Papers › A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks

7 Oct 2016arXiv:1610.02136archive 2025-07-28

Dan Hendrycks, Kevin Gimpel

We consider the two related problems of detecting if an example is misclassified or out-of-distribution. We present a simple baseline that utilizes probabilities from softmax distributions. Correctly classified examples tend to have greater maximum softmax probabilities than erroneously classified and out-of-distribution examples, allowing for their detection. We assess performance by defining several tasks in computer vision, natural language processing, and automatic speech recognition, showing the effectiveness of this baseline across all. We then show the baseline can sometimes be surpassed, demonstrating the room for future research on these underexplored detection tasks.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1610.02136")

Code

Syntology Ran 7 of 21 code samples harvested from 7 repositories linked to this paper; 14 have no recorded run. Of those that ran: 4 ran · honoured contract; 3 ran · our draft was wrong.

By repository: official repository: 14 samples from 1 repository, 0 ran; community (archive-listed): 7 samples from 6 repositories, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

14 repositories listed; official and paper-mentioned ones first.

hendrycks/error-detection officialmentioned in papermentioned on GitHubtfMIT report
2sang/OOD-baseline mentioned on GitHubtf report
drumpt/RotNet-OOD mentioned on GitHubpytorch report
guyAmit/GLOD mentioned on GitHubpytorch report
kingjamessong/rankfeat mentioned on GitHubpytorch report
lancopku/avg-avg mentioned on GitHubpytorchMIT report
oliverzhang42/ood_medical_images mentioned on GitHubpytorch report
sooonwoo/RotNet-OOD mentioned on GitHubpytorch report
thuiar/textoir mentioned on GitHubpytorchMIT report
thuiar/textoir-demo mentioned on GitHubpytorchGPL-3.0 report
zjysteven/mixoe mentioned on GitHubpytorch 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

21 samples harvested; 7 ran; 4 honoured the contract we drafted; 14 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

4ran · honoured contract
3ran · our draft was wrong
14unverified

Licence: 6 of the 21 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 7 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

clipped_gelu hendrycks/error-detection/ASR/CTC/CTC_eval.py official repository unverified MIT (permissive) · e70a9b1d04bacb16 · report
data_lists_to_batches hendrycks/error-detection/ASR/CTC/utils.py official repository unverified MIT (permissive) · 5f1003adf845195e · report
data_to_mat hendrycks/error-detection/Appendix_B_Cautious_Classification/POS/helper_functions_twitter.py official repository unverified MIT (permissive) · 70ffbe91cbb5596b · report
embeddings_to_dict hendrycks/error-detection/Appendix_B_Cautious_Classification/POS/helper_functions_twitter.py official repository unverified MIT (permissive) · 7d646d3612cadf34 · report
load_batch hendrycks/error-detection/Vision/load_cifar10.py official repository unverified MIT (permissive) · 8633f606824fb007 · report
load_batch hendrycks/error-detection/Vision/load_cifar100.py official repository unverified MIT (permissive) · 4e5831192b762838 · report
load_batched_data hendrycks/error-detection/ASR/CTC/utils.py official repository unverified MIT (permissive) · 201106667cf3cb5c · report
load_data10 hendrycks/error-detection/Vision/load_cifar10.py official repository unverified MIT (permissive) · 9db68167799bea76 · report
load_data100 hendrycks/error-detection/Vision/load_cifar100.py official repository unverified MIT (permissive) · 634643388318c5b7 · report
softmax hendrycks/error-detection/ASR/CTC/CTC_eval.py official repository unverified MIT (permissive) · f3dea44d35e56a40 · report
target_list_to_sparse_tensor hendrycks/error-detection/ASR/CTC/utils.py official repository unverified MIT (permissive) · 907b6771b97cb718 · report
to_categorical hendrycks/error-detection/Vision/load_cifar10.py official repository unverified MIT (permissive) · 70f5b5175a23f59d · report
unpickle hendrycks/error-detection/Vision/CIFAR_Detection.py official repository unverified MIT (permissive) · 9cf114efaf65dc13 · report
word_list_to_embedding hendrycks/error-detection/Appendix_B_Cautious_Classification/POS/helper_functions_twitter.py official repository unverified MIT (permissive) · c08d1e05487f7323 · report
entropy_from_distribution 2sang/OOD-baseline/exp_util.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 2ae461db08765c9b · report
entropy_stats 2sang/OOD-baseline/exp_util.py community (archive-listed) ran · our draft was wrong fingerprinted no licence file found · pointer only · 72903b57f29a3ee1 · report
get_Mahalanobis_score kingjamessong/rankfeat/utils/mahalanobis_lib.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · d2b7861b22672799 · report
get_base_score lancopku/avg-avg/lib/inference/base.py community (archive-listed) ran · honoured contract MIT (permissive) · d47e87d197d79e74 · report
get_confidence_baseline oliverzhang42/ood_medical_images/src/utils.py community (archive-listed) ran · our draft was wrong no licence file found · pointer only · 0d73cb6aa8f3382b · report
predict_llr guyAmit/GLOD/FOOD/Gaussain_layer.py community (archive-listed) ran · honoured contract no licence file found · pointer only · 0222c378f0e6e52e · report
softmax kobybibas/pnml_ood_detection/src/score_utils.py community (archive-listed) ran · honoured contract fingerprinted no licence file found · pointer only · 7ddc824e88e78020 · report

Tasks

Anomaly DetectionAutomatic Speech RecognitionAutomatic Speech Recognition (ASR)Out-of-Distribution DetectionSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 (MSP Baseline) AUPR 55.8 #13 of 14 Archive leaderboard report
Out-of-Distribution Detection CIFAR-10 vs CIFAR-100 WRN 40-2 (MSP Baseline) AUROC 87.9 #13 of 14 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual ConnectionSoftmax

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