SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2002.05810 · 2020

RNA Secondary Structure Prediction By Learning Unrolled Algorithms

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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 8 have no contract verdict; 2 failures of our instrument; 1 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/2002.05810.json · badge: /api/ran/2002.05810.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
ml4bio/e2efold canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
Gaussian Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/utils.py
code served (permissive licence) · get_code("133678d9013b3eeb")
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 float, 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 math

def Gaussian(x):
    return math.exp(-0.5 * (x * x))

ARGS = {
    "x": 0.5
}
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 float, 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
combine_chunk_u_maps Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/long_seq_pre_post_process.py
code served (permissive licence) · get_code("7fd98b5c22388683")
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 (12, 12) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
import numpy as np

torch.manual_seed(0)

# Analyze the function:
# - chunk_cm_list: list of tensors, each with shape (2*chunk_size, 2*chunk_size)
# - comb_index: list of tuples (i, j) pairs
# - chunks: integer, maximum value in comb_index should be chunks - 1

# Set up parameters
chunk_size = 4
chunks = 3

# Create chunk_cm_list with small tensors of shape (8, 8)
# Each tensor is (2*chunk_size, 2*chunk_size) = (8, 8)
chunk_cm_list = [
    torch.randn(2 * chunk_size, 2 * chunk_size),
    torch.randn(2 * chunk_size, 2 * chunk_size),
    torch.randn(2 * chunk_size, 2 * chunk_size),
]

# Create comb_index with valid (i, j) pairs
# Max value should be chunks - 1 = 2
comb_index = [
    (0, 1),
    (0, 2),
    (1, 2),
]

ARGS = {
    'chunk_cm_list': chunk_cm_list,
    'comb_index': comb_index,
    'chunks': chunks,
}
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 Tensor, ndim 2, dtype family float, shape (12, 12) — shape (12, 12) 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_activation Ran
ran; our contract draft was wrong, not the code
ml4bio/e2efold/experiment_archiveii/e2e_learning_stage1.py
pointer only (licence: MIT); the stored copy get_code serves, from adverml/spectraldef_framework, is pointer only (licence: AGPL-3.0) · get_code("315b5ee37bf1681f")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from adverml/spectraldef_framework, and AGPL-3.0, as GitHub detects it on that repository, is not in the permissive set Syntology serves inline. 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_chunk_combination Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/long_seq_pre_post_process.py
code served (permissive licence) · get_code("9141977368ce6516")
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
from itertools import combinations

torch.manual_seed(0)

# The function expects:
# - long_seq: a tensor that has length divisible by 300
# - chunk_size: an integer (default 300)

# Create a small tensor with length divisible by 300
# Using 600 elements (divisible by 300) with shape (600, 4) to keep it small
long_seq = torch.randn(600, 4)

ARGS = {
    "long_seq": long_seq,
    "chunk_size": 300,
}
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
get_chunk_gt Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/long_seq_pre_post_process.py
code served (permissive licence) · get_code("e9a961c50de00a20")
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 list, ndim 3, 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

torch.manual_seed(0)

# Create a ground truth tensor
# The function slices it into chunks, so we need it large enough
# With chunk_size=300 and indices up to 1, we need at least 600x600
gt = torch.randn(600, 600)

# Create comb_index: a list of tuples (i, j) representing chunk combinations
# Each tuple represents a pair of chunk indices
comb_index = [(0, 1), (1, 0)]

ARGS = {
    "gt": gt,
    "comb_index": comb_index,
    "chunk_size": 300
}
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 list, ndim 3, 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
get_config_from_json Ran
ran; our contract draft was wrong, not the code
ml4bio/e2efold/e2efold/common/config.py
code served (permissive licence) · get_code("4258b63a95c75aee")
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 dict. 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 json
import tempfile
import os

