SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1603.08983 · 2016

Adaptive Computation Time for Recurrent Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

4 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, 1 violated it and 3 have no contract verdict; 0 failures of our instrument; 0 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/1603.08983.json · badge: /api/ran/1603.08983.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
ceyzaguirre4/adaptive_computation community (classifier label)
classifier basis not recorded on the link
3 ran · 0 no recorded run
andreamad8/Universal-Transformer-Pytorch reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
get_attn_key_pad_mask Ran
ran, violated the contract we drafted
andreamad8/Universal-Transformer-Pytorch/models/UTransformer.py
pointer only (licence: NONE) · get_code("095dea140acd99f6")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, andreamad8/Universal-Transformer-Pytorch 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.

get_path Ran
ran on a synthesized input
ceyzaguirre4/adaptive_computation/act/utils.py
code served (permissive licence) · get_code("58caec2a4f1159dc")
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.

from pathlib import Path

ARGS = {
    'path': 'output/results',
    'prefix': ''
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — 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
pad_batch Ran
ran on a synthesized input
ceyzaguirre4/adaptive_computation/act/utils.py
code served (permissive licence) · get_code("ad8b210c90bf993e")
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 tuple. 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

torch.manual_seed(0)

# Construct a batch for pad_batch function
# The function expects a list of tuples, where each tuple contains tensors
# Each tuple's first element is a tensor where the first dimension varies
# Each tuple's second element is a tensor used for masking (summed over dim 2)

# Create sample data with varying first dimension lengths
# First tuple: 2D tensor (3, 4) and 3D tensor (3, 4, 5)
tup1_elem1 = torch.randn(3, 4)
tup1_elem2 = torch.randn(3, 4, 5)
tup1 = (tup1_elem1, tup1_elem2)

# Second tuple: 2D tensor (5, 4) and 3D tensor (5, 4, 5)
tup2_elem1 = torch.randn(5, 4)
tup2_elem2 = torch.randn(5, 4, 5)
tup2 = (tup2_elem1, tup2_elem2)

# Batch is a list of tuples
batch = [tup1, tup2]

ARGS = {
    "batch": batch
}
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 tuple — a tuple output has no array shape of its own; none is 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
pad_tensor Ran
ran on a synthesized input
ceyzaguirre4/adaptive_computation/act/utils.py
code served (permissive licence) · get_code("4ba0c3a66ce30058")
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 Tensor, ndim 2, dtype family float, shape (2, 6) 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)

# Create a small tensor to pad
# Using shape (2, 4) for batch_size=2, feature_dim=4
vec = torch.randn(2, 4)

# Padding size - larger than current size in the dimension
pad = 6

# Dimension to pad along
dim = 1

ARGS = {
    "vec": vec,
    "pad": pad,
    "dim": dim,
}
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 Tensor, ndim 2, dtype family float, shape (2, 6) — shape (2, 6) 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

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, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the network architecture, is deterministic and differentiable, and does not add any noise to the parameter gradients. Experimental results are provided for four synthetic problems: determining the parity of binary vectors, applying binary logic operations, adding integers, and sorting real numbers. Overall, performance is dramatically improved by the use of ACT, which successfully adapts the number of computational steps to the requirements of the problem. We also present character-level language modelling results on the Hutter prize Wikipedia dataset. In this case ACT does not yield large gains in performance; however it does provide intriguing insight into the structure of the data, with more computation allocated to harder-to-predict transitions, such as spaces between words and ends of sentences. This suggests that ACT or other adaptive computation methods could provide a generic method for inferring segment boundaries in sequence data.

For agents

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

get_harvested_code_for_paper("1603.08983")
get_code_for_paper("1603.08983")
have("1603.08983")

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

curl https://syntology.ai/api/ran/1603.08983.json

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

[![Syntology run record](https://syntology.ai/api/ran/1603.08983.svg)](https://syntology.ai/paper/1603.08983)

Connect an agent — have() is free.