Pith Number

pith:52FPSCX5

pith:2019:52FPSCX54XKSAO7XWVIESKS6JR

not attested not anchored not stored refs resolved

Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

Du Phan, Martin Jankowiak, Neeraj Pradhan

NumPyro composes Pyro effect handlers with JAX to deliver a fully JIT-compiled iterative NUTS sampler.

arxiv:1912.11554 v1 · 2019-12-24 · stat.ML · cs.AI · cs.LG · cs.PL

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

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{52FPSCX54XKSAO7XWVIESKS6JR}

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

NumPyro provides an iterative formulation of the No-U-Turn Sampler (NUTS) that can be end-to-end JIT compiled, yielding an implementation that is much faster than existing alternatives in both the small and large dataset regimes.

C2weakest assumption

That Pyro's effect handlers compose cleanly with JAX's functional transformations without introducing correctness issues or losing expressiveness in the modeling API.

C3one line summary

NumPyro delivers a JIT-compilable iterative NUTS sampler by composing Pyro effect handlers with JAX transformations, achieving faster performance than prior implementations.

References

25 extracted · 25 resolved · 3 Pith anchors

[1] Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro 1912 · arXiv:1912.11554

[2] 2018 , copyright = 2018

[3] Chen, Martin Jankowiak, Fritz Obermeyer, Neeraj Pradhan, Theofanis Karaletsos, Rohit Singh, Paul Szerlip, Paul Horsfall, and Noah D 2019

[4] Learning disentangled representations with semi-supervised deep generative models 2017

[5] Automatic differentiation in pytorch 2017

Formal links

2 machine-checked theorem links

Cited by

50 papers in Pith

Uncertainty-aware classification and triage of structural heart disease using electrocardiography and echocardiography metrics

A Strongly Parametrized Mass Ratio Model for the Stable Mass Transfer Channel: a Case Study of the $10 \, \rm{M}_{\odot}$ Peak

Archimedean Copula Inference via Taylor-Mode AD

Temporal Point Process Modeling of Aggressive Behavior Onset in Psychiatric Inpatient Youths with Autism

LITMUS: Bayesian Lag Recovery in Reverberation Mapping with Fast Differentiable Models

Receipt and verification

First computed	2026-05-17T23:38:50.992672Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

ee8af90afde5d5203bf7b550492a5e4c46bd268faf40cd2a835c37b32cb09d3c

Aliases

arxiv: 1912.11554 · arxiv_version: 1912.11554v1 · doi: 10.48550/arxiv.1912.11554 · pith_short_12: 52FPSCX54XKS · pith_short_16: 52FPSCX54XKSAO7X · pith_short_8: 52FPSCX5

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/52FPSCX54XKSAO7XWVIESKS6JR \
  | 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: ee8af90afde5d5203bf7b550492a5e4c46bd268faf40cd2a835c37b32cb09d3c

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "23b4291795aec701f8a107f83cc5925ae9b17f75d4488a1480b7e616c2a31232",
    "cross_cats_sorted": [
      "cs.AI",
      "cs.LG",
      "cs.PL"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "stat.ML",
    "submitted_at": "2019-12-24T22:09:36Z",
    "title_canon_sha256": "4cada3a002c300a0256c850b4de223b1aecb15768cfd628ce5059fb220f3bb79"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1912.11554",
    "kind": "arxiv",
    "version": 1
  }
}