Hierarchical occlusion saliency engine#3
Merged
Merged
Conversation
- SaliencyEngine: two-pass hierarchical occlusion (segment then sentence level) with logprob-drop scoring and binary fallback - Core types: Segment, SaliencyScore, SaliencyResult - 41 unit tests, all passing, no network calls - CI: code_checks and unit_tests workflows, pre-commit config - pyproject.toml: full ruff/mypy/pytest/uv setup matching helix conventions - DESIGN.md: updated to reflect actual architecture and drop structured reasoning - README and working example script
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
SaliencyEngine: two-pass hierarchical occlusion that masks input context segments, re-runs the agent's decision call, and scores each segment by the drop in log-probability of the original decisionSegment,SaliencyScore,SaliencyResultTest plan
uv run pytest tests/)examples/demo_saliency.pyagainst the Vector proxy to verify end-to-end output