Papers › A Consistent and Differentiable Lp Canonical Calibration Error Estimator

A Consistent and Differentiable Lp Canonical Calibration Error Estimator

13 Oct 2022arXiv:2210.07810archive 2025-07-28

Teodora Popordanoska, Raphael Sayer, Matthew B. Blaschko

Calibrated probabilistic classifiers are models whose predicted probabilities can directly be interpreted as uncertainty estimates. It has been shown recently that deep neural networks are poorly calibrated and tend to output overconfident predictions. As a remedy, we propose a low-bias, trainable calibration error estimator based on Dirichlet kernel density estimates, which asymptotically converges to the true Lₚ calibration error. This novel estimator enables us to tackle the strongest notion of multiclass calibration, called canonical (or distribution) calibration, while other common calibration methods are tractable only for top-label and marginal calibration. The computational complexity of our estimator is 𝒪(n²), the convergence rate is 𝒪(n^(-1/2)), and it is unbiased up to 𝒪(n⁻²), achieved by a geometric series debiasing scheme. In practice, this means that the estimator can be applied to small subsets of data, enabling efficient estimation and mini-batch updates. The proposed method has a natural choice of kernel, and can be used to generate consistent estimates of other quantities based on conditional expectation, such as the sharpness of a probabilistic classifier. Empirical results validate the correctness of our estimator, and demonstrate its utility in canonical calibration error estimation and calibration error regularized risk minimization.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 16 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. Where Syntology's instrument failed: 8 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 10 ran (0 with no instrument failure; 10 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 10 samples that ran have no recorded date.

tpopordanoska/ece-kde officialmentioned in papermentioned on GitHubpytorchSyntology: 16 samples, 10 ran (10 instrument-failed) · 6 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 10 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Every run on this page is a failure of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

8ran · our draft was wrong
2ran; the contract check could not run
6unverified

Licence: 0 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from tpopordanoska/ece-kde. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

tpopordanoska/ece-kde official repository 16 samples, 10 ran (10 instrument-failed) · 6 unverified
dirichlet_kernel ece_kde.py ran · our draft was wrong fingerprinted MIT (permissive) · 9bc246bd29ace132 · report fixture: signature z:Tensor/2/float, bandwidth:float/0/float · returned Tensor · level recorded 2026-09-22
get_ece_kde ece_kde.py ran · our draft was wrong MIT (permissive) · b0a9bed5ef6c4741 · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, mc_type:str/0/str, device:str/0/str · returned Tensor · level recorded, date not recorded
get_ece_kde ece_kde.py ran · our draft was wrong MIT (permissive) · 33dce314122602ee · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, mc_type:str/0/str, device:str/0/str · returned Tensor · level recorded 2026-09-22
get_kernel in 18 papers ece_kde.py ran · our draft was wrong MIT (permissive) · c78951863d26681b · report fixture: signature f:Tensor/2/float, bandwidth:float/0/float, device:device/0/? · returned Tensor · level recorded 2026-09-22
get_ratio_binary ece_kde.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 6b46daa5f7c4ef39 · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, device:device/0/? · returned Tensor · level recorded, date not recorded
get_ratio_binary ece_kde.py ran; the contract check could not run (RAISES) MIT (permissive) · 0bda15c6f233eb5e · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
get_ratio_canonical ece_kde.py ran · our draft was wrong MIT (permissive) · 1279552d0b4571d1 · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:float/0/float, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_ratio_canonical_log ece_kde.py ran · our draft was wrong MIT (permissive) · b6fec1cfc955ec72 · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, device:str/0/str · returned Tensor · level recorded 2026-09-24
get_ratio_toplabel ece_kde.py ran · our draft was wrong MIT (permissive) · b1690d11037e0673 · report fixture: signature f:Tensor/2/float, y:Tensor/1/int, bandwidth:float/0/float, p:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-24
isnan in 24 papers
census: 3 implementations from 8 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32
ece_kde.py ran · our draft was wrong fingerprinted MIT (permissive) · 75ac62b189ead8eb · report fixture: signature a:Tensor/2/float · returned Tensor · level recorded 2026-09-22
beta_kernel ece_kde.py unverified MIT (permissive) · 1229a437a6fcfedf · report
check_input ece_kde.py unverified MIT (permissive) · 5c6e3a10d18a0b2d · report
get_bandwidth ece_kde.py unverified MIT (permissive) · 8c9800fbef285941 · report
get_kde_for_ece ece_kde.py unverified MIT (permissive) · 20c0edbda0d40b3a · report
get_kde_for_ece_vect ece_kde.py unverified MIT (permissive) · 489d7eeee8368ef1 · report
get_ratio_marginal_vect ece_kde.py unverified MIT (permissive) · e3bed5deae86a699 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for L p Canonical Calibration Error Estimator (graph method: L p Canonical Calibration Error Estimator). 13 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 5 unverified. The assembly has not been run end-to-end.

  1. get_ece_kde entry · level 1 · ran · our draft was wrong · 33dce314122602ee
  2. check_input helper · level 0 · unverified · 5c6e3a10d18a0b2d
  3. get_ratio_binary helper · level 1 · ran; the contract check could not run (RAISES) · 0bda15c6f233eb5e
  4. get_ratio_canonical helper · level 1 · ran · our draft was wrong · 1279552d0b4571d1
  5. get_ratio_marginal_vect helper · level 0 · unverified · e3bed5deae86a699
  6. get_ratio_toplabel helper · level 1 · ran · our draft was wrong · b1690d11037e0673
  7. isnan helper · level 1 · ran · our draft was wrong · 75ac62b189ead8eb
  8. get_kde_for_ece metric · level 0 · unverified · 20c0edbda0d40b3a
  9. get_kernel helper · level 1 · ran · our draft was wrong · c78951863d26681b
  10. get_ratio_canonical_log helper · level 1 · ran · our draft was wrong · b6fec1cfc955ec72
  11. beta_kernel helper · level 0 · unverified · 1229a437a6fcfedf
  12. get_kde_for_ece_vect helper · level 0 · unverified · 489d7eeee8368ef1
  13. dirichlet_kernel helper · level 1 · ran · our draft was wrong · 9bc246bd29ace132

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2210.07810") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections