs resolved

HyperNetworks

Andrew Dai, David Ha, Quoc V. Le

A hypernetwork generates the weights for another network to enable non-shared weights in LSTMs.

arxiv:1609.09106 v4 · 2016-09-27 · 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{XTMPV52MWM2PJDBQXKLMDG7SUW}

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

Our main result is that hypernetworks can generate non-shared weights for LSTM and achieve near state-of-the-art results on a variety of sequence modelling tasks including character-level language modelling, handwriting generation and neural machine translation, challenging the weight-sharing paradigm for recurrent networks.

C2weakest assumption

The assumption that the hypernetwork can be effectively trained end-to-end with backpropagation to produce high-quality weights for the main network without introducing instability, overfitting, or requiring excessive additional computation.

C3one line summary

Hypernetworks generate weights for a main network, allowing LSTMs to use non-shared weights and achieve near state-of-the-art results on sequence modeling tasks while using fewer parameters overall.

References

2 extracted · 2 resolved · 0 Pith anchors

[1] TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems 2016 · arXiv:1603.04467

[2] Large Embedding 2015

Formal links

2 machine-checked theorem links

Cited by

35 papers in Pith

ARMIN: Towards a More Efficient and Light-weight Recurrent Memory Network

UniReg: A Universal Model for Controllable CT Image Registration

DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation

Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentation

TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Receipt and verification

First computed	2026-05-18T03:23:37.616277Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f

Aliases

arxiv: 1609.09106 · arxiv_version: 1609.09106v4 · doi: 10.48550/arxiv.1609.09106 · pith_short_12: XTMPV52MWM2P · pith_short_16: XTMPV52MWM2PJDBQ · pith_short_8: XTMPV52M

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/XTMPV52MWM2PJDBQXKLMDG7SUW \
  | 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: bcd8faf74cb334f48c30ba96c19bf2a5a450e16762219b99ee36f70678c1053f

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "85d2334c445f73488e44c555f4a9dff5581eefd31f01895a8957c256ad2c12be",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.LG",
    "submitted_at": "2016-09-27T05:57:00Z",
    "title_canon_sha256": "8bf1cfa479388c867ba136c02430ed6c91ee9657893763355e6cdb314b78f562"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1609.09106",
    "kind": "arxiv",
    "version": 4
  }
}