# Create a temporary JSON file with valid config data
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 10,
    "layers": [64, 128, 256],
    "dropout": 0.5
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "json_file": json_file_path
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
logit2binary Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/postprocess.py
code served (permissive licence) · get_code("cb6b26ed872b6647")
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, 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)

# Create a small tensor of logits with shape (2, 4)
pred_contacts = torch.randn(2, 4)

ARGS = {
    "pred_contacts": pred_contacts
}
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, 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
process_config Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/config.py
code served (permissive licence) · get_code("57d3d5717cefa038")
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 Munch. 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 json
import munch
import tempfile
import os

# Create a temporary JSON file with test configuration
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "model": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "test": {
        "test_metric": "accuracy",
        "test_threshold": 0.5
    }
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "jsonfile": json_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
munch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Munch — a Munch output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Munch 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
seq_encoding Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/utils.py
code served (permissive licence) · get_code("f0ecf8166e651350")
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 ndarray, ndim 2, dtype family int, shape (4, 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 numpy as np

def seq_encoding(string):
    seq_dict = {'A': np.array([1, 0, 0, 0]), 'U': np.array([0, 1, 0, 0]), 'C': np.array([0, 0, 1, 0]), 'G': np.array([0, 0, 0, 1]), 'N': np.array([0, 0, 0, 0]), 'M': np.array([1, 0, 1, 0]), 'Y': np.array([0, 1, 1, 0]), 'W': np.array([1, 0, 0, 0]), 'V': np.array([1, 0, 1, 1]), 'K': np.array([0, 1, 0, 1]), 'R': np.array([1, 0, 0, 1]), 'I': np.array([0, 0, 0, 0]), 'X': np.array([0, 0, 0, 0]), 'S': np.array([0, 0, 1, 1]), 'D': np.array([1, 1, 0, 1]), 'P': np.array([0, 0, 0, 0]), 'B': np.array([0, 1, 1, 1]), 'H': np.array([1, 1, 1, 0])}
    str_list = list(string)
    encoding = list(map(lambda x: seq_dict[x], str_list))
    return np.stack(encoding, axis=0)

ARGS = {
    'string': 'AUGC'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 4) — shape (4, 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
soft_sign Ran
ran on a synthesized input
ml4bio/e2efold/e2efold/common/utils.py
code served (permissive licence) · get_code("450a5b4a33ce4abf")
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, 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)

x = torch.randn(2, 4)
k = 2.0

ARGS = {
    "x": x,
    "k": k,
}
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, 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
load_seq Not yet run
unverified (harvested, no recorded run)
ml4bio/e2efold/e2efold_productive/e2efold_productive_long.py
code served (permissive licence) · get_code("a404ff88fb29c75d")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 2 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 9 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
get_activation 4 other papers
4 later
2103.03000 (2021-03)
SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
2305.19435 (2023-05)
AdANNS: A Framework for Adaptive Semantic Search
2311.05808 (2023-11)
Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction
and 1 more not named here
get_config_from_json 1 other paper
1 dated earlier
1607.08022 (2016-07)
Instance Normalization: The Missing Ingredient for Fast Stylization

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

In this paper, we propose an end-to-end deep learning model, called E2Efold, for RNA secondary structure prediction which can effectively take into account the inherent constraints in the problem. The key idea of E2Efold is to directly predict the RNA base-pairing matrix, and use an unrolled algorithm for constrained programming as the template for deep architectures to enforce constraints. With comprehensive experiments on benchmark datasets, we demonstrate the superior performance of E2Efold: it predicts significantly better structures compared to previous SOTA (especially for pseudoknotted structures), while being as efficient as the fastest algorithms in terms of inference time.

For agents

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

get_harvested_code_for_paper("2002.05810")
get_code_for_paper("2002.05810")
have("2002.05810")

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

curl https://syntology.ai/api/ran/2002.05810.json

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

[![Syntology run record](https://syntology.ai/api/ran/2002.05810.svg)](https://syntology.ai/paper/2002.05810)

Connect an agent — have() is free.