Repository navigation
fix(bell): reindex censored_mask to leaf order in dynamic-censoring path - #10
Merged
Merged
Conversation
optimize_order() permutes leaves by uncensored-leaf count, but the dynamic-censoring path indexed the caller-supplied censored_mask by leaf position while the mask arrives in obs (dimension) order. Nested models with heterogeneous panel sizes AND a censored leaf therefore flagged the WRONG leaves as censored, producing incorrect nested log-densities. Homogeneous panels were unaffected (optimize_order is identity there), which is why this escaped earlier tests. Add _mask_to_leaf_order() and reindex the mask at both Bell entry points, mirroring the obs gather in _marginal_transforms_chunked. Validated against an independent mpmath ground truth. Adds tests/test_nested_censoring_heteropanel.py (panels [3,4]/[2,4]/[2,2,3] + uncensored control) — fails before, passes after (5/5). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
optimize_order() permutes leaves by uncensored-leaf count, but the dynamic-censoring path indexed the caller-supplied censored_mask by leaf position while the mask arrives in obs (dimension) order. Nested models with heterogeneous panel sizes AND a censored leaf therefore flagged the WRONG leaves as censored, producing incorrect nested log-densities. Homogeneous panels were unaffected (optimize_order is identity there), which is why this escaped earlier tests.
Add _mask_to_leaf_order() and reindex the mask at both Bell entry points, mirroring the obs gather in _marginal_transforms_chunked.
Validated against an independent mpmath ground truth. Adds tests/test_nested_censoring_heteropanel.py (panels [3,4]/[2,4]/[2,2,3] + uncensored control) — fails before, passes after (5/5).