SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.06732 · 2019

Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 1 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/1907.06732.json · badge: /api/ran/1907.06732.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
ml-research/rational_activations extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
ChristophReich1996/Pade-Activation-Unit reimplementation (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
FunctionStatusWhere it lives
Rational_PYTORCH_A_F Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-research/rational_activations/rational/torch/rational_pytorch_functions.py
code served (permissive licence) · get_code("39ec3d1f9d97cc5c")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# Analyze the function:
# - x: tensor that gets viewed as 1D, then reshaped back to original shape
# - weight_numerator: list/sequence with len() called on it
# - weight_denominator: list/sequence with len() called on it
# - training: boolean flag (used in function signature but not in body)

# Create small test tensors and weights
x = torch.randn(2, 4)  # batch_size=2, feature_dim=4
weight_numerator = torch.tensor([0.5, 0.3, 0.2])  # length 3
weight_denominator = torch.tensor([0.1, 0.05])  # length 2
training = True

ARGS = {
    "x": x,
    "weight_numerator": weight_numerator,
    "weight_denominator": weight_denominator,
    "training": training,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
Rational_PYTORCH_B_F Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-research/rational_activations/rational/torch/rational_pytorch_functions.py
code served (permissive licence) · get_code("15a510212432a6c3")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# Analyze the function:
# - x: tensor that gets viewed as 1D, then reshaped back to original shape
# - weight_numerator: list/sequence, len() is called on it
# - weight_denominator: list/sequence, len() is called on it
# - training: boolean flag (not used in function body, but parameter exists)

# Create small test tensors
x = torch.randn(2, 4)  # batch_size=2, feature_dim=4

# weight_numerator and weight_denominator are used in:
# xps.mul(weight_numerator).sum(1) - so they need to be broadcastable with xps
# xps has shape (flattened_x_size, max(len_num, len_deno))
# They're multiplied element-wise, so they should be 1D tensors of appropriate length

len_num = 3
len_deno = 2

weight_numerator = torch.randn(len_num)
weight_denominator = torch.randn(len_deno)

training = True

ARGS = {
    "x": x,
    "weight_numerator": weight_numerator,
    "weight_denominator": weight_denominator,
    "training": training,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
Rational_PYTORCH_C_F Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ml-research/rational_activations/rational/torch/rational_pytorch_functions.py
code served (permissive licence) · get_code("6e3e9a40d8b5f9f7")
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) and returned Tensor, ndim 2, dtype family float, shape (2, 4) 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 torch

torch.manual_seed(0)

# Analyze the function:
# - x: tensor that gets viewed as 1D, then reshaped back to original shape
# - weight_numerator: list/sequence with len() called, elements used in multiplication
# - weight_denominator: list/sequence with len() called, elements used in multiplication
# - training: boolean flag (not used in function body, but parameter exists)

# Create a small input tensor (batch=2, features=4)
x = torch.randn(2, 4)

# weight_numerator and weight_denominator need to be sequences of scalars/tensors
# that can be multiplied with xps (which has shape [batch_size*features, max_len+1])
# Looking at the code: xps.mul(weight_numerator).sum(1)
# This means weight_numerator should be broadcastable with xps
# xps shape is [z.numel(), max(len_num, len_deno)]
# So weight_numerator should have length max(len_num, len_deno)

# Let's use len_numerator=3, len_denominator=2
weight_numerator = torch.tensor([0.5, 0.3, 0.2])
weight_denominator = torch.tensor([0.4, 0.6])

training = True

ARGS = {
    "x": x,
    "weight_numerator": weight_numerator,
    "weight_denominator": weight_denominator,
    "training": training,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) 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
freeze_pau Not yet run
unverified (harvested, no recorded run)
ChristophReich1996/Pade-Activation-Unit/pau/pau.py
code served (permissive licence) · get_code("e09004320aabd5a6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 1 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
Rational_PYTORCH_A_F 1 other paper
1 later
2102.09407 (2021-02)
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Rational_PYTORCH_B_F 1 other paper
1 later
2102.09407 (2021-02)
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Rational_PYTORCH_C_F 1 other paper
1 later
2102.09407 (2021-02)
Adaptive Rational Activations to Boost Deep Reinforcement Learning

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

The performance of deep network learning strongly depends on the choice of the non-linear activation function associated with each neuron. However, deciding on the best activation is non-trivial, and the choice depends on the architecture, hyper-parameters, and even on the dataset. Typically these activations are fixed by hand before training. Here, we demonstrate how to eliminate the reliance on first picking fixed activation functions by using flexible parametric rational functions instead. The resulting Padé Activation Units (PAUs) can both approximate common activation functions and also learn new ones while providing compact representations. Our empirical evidence shows that end-to-end learning deep networks with PAUs can increase the predictive performance. Moreover, PAUs pave the way to approximations with provable robustness. https://github.com/ml-research/pau

For agents

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

get_harvested_code_for_paper("1907.06732")
get_code_for_paper("1907.06732")
have("1907.06732")

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

curl https://syntology.ai/api/ran/1907.06732.json

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

[![Syntology run record](https://syntology.ai/api/ran/1907.06732.svg)](https://syntology.ai/paper/1907.06732)

Connect an agent — have() is free.