SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1906.03028 · 2019

Automatic Reparameterisation of Probabilistic Programs

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 1 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 0 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1906.03028.json · badge: /api/ran/1906.03028.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
mgorinova/autoreparam canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
compute_V_cp Ran
ran on a synthesized input
mgorinova/autoreparam/util.py
code served (permissive licence) · get_code("9f22b38048661a6f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Analyze the function:
# - q: used in arithmetic operations (v * q, q + 1.0, q * v + 1.0)
#   appears to be a scalar
# - v: used in arithmetic operations (v * q, v * ..., q * v + 1.0)
#   appears to be a scalar

# Both q and v should be numeric scalars (float or int)

ARGS = {
    "q": 2.5,
    "v": 1.5,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
compute_V_ncp Ran
ran on a synthesized input
mgorinova/autoreparam/util.py
code served (permissive licence) · get_code("0e1ccee430cf81fb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (2, 2) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

ARGS = {
    "q": 0.5,
    "v": 2.0,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (2, 2) — shape (2, 2) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
condition_number_cp Ran
ran on a synthesized input
mgorinova/autoreparam/util.py
code served (permissive licence) · get_code("3da7a9d10a513e29")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned float64, ndim 0, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# The function takes two parameters: q and v
# Looking at the function body, both q and v are used in arithmetic operations
# They appear to be scalars or array-like values that support multiplication and addition

# Create simple scalar values
q = 0.5
v = 2.0

ARGS = {
    "q": q,
    "v": v
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
make_name Ran
ran on a synthesized input
mgorinova/autoreparam/interleaved.py
code served (permissive licence) · get_code("c9bbc9c0ea59e04e")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

ARGS = {
    'super_name': 'layer',
    'default_super_name': 'default_layer',
    'sub_name': 'activation'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
noop Ran
ran, honoured the contract we drafted
mgorinova/autoreparam/experiments.py
pointer only (licence: Apache-2.0); the stored copy get_code serves, from Abhimanyu08/Fixup_Initialization, is pointer only (licence: NONE) · get_code("5e2ed23acb71ee11")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (Apache-2.0), but get_code serves the stored copy, first harvested from Abhimanyu08/Fixup_Initialization, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

noop Ran
ran on a synthesized input
mgorinova/autoreparam/interleaved.py
code served (permissive licence) · get_code("aba14daf28d3175a")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

# The function noop simply takes a state and returns it unchanged
# So we need to provide any valid state object

# State can be anything - let's use a simple dictionary containing
# common state elements like tensors and scalars
state = {
    "model_weights": torch.randn(2, 4),
    "optimizer_step": 42,
    "loss_history": [0.5, 0.3, 0.1],
    "embeddings": torch.randn(3, 5),
}

ARGS = {
    "state": state
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
vectorize_log_joint_fn Ran
ran on a synthesized input
mgorinova/autoreparam/inference.py
code served (permissive licence) · get_code("66b5334755ae400b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned function. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tensorflow.compat.v1 as tf

# Disable v2 behavior for TensorFlow 1.x compatibility
tf.disable_v2_behavior()

# Define a simple log_joint_fn that takes tensor arguments
def simple_log_joint_fn(x, y=None):
    """A simple log joint function that returns a scalar log probability."""
    # Sum the input tensors to create a scalar log probability
    result = tf.reduce_sum(x)
    if y is not None:
        result = result + tf.reduce_sum(y)
    return result

# Create test tensors with batch dimension
# Batch size 2, feature dimension 4
x_tensor = tf.constant([[1.0, 2.0, 3.0, 4.0], 
                        [5.0, 6.0, 7.0, 8.0]], dtype=tf.float32)

y_tensor = tf.constant([[0.1, 0.2, 0.3, 0.4],
                        [0.5, 0.6, 0.7, 0.8]], dtype=tf.float32)

ARGS = {
    'log_joint_fn': simple_log_joint_fn
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_elbos Not yet run
unverified (harvested, no recorded run)
mgorinova/autoreparam/analyze.py
code served (permissive licence) · get_code("c99ff784c604402c")
How it ran

no invocation recorded.

get_ess Not yet run
unverified (harvested, no recorded run)
mgorinova/autoreparam/analyze.py
code served (permissive licence) · get_code("2a770f8d95a41e3c")
How it ran

no invocation recorded.

get_reparam Not yet run
unverified (harvested, no recorded run)
mgorinova/autoreparam/analyze.py
code served (permissive licence) · get_code("1d4e615330e70e0f")
How it ran

no invocation recorded.

transform_mcmc_states Not yet run
unverified (harvested, no recorded run)
mgorinova/autoreparam/experiments.py
code served (permissive licence) · get_code("24da04d140b6c70a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 10 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
noop 9 other papers
2 dated earlier, 7 later
1805.08318 (2018-05)
Self-Attention Generative Adversarial Networks
1901.09321 (2019-01)
Fixup Initialization: Residual Learning Without Normalization
1908.08681 (2019-08)
Mish: A Self Regularized Non-Monotonic Activation Function
and 6 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Probabilistic programming has emerged as a powerful paradigm in statistics, applied science, and machine learning: by decoupling modelling from inference, it promises to allow modellers to directly reason about the processes generating data. However, the performance of inference algorithms can be dramatically affected by the parameterisation used to express a model, requiring users to transform their programs in non-intuitive ways. We argue for automating these transformations, and demonstrate that mechanisms available in recent modeling frameworks can implement non-centring and related reparameterisations. This enables new inference algorithms, and we propose two: a simple approach using interleaved sampling and a novel variational formulation that searches over a continuous space of parameterisations. We show that these approaches enable robust inference across a range of models, and can yield more efficient samplers than the best fixed parameterisation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1906.03028")
get_code_for_paper("1906.03028")
have("1906.03028")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1906.03028.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1906.03028.svg)](https://syntology.ai/paper/1906.03028)

Connect an agent — have() is free.