SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.12800 · ICLR · 2021

Calibration of Neural Networks using Splines

Amir Rahimi, Richard Hartley, Thalaiyasingam Ajanthan, Kartik Gupta, Thomas Mensink, Cristian Sminchisescu

arXiv · PDF · Open in the Atlas

Code that ran

1 of 4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 0 failures of our instrument; 3 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/2006.12800.json · badge: /api/ran/2006.12800.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
kartikgupta-at-anu/spline-calibration canonical (classifier label)
classifier basis: classifier_2025
1 ran · 3 no recorded run
FunctionStatusWhere it lives
ensure_numpy Ran
ran, honoured the contract we drafted
kartikgupta-at-anu/spline-calibration/recalibrate.py
code served (permissive licence) · get_code("2bd69793c2565f55")
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 ndarray, 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
import numpy as np

torch.manual_seed(0)

# The function ensure_numpy takes one parameter 'a' and checks if it's a numpy array.
# If not, it calls .numpy() on it (so it expects a torch tensor).
# We need to provide both cases as test values.

# Case 1: numpy array (already numpy)
numpy_array = np.array([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=np.float32)

# Case 2: torch tensor (will be converted to numpy)
torch_tensor = torch.randn(2, 4)

# We'll test with the torch tensor case since that exercises the .numpy() path
ARGS = {
    "a": torch_tensor
}
Setup block drafted by
a language model, Claude Haiku 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 ndarray, 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
first_above Not yet run
unverified (harvested, no recorded run)
kartikgupta-at-anu/spline-calibration/recalibrate.py
code served (permissive licence) · get_code("6e568fe936bc7131")
How it ran

no invocation recorded.

get_recalibration_function Not yet run
unverified (harvested, no recorded run)
kartikgupta-at-anu/spline-calibration/recalibrate.py
code served (permissive licence) · get_code("1dd42ccce10f052e")
How it ran

no invocation recorded.

interpolated_function Not yet run
unverified (harvested, no recorded run)
kartikgupta-at-anu/spline-calibration/recalibrate.py
code served (permissive licence) · get_code("e9108e0765233758")
How it ran

no invocation recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 3 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
ensure_numpy
brick of this paper's assembly: helper
2 other papers
2 later
2401.02718 (2024-01)
Calibration Attacks: A Comprehensive Study of Adversarial Attacks on Model Confidence
2404.13016 (2024-04)
Optimizing Calibration by Gaining Aware of Prediction Correctness

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

Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities. Measuring calibration error amounts to comparing two empirical distributions. In this work, we introduce a binning-free calibration measure inspired by the classical Kolmogorov-Smirnov (KS) statistical test in which the main idea is to compare the respective cumulative probability distributions. From this, by approximating the empirical cumulative distribution using a differentiable function via splines, we obtain a recalibration function, which maps the network outputs to actual (calibrated) class assignment probabilities. The spline-fitting is performed using a held-out calibration set and the obtained recalibration function is evaluated on an unseen test set. We tested our method against existing calibration approaches on various image classification datasets and our spline-based recalibration approach consistently outperforms existing methods on KS error as well as other commonly used calibration measures.

For agents

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

get_harvested_code_for_paper("2006.12800")
get_code_for_paper("2006.12800")
have("2006.12800")

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

curl https://syntology.ai/api/ran/2006.12800.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.12800.svg)](https://syntology.ai/paper/2006.12800)

Connect an agent — have() is free.