SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.12238 · 2023

Improving Adaptive Conformal Prediction Using Self-Supervised Learning

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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 7 have no contract verdict; 0 failures of our instrument; 2 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/2302.12238.json · badge: /api/ran/2302.12238.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
seedatnabeel/sscp canonical (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_excess Ran
ran on a synthesized input
seedatnabeel/sscp/src/utils.py
code served (permissive licence) · get_code("d390a6edd3379382")
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, 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 numpy as np

# Create small test arrays
# true values should be between lb and ub for some entries
true = np.array([5.0, 10.0, 15.0, 20.0])
lb = np.array([3.0, 8.0, 12.0, 18.0])
ub = np.array([7.0, 12.0, 18.0, 22.0])

ARGS = {
    "lb": lb,
    "ub": ub,
    "true": true,
}
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 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
compute_interval_metrics Ran
ran on a synthesized input
seedatnabeel/sscp/src/utils.py
code served (permissive licence) · get_code("6be3f50cecdae342")
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, 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 numpy as np

# Analyze the function:
# - lower_bound: float - scalar value for lower confidence interval bound
# - upper_bound: float - scalar value for upper confidence interval bound
# - y_true: float - used with np.sum, len(), and np.mean() - should be numpy array or array-like
#
# The function expects:
# - lower_bound and upper_bound to be scalars (floats)
# - y_true to be array-like (numpy array) that supports >= and <= comparisons
# - Operations: np.sum with boolean indexing, len(y_true), np.mean(abs(...))

np.random.seed(0)

# Create small sample data
y_true = np.array([1.5, 2.3, 3.1, 4.2, 5.0, 6.5])

# Define confidence interval bounds
lower_bound = 2.0
upper_bound = 5.5

ARGS = {
    "lower_bound": lower_bound,
    "upper_bound": upper_bound,
    "y_true": y_true,
}
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 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
logit Ran
ran on a synthesized input
seedatnabeel/sscp/src/VIME/supervised_models.py
code served (permissive licence) · get_code("c3a4797422393459")
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 float, shape (3, 2) 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
from sklearn.linear_model import LogisticRegression

def convert_matrix_to_vector(y):
    """Helper function to convert matrix to vector if needed."""
    if len(y.shape) > 1:
        return y.ravel()
    return y

# Create small sample data
np.random.seed(0)

# x_train: 2 samples, 4 features
x_train = np.random.randn(2, 4).astype(np.float32)

# y_train: 2 labels (binary classification) - as a 1D vector
y_train = np.array([0, 1], dtype=np.int32)

# x_test: 3 samples, 4 features
x_test = np.random.randn(3, 4).astype(np.float32)

ARGS = {
    "x_train": x_train,
    "y_train": y_train,
    "x_test": x_test,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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 float, shape (3, 2) — shape (3, 2) 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
mlp Ran
ran on a synthesized input
seedatnabeel/sscp/src/VIME/supervised_models.py
code served (permissive licence) · get_code("5785647801cd5536")
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 float, shape (5, 3) 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 convert_vector_to_matrix(y):
    """Convert 1D vector to 2D matrix."""
    return y.reshape(-1, 1)

# Set random seed for reproducibility
np.random.seed(0)

# Create small synthetic datasets
n_train_samples = 20
n_test_samples = 5
n_features = 4
n_classes = 3

# Training data
x_train = np.random.randn(n_train_samples, n_features).astype(np.float32)
y_train = np.random.randint(0, n_classes, n_train_samples)
# Convert to one-hot encoding for categorical_crossentropy
y_train_onehot = np.eye(n_classes)[y_train].astype(np.float32)

# Test data
x_test = np.random.randn(n_test_samples, n_features).astype(np.float32)

# Parameters dictionary
parameters = {
    'hidden_dim': 8,
    'epochs': 5,
    'activation': 'relu',
    'batch_size': 4
}

ARGS = {
    'x_train': x_train,
    'y_train': y_train_onehot,
    'x_test': x_test,
    'parameters': parameters
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
keras, 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 float, shape (5, 3) — shape (5, 3) 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_data Ran
ran on a synthesized input
seedatnabeel/sscp/src/datasets.py
code served (permissive licence) · get_code("d1b636d4bc9cad39")
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 numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Create small synthetic dataset
np.random.seed(42)
n_samples = 100
n_features = 4

X = np.random.randn(n_samples, n_features).astype(np.float32)
y = np.random.randn(n_samples, 1).astype(np.float32)

seed = 0

ARGS = {
    "X": X,
    "y": y,
    "seed": seed,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sklearn — 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
read_from_file Ran
ran on a synthesized input
seedatnabeel/sscp/src/utils.py
code served (permissive licence) · get_code("5ac99cb584fbcf71")
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 pickle
import tempfile
import os

# Create a temporary pickle file with some test data
test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "dict"}
}

# Create a temporary directory and file
temp_dir = tempfile.gettempdir()
temp_filename = os.path.join(temp_dir, "test_pickle_file.pkl")

# Write the test data to a pickle file
with open(temp_filename, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    "filename": temp_filename
}
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
xgb_model Ran
ran on a synthesized input
seedatnabeel/sscp/src/VIME/supervised_models.py
code served (permissive licence) · get_code("fe7fea7d2654c9a6")
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 float, shape (3, 2) 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
import xgboost as xgb

def convert_matrix_to_vector(y):
    """Helper function that converts matrix to vector if needed"""
    if len(y.shape) > 1:
        return y.ravel()
    return y

# Create small training dataset
np.random.seed(0)
x_train = np.random.randn(8, 4).astype(np.float32)
y_train = np.random.randint(0, 2, size=(8,)).astype(np.int32)

# Create small test dataset
x_test = np.random.randn(3, 4).astype(np.float32)

ARGS = {
    "x_train": x_train,
    "y_train": y_train,
    "x_test": x_test,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, xgboost — 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 float, shape (3, 2) — shape (3, 2) 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
GetDataset Not yet run
unverified (harvested, no recorded run)
seedatnabeel/sscp/src/datasets.py
code served (permissive licence) · get_code("4eceac6d8e1b7e65")
How it ran

no invocation recorded.

load_mnist_data Not yet run
unverified (harvested, no recorded run)
seedatnabeel/sscp/src/VIME/data_loader.py
code served (permissive licence) · get_code("8903c23dbfd22bb7")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 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.

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

Conformal prediction is a powerful distribution-free tool for uncertainty quantification, establishing valid prediction intervals with finite-sample guarantees. To produce valid intervals which are also adaptive to the difficulty of each instance, a common approach is to compute normalized nonconformity scores on a separate calibration set. Self-supervised learning has been effectively utilized in many domains to learn general representations for downstream predictors. However, the use of self-supervision beyond model pretraining and representation learning has been largely unexplored. In this work, we investigate how self-supervised pretext tasks can improve the quality of the conformal regressors, specifically by improving the adaptability of conformal intervals. We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.

For agents

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

get_harvested_code_for_paper("2302.12238")
get_code_for_paper("2302.12238")
have("2302.12238")

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

curl https://syntology.ai/api/ran/2302.12238.json

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

[![Syntology run record](https://syntology.ai/api/ran/2302.12238.svg)](https://syntology.ai/paper/2302.12238)

Connect an agent — have() is free.