SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.03474 · 2016

Recurrent Highway Networks

arXiv · PDF · Open in the Atlas

Code that ran

1 of 5 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; 1 failure of our instrument; 4 no recorded run), measured 2026-11-21; 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/1607.03474.json · badge: /api/ran/1607.03474.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
jzilly/RecurrentHighwayNetworks canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
julian121266/RecurrentHighwayNetworks canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
FunctionStatusWhere it lives
get_noise Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
jzilly/RecurrentHighwayNetworks/rhn_train.py
code served (permissive licence) · get_code("707c42ff0294c173")
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 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 numpy as np

class MockModel:
    def __init__(self, batch_size, num_steps, in_size, num_layers, size):
        self.batch_size = batch_size
        self.num_steps = num_steps
        self.in_size = in_size
        self.num_layers = num_layers
        self.size = size

# Create a mock model with distinct dimensions
m = MockModel(
    batch_size=2,
    num_steps=5,
    in_size=3,
    num_layers=4,
    size=6
)

# Create input x with shape (batch_size, num_steps)
# x contains indices that may repeat within a batch
x = np.array([
    [0, 1, 2, 1, 3],
    [1, 2, 3, 2, 4]
], dtype=np.int32)

# Dropout rates
drop_x = 0.1
drop_i = 0.2
drop_h = 0.15
drop_o = 0.25

ARGS = {
    "x": x,
    "m": m,
    "drop_x": drop_x,
    "drop_i": drop_i,
    "drop_h": drop_h,
    "drop_o": drop_o
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — 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
get_data Not yet run
unverified (harvested, no recorded run)
jzilly/RecurrentHighwayNetworks/rhn_train.py
code served (permissive licence) · get_code("1830fedb612f3096")
How it ran

no invocation recorded.

hutter_raw_data Not yet run
unverified (harvested, no recorded run)
julian121266/RecurrentHighwayNetworks/theano_data.py
code served (permissive licence) · get_code("6a69d00503759095")
How it ran

no invocation recorded.

linear Not yet run
unverified (harvested, no recorded run)
julian121266/RecurrentHighwayNetworks/rhn.py
code served (permissive licence) · get_code("8d9ff9ce8321b114")
How it ran

no invocation recorded.

ptb_raw_data Not yet run
unverified (harvested, no recorded run)
julian121266/RecurrentHighwayNetworks/theano_data.py
code served (permissive licence) · get_code("65745cdcd83aced6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 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.

FunctionAlso present inEarliest-datedOthers named
ptb_raw_data 1 other paper
1 later
1611.10176 (2016-11)
Effective Quantization Methods for Recurrent Neural Networks

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with 'deep' transition functions remain difficult to train, even when using Long Short-Term Memory (LSTM) networks. We introduce a novel theoretical analysis of recurrent networks based on Gersgorin's circle theorem that illuminates several modeling and optimization issues and improves our understanding of the LSTM cell. Based on this analysis we propose Recurrent Highway Networks, which extend the LSTM architecture to allow step-to-step transition depths larger than one. Several language modeling experiments demonstrate that the proposed architecture results in powerful and efficient models. On the Penn Treebank corpus, solely increasing the transition depth from 1 to 10 improves word-level perplexity from 90.6 to 65.4 using the same number of parameters. On the larger Wikipedia datasets for character prediction (text8 and enwik8), RHNs outperform all previous results and achieve an entropy of 1.27 bits per character.

For agents

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

get_harvested_code_for_paper("1607.03474")
get_code_for_paper("1607.03474")
have("1607.03474")

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

curl https://syntology.ai/api/ran/1607.03474.json

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

[![Syntology run record](https://syntology.ai/api/ran/1607.03474.svg)](https://syntology.ai/paper/1607.03474)

Connect an agent — have() is free.