Skip to content

Vince/evidence source indices#935

Draft
vintrocode wants to merge 3 commits into
mainfrom
vince/evidence-source-indices
Draft

Vince/evidence source indices#935
vintrocode wants to merge 3 commits into
mainfrom
vince/evidence-source-indices

Conversation

@vintrocode

Copy link
Copy Markdown
Contributor

make the deriver indicate which messages a conclusion came from via source ids

vintrocode and others added 3 commits July 24, 2026 15:51
- Renamed 'atomic facts' to 'molecular facts'
- Added decontextuality (stranger test) instruction with enduring vs incidental descriptors
- Added minimality instruction (only enough context for interpretability)
- Removed proposition gate (redundant with d + m gradient)
- Updated examples to show molecular ideal
Each explicit observation now carries source_indices — 0-based indices
into the <messages> block pointing to the messages that directly support
the conclusion. Messages in the prompt are prefixed with [N] indices.

This enables the action-based judge's evidence entailment criterion to
slice the conversation to just the supporting messages instead of using
the full conversation as evidence context (degraded mode).

No text duplication — the LLM outputs indices (cheap, low-error), and
the judge looks up the real message text from the trace input.
- Clarify that source_indices can point at any speaker's messages,
  not just the user's — what matters is which messages contain the evidence
- Add two examples: assistant-sourced attribution and multi-message
  attribution showing question + recommendation + confirmation
- Addresses issue where deriver cited wrong messages for conclusions
  derived from assistant responses
@coderabbitai

coderabbitai Bot commented Jul 24, 2026

Copy link
Copy Markdown
Contributor

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro

Run ID: 1f6b7b60-5519-4c31-a815-4b8f0c047710

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

  • 🔍 Trigger review
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch vince/evidence-source-indices

Comment @coderabbitai help to get the list of available commands.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant