Pith. sign in

REVIEW 3 cited by

Understanding Softmax Confidence and Uncertainty

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2106.04972 v1 pith:JTKV2QPT submitted 2021-06-09 cs.LG cs.AIstat.ML

classification cs.LGcs.AIstat.ML
keywords confidencesoftmaxuncertaintynetworksdatafailoverlaptraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

It is often remarked that neural networks fail to increase their uncertainty when predicting on data far from the training distribution. Yet naively using softmax confidence as a proxy for uncertainty achieves modest success in tasks exclusively testing for this, e.g., out-of-distribution (OOD) detection. This paper investigates this contradiction, identifying two implicit biases that do encourage softmax confidence to correlate with epistemic uncertainty: 1) Approximately optimal decision boundary structure, and 2) Filtering effects of deep networks. It describes why low-dimensional intuitions about softmax confidence are misleading. Diagnostic experiments quantify reasons softmax confidence can fail, finding that extrapolations are less to blame than overlap between training and OOD data in final-layer representations. Pre-trained/fine-tuned networks reduce this overlap.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 47 citations worldwide. Full citation record

  1. Imputation-free transformer learning enables robust Alzheimer's disease prediction and calibrated uncertainty quantification across heterogeneous clinical cohorts

    q-bio.NC 2026-07 conditional novelty 6.0 of 10

    An imputation-free transformer with masked and intersample attention predicts Alzheimer’s status and scores across cohorts with better calibration than tree ensembles.

  2. TRUST: Test-time Resource Utilization for Superior Trustworthiness

    cs.LG 2025-06 conditional novelty 5.0 of 10

    TRUST computes confidence as the angular distance between a test image and a slightly modified, maximally-confident version of it, and claims this ranks predictions monotonically.

  3. Recursive Offloading for LLM Serving in Multi-tier Networks

    cs.DC 2025-05 conditional novelty 5.0 of 10

    RecServe routes LLM requests across device, edge, and cloud using adaptive confidence thresholds based on recent history, cutting communication by over 50% versus cloud-only serving while keeping quality close to cloud-level.

Pith tools