Papers › Optimizing Calibration by Gaining Aware of Prediction Correctness

Optimizing Calibration by Gaining Aware of Prediction Correctness

19 Apr 2024arXiv:2404.13016archive 2025-07-28

Yuchi Liu, Lei Wang, Yuli Zou, James Zou, Liang Zheng

Model calibration aims to align confidence with prediction correctness. The Cross-Entropy (CE) loss is widely used for calibrator training, which enforces the model to increase confidence on the ground truth class. However, we find the CE loss has intrinsic limitations. For example, for a narrow misclassification, a calibrator trained by the CE loss often produces high confidence on the wrongly predicted class (e.g., a test sample is wrongly classified and its softmax score on the ground truth class is around 0.4), which is undesirable. In this paper, we propose a new post-hoc calibration objective derived from the aim of calibration. Intuitively, the proposed objective function asks that the calibrator decrease model confidence on wrongly predicted samples and increase confidence on correctly predicted samples. Because a sample itself has insufficient ability to indicate correctness, we use its transformed versions (e.g., rotated, greyscaled and color-jittered) during calibrator training. Trained on an in-distribution validation set and tested with isolated, individual test samples, our method achieves competitive calibration performance on both in-distribution and out-of-distribution test sets compared with the state of the art. Further, our analysis points out the difference between our method and commonly used objectives such as CE loss and mean square error loss, where the latters sometimes deviates from the calibration aim.

PaperPDFCodeCode Syntology ran

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 7 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 7 samples from 1 repository, 7 ran (6 with no instrument failure; 1 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.

liuyvchi/correctness-aware-calibration officialmentioned in papermentioned on GitHubpytorchSyntology: 7 samples, 7 ran (1 instrument-failed) · 0 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

7 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · violated contract
1ran · our draft was wrong
3ran

Licence: 7 of the 7 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 liuyvchi/correctness-aware-calibration. “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.

liuyvchi/correctness-aware-calibration official repository 7 samples, 7 ran (1 instrument-failed) · 0 unverified
AUs_dropout src/dataset.py ran no licence file found · pointer only · 287eaf9aa611ce22 · report fixture: signature ganimation_model:callable/0/?, imgs:Tensor/2/float · returned Tensor · level recorded 2026-09-24
AdaptiveECE src/cal_metrics/all_metrics.py ran no licence file found · pointer only · e0fd1257cf92181b · report fixture: signature conf:ndarray/1/float, correctness:ndarray/1/int, conf_bin_num:int/0/int · returned float64 · level recorded 2026-09-24
KS_error_from_conf_acc src/cal_metrics/all_metrics.py ran · violated contract no licence file found · pointer only · cac3e3bf547db5b2 · report fixture: signature confidences:Tensor/1/float, accuracies:Tensor/1/float · returned float32 · level recorded 2026-09-24
brier_score in 6 papers src/cal_metrics/BS.py ran · violated contract fingerprinted no licence file found · pointer only · 0738ab13a0a3dd82 · report fixture: signature y_pred:ndarray/1/float, y:ndarray/1/int · returned float · level recorded 2026-09-24
ensure_numpy src/cal_metrics/KS.py ran · honoured contract no licence file found · pointer only · 2bd69793c2565f55 · report fixture: signature a:Tensor/2/float · returned ndarray · level recorded 2026-09-22
get_ImageNetV2 src/dataset.py ran · our draft was wrong no licence file found · pointer only · 97c635174ecd1160 · report fixture: signature dataset_folder:str/0/str, transform:callable/0/? · returned ImageFolder · level recorded 2026-09-24
top1_brier_score src/cal_metrics/BS.py ran fingerprinted no licence file found · pointer only · ae9913063b8b19f9 · report fixture: signature score:ndarray/1/float, acc:ndarray/1/int · returned float64 · level recorded 2026-09-24

Tasks

Prediction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNSETSoftmax

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