SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1602.02410 · 2016

Exploring the Limits of Language Modeling

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 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 2 have no contract verdict; 2 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/1602.02410.json · badge: /api/ran/1602.02410.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
okuchaiev/f-lm community (classifier label)
classifier basis not recorded on the link
2 ran · 4 no recorded run
rafaljozefowicz/lm reimplementation (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
assign_to_gpu Ran
ran on a synthesized input
okuchaiev/f-lm/common.py
code served (permissive licence) · get_code("6b2a8f1c93d0b071")
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 as tf

# The function assign_to_gpu takes two parameters:
# - gpu: an integer specifying which GPU to use
# - ps_dev: a string specifying the parameter server device

# Looking at the function body, it returns a closure _assign that:
# 1. Takes an op (which can be a tf.NodeDef or an object with a .node_def attribute)
# 2. Checks if op.node_def.op == 'Variable'
# 3. Returns either ps_dev or a GPU device string

# Create a minimal mock NodeDef-like object for testing
class MockNodeDef:
    def __init__(self, op_type='MatMul'):
        self.op = op_type

class MockOp:
    def __init__(self, op_type='MatMul'):
        self.node_def = MockNodeDef(op_type)

# Define the arguments
ARGS = {
    'gpu': 0,
    'ps_dev': '/device:CPU:0'
}
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
create_tmux_commands Ran
ran; our contract draft was wrong, not the code
rafaljozefowicz/lm/single_lm_run.py
code served (permissive licence) · get_code("ae7f96f3c9e86ec8")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned list, ndim 1, 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 torch
import numpy as np

torch.manual_seed(0)

session = "my_session"
gpus = [0, 1, 2]
logdir = "/tmp/logdir"
hpconfig = "config1"
datadir = "/tmp/datadir"

ARGS = {
    "session": session,
    "gpus": gpus,
    "logdir": logdir,
    "hpconfig": hpconfig,
    "datadir": datadir
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
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
getdtype Ran
ran on a synthesized input
okuchaiev/f-lm/model_utils.py
code served (permissive licence) · get_code("a5f575756e5a77ed")
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 DType. 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 as tf

class HPS:
    def __init__(self, float16_rnn=False, float16_non_rnn=False):
        self.float16_rnn = float16_rnn
        self.float16_non_rnn = float16_non_rnn

hps_rnn_false = HPS(float16_rnn=False, float16_non_rnn=False)
hps_rnn_true = HPS(float16_rnn=True, float16_non_rnn=False)
hps_non_rnn_true = HPS(float16_rnn=False, float16_non_rnn=True)

ARGS = {
    "hps": hps_rnn_false,
    "is_rnn": False
}
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 DType — a DType output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DType 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
new_tmux_cmd Ran
ran; our contract draft was wrong, not the code
rafaljozefowicz/lm/single_lm_run.py
code served (permissive licence) · get_code("ca384af890f0edff")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned tuple, ndim 1, 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 torch
import numpy as np

# The function takes two parameters: name and cmd
# name: a string representing the tmux session name
# cmd: either a string or a list/tuple that will be converted to a string

# Test case 1: cmd as a string
name_str = "my_session"
cmd_str = "python train.py --epochs 10"

# Test case 2: cmd as a list (the function will join it)
name_list = "another_session"
cmd_list = ["python", "train.py", "--epochs", 10, "--lr", 0.001]

# We'll use the list version to test the isinstance and join logic
ARGS = {
    "name": name_list,
    "cmd": cmd_list
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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
find_trainable_variables Not yet run
unverified (harvested, no recorded run)
okuchaiev/f-lm/common.py
code served (permissive licence) · get_code("909cf81b1c39b724")
How it ran

no invocation recorded.

linear Not yet run
unverified (harvested, no recorded run)
okuchaiev/f-lm/model_utils.py
code served (permissive licence) · get_code("9aa311876def94db")
How it ran

no invocation recorded.

load_from_checkpoint Not yet run
unverified (harvested, no recorded run)
okuchaiev/f-lm/common.py
code served (permissive licence) · get_code("3d6b054785523852")
How it ran

no invocation recorded.

sharded_variable Not yet run
unverified (harvested, no recorded run)
okuchaiev/f-lm/model_utils.py
code served (permissive licence) · get_code("7045d5e35d2c9925")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 5 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
assign_to_gpu 3 other papers
3 later
1606.04934 (2016-06)
Improving Variational Inference with Inverse Autoregressive Flow
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2004.13922 (2020-04)
Revisiting Pre-trained Models for Chinese Natural Language Processing
load_from_checkpoint 2 other papers
2 later
1901.02860 (2019-01)
Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context
2004.13922 (2020-04)
Revisiting Pre-trained Models for Chinese Natural Language Processing
find_trainable_variables 1 other paper
1 later
1606.04934 (2016-06)
Improving Variational Inference with Inverse Autoregressive Flow

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

In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language. We perform an exhaustive study on techniques such as character Convolutional Neural Networks or Long-Short Term Memory, on the One Billion Word Benchmark. Our best single model significantly improves state-of-the-art perplexity from 51.3 down to 30.0 (whilst reducing the number of parameters by a factor of 20), while an ensemble of models sets a new record by improving perplexity from 41.0 down to 23.7. We also release these models for the NLP and ML community to study and improve upon.

For agents

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

get_harvested_code_for_paper("1602.02410")
get_code_for_paper("1602.02410")
have("1602.02410")

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

curl https://syntology.ai/api/ran/1602.02410.json

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

[![Syntology run record](https://syntology.ai/api/ran/1602.02410.svg)](https://syntology.ai/paper/1602.02410)

Connect an agent — have() is free.