citecheck: address v2 audit findings (WILDS placement + Bayesian-adaptation citation)#98
Merged
Conversation
WILDS (2012.07421) is a distribution-shift benchmark, not an uncertainty-quantification method. Move it to the distributional-shift sentence alongside HELM, and cite genuine UQ references on the UQ-methods sentence: Deep Ensembles (1612.01474) and a conformal prediction introduction (2107.07511). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
The "Bayesian rules activate test-time updates only when uncertainty is manageable" claim cited an unsupervised anomaly-detection TTA paper (2410.03306) with no Bayesian or uncertainty-gating content. Replace with BACS, "Training on Test Data with Bayesian Adaptation for Covariate Shift" (2109.12746, Zhou and Levine), a Bayesian test-time adaptation method that ties adaptation to calibrated uncertainty under distribution shift. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
cnellington
changed the title
github-actions Bot
pushed a commit
that referenced
this pull request
Jul 15, 2026
[ci skip] This build is based on c423711. This commit was created by the following CI build and job: https://github.com/AdaptInfer/context-review/commit/c423711f8f8c7650fb5b5db8586c4ad9fa2052d1/checks https://github.com/AdaptInfer/context-review/actions/runs/29394184628
github-actions Bot
pushed a commit
that referenced
this pull request
Jul 15, 2026
[ci skip] This build is based on c423711. This commit was created by the following CI build and job: https://github.com/AdaptInfer/context-review/commit/c423711f8f8c7650fb5b5db8586c4ad9fa2052d1/checks https://github.com/AdaptInfer/context-review/actions/runs/29394184628
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to the merged citecheck audit PR #97, applying the findings from the v2 re-audit. Two citation fixes:
future_trends (12.future_trends.md:44) — WILDS (arXiv:2012.07421) is a distribution-shift benchmark, not a UQ method, but it was cited on the deep-ensembles / Bayesian-ensembling / conformal-prediction sentence. Moved WILDS to the distributional-shift sentence (alongside HELM) and cited genuine UQ references on the UQ-methods sentence: Deep Ensembles (arXiv:1612.01474) and a conformal-prediction introduction (arXiv:2107.07511).
principles (05.principles.md:28) — the 'Bayesian rules activate test-time updates only when uncertainty is manageable' claim cited an unsupervised anomaly-detection TTA paper (arXiv:2410.03306) with no Bayesian or uncertainty-gating content. Replaced with BACS, 'Training on Test Data with Bayesian Adaptation for Covariate Shift' (arXiv:2109.12746, Zhou and Levine), a Bayesian test-time adaptation method that ties adaptation to calibrated uncertainty.
All replacement identifiers were resolved and verified against their titles/abstracts. Both were pre-existing issues, not introduced by PR #97.
Generated with Claude Code.