SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1611.01989 · 2016

DeepCoder: Learning to Write Programs

arXiv · PDF · Open in the Atlas

Code that ran

8 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 5 have no contract verdict; 3 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/1611.01989.json · badge: /api/ran/1611.01989.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
dkamm/deepcoder community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
lcary/io-generation extension (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
get_input_prefix Ran
ran on a synthesized input
dkamm/deepcoder/deepcoder/nn/encoding.py
code served (permissive licence) · get_code("6226638f508b08ae")
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
import numpy as np

torch.manual_seed(0)

ARGS = {
    'example_idx': 0,
    'input_idx': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
get_input_typename Ran
ran on a synthesized input
dkamm/deepcoder/deepcoder/nn/encoding.py
code served (permissive licence) · get_code("8e0afcd90da2176e")
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
import numpy as np

torch.manual_seed(0)

def get_input_prefix(example_idx, input_idx):
    return 'example{}input{}'.format(example_idx, input_idx)

def get_input_typename(example_idx, input_idx):
    return get_input_prefix(example_idx, input_idx) + 'type'

ARGS = {
    'example_idx': 0,
    'input_idx': 1
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
get_max_nb_inputs Ran
ran on a synthesized input
dkamm/deepcoder/deepcoder/nn/model.py
code served (permissive licence) · get_code("deb6c67a74099fa1")
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 int, ndim 0, dtype family int, shape () 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.

from keras.models import Sequential, Model
from keras.layers import Input, Dense, Embedding, Flatten, InputLayer

# Create a simple Keras model with multiple input layers
inputs = []
outputs = []

# Create input1
input1 = Input(shape=(4,), name='input1')
dense1 = Dense(3)(input1)
inputs.append(input1)
outputs.append(dense1)

# Create input2
input2 = Input(shape=(5,), name='input2')
dense2 = Dense(3)(input2)
inputs.append(input2)
outputs.append(dense2)

# Create input3
input3 = Input(shape=(6,), name='input3')
dense3 = Dense(3)(input3)
inputs.append(input3)
outputs.append(dense3)

# Merge outputs
from keras.layers import Concatenate
merged = Concatenate()(outputs)
final_output = Dense(1)(merged)

model = Model(inputs=inputs, outputs=final_output)

ARGS = {
    'model': model
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type int, ndim 0, dtype family int, shape () — shape () 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
get_tasks Ran
ran; our contract draft was wrong, not the code
lcary/io-generation/iogen/iogen.py
pointer only (licence: NONE) · get_code("9a6e7bf5b92722cf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lcary/io-generation 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_unused_indices Ran
ran on a synthesized input
dkamm/deepcoder/deepcoder/dsl/program.py
code served (permissive licence) · get_code("bd83420f86e6d415")
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 set. 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

class Program:
    def __init__(self, stmts, types):
        self.stmts = stmts
        self.types = types

# Create a simple program with statements and types
# stmts is a list of (operation, inputs) tuples
# types is a list representing variable types (length n+1 where n is max variable index)

stmts = [
    ("op1", [0, 1]),      # statement 0 uses variables 0 and 1
    ("op2", [1, 2]),      # statement 1 uses variables 1 and 2
    ("op3", [0, 3]),      # statement 2 uses variables 0 and 3
]

# types should have length = len(program.types) - 1 + 1
# We have variables 0, 1, 2, 3 used, so we need at least 4 types
# Plus one extra for the -1 indexing, so 5 types total
types = ["int", "int", "int", "int", "int"]

program = Program(stmts=stmts, types=types)

ARGS = {
    "program": program
}
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 set — a set output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a set 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
is_solution Ran
ran on a synthesized input
dkamm/deepcoder/deepcoder/search.py
code served (permissive licence) · get_code("7ea6698dfb1db180")
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 bool, ndim 0, dtype family float, shape () 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

def dummy_program(*inputs):
    # A simple program that returns the sum of all inputs
    return sum(inputs)

def create_examples():
    # Create a list of (inputs, output) tuples
    # Each example is (inputs_tuple, expected_output)
    examples = [
        ((2, 3), 5),
        ((1, 4), 5),
        ((0, 2), 2),
    ]
    return examples

ARGS = {
    "program": dummy_program,
    "examples": create_examples(),
}
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 bool, ndim 0, dtype family float, shape () — shape () 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
progress Ran
ran; our contract draft was wrong, not the code
lcary/io-generation/iogen/iogen.py
pointer only (licence: NONE) · get_code("c8528013d546438b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lcary/io-generation 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.

read_json Ran
ran; our contract draft was wrong, not the code
lcary/io-generation/iogen/iogen.py
pointer only (licence: NONE) · get_code("7cd9850de8c20aa3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, lcary/io-generation 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.

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, 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 8 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

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network's predictions to augment search techniques from the programming languages community, including enumerative search and an SMT-based solver. Empirically, we show that our approach leads to an order of magnitude speedup over the strong non-augmented baselines and a Recurrent Neural Network approach, and that we are able to solve problems of difficulty comparable to the simplest problems on programming competition websites.

For agents

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

get_harvested_code_for_paper("1611.01989")
get_code_for_paper("1611.01989")
have("1611.01989")

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

curl https://syntology.ai/api/ran/1611.01989.json

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

[![Syntology run record](https://syntology.ai/api/ran/1611.01989.svg)](https://syntology.ai/paper/1611.01989)

Connect an agent — have() is free.