-
Notifications
You must be signed in to change notification settings - Fork 0
CXF-233: publish the Tier-1 E2E control-group baseline.json (6-run matrix) #18
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,182 @@ | ||
| { | ||
| "schema_version": 1, | ||
|
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 🟡 Suggestion: This file becomes a committed contract artifact that a future CI gate will consume, but nothing validates it — |
||
| "generated_at": "2026-09-05T01:50:55.103Z", | ||
| "model": "together/deepseek-ai/DeepSeek-V4-Flash-0731", | ||
| "reasoning_effort": "high", | ||
| "scenarios": [ | ||
| "tier1-directory", | ||
| "tier1-directory-guide-only" | ||
| ], | ||
|
Comment on lines
+6
to
+9
Contributor
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 🟡 Suggestion: |
||
| "modes": { | ||
| "guide-only": { | ||
| "run_ids": [ | ||
| "evals-tier1-directory-guide-only-20260905-000901-207", | ||
| "evals-tier1-directory-guide-only-20260905-012128-950", | ||
| "evals-tier1-directory-guide-only-20260905-015055-103" | ||
| ], | ||
| "runs": 3, | ||
| "passes": 0, | ||
| "pass_rate": 0, | ||
| "pass_at_3": 0, | ||
| "first_pass_rate_mean": 0.6111111111111112, | ||
| "per_stage": { | ||
| "S0": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 1 | ||
| }, | ||
| "S1": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S2": { | ||
| "runs": 3, | ||
| "failures": 3, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S3": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S4": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 1 | ||
| }, | ||
| "S5": { | ||
| "runs": 3, | ||
| "failures": 2, | ||
| "first_pass_failures": 2 | ||
| }, | ||
| "S6": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S7": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S8": { | ||
| "runs": 3, | ||
| "failures": 3, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S9": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S10": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 1 | ||
| }, | ||
| "S11": { | ||
| "runs": 3, | ||
| "failures": 3, | ||
| "first_pass_failures": 3 | ||
| } | ||
| } | ||
| }, | ||
| "none": { | ||
| "run_ids": [ | ||
| "evals-tier1-directory-20260904-204206-352", | ||
| "evals-tier1-directory-20260904-221013-308", | ||
| "evals-tier1-directory-20260904-231553-272" | ||
| ], | ||
| "runs": 3, | ||
| "passes": 0, | ||
| "pass_rate": 0, | ||
| "pass_at_3": 0, | ||
| "first_pass_rate_mean": 0.47222222222222227, | ||
| "per_stage": { | ||
| "S0": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 1 | ||
| }, | ||
| "S1": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S2": { | ||
| "runs": 3, | ||
| "failures": 3, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S3": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 2 | ||
| }, | ||
| "S4": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S5": { | ||
| "runs": 3, | ||
| "failures": 2, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S6": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S7": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S8": { | ||
| "runs": 3, | ||
| "failures": 3, | ||
| "first_pass_failures": 3 | ||
| }, | ||
| "S9": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 0 | ||
| }, | ||
| "S10": { | ||
| "runs": 3, | ||
| "failures": 0, | ||
| "first_pass_failures": 2 | ||
| }, | ||
| "S11": { | ||
| "runs": 3, | ||
| "failures": 2, | ||
| "first_pass_failures": 2 | ||
| } | ||
| } | ||
| } | ||
| }, | ||
| "pareto": [ | ||
| { | ||
| "stage": "S2", | ||
| "failures": 6, | ||
| "share": 0.2857142857142857 | ||
| }, | ||
| { | ||
| "stage": "S8", | ||
| "failures": 6, | ||
| "share": 0.2857142857142857 | ||
| }, | ||
| { | ||
| "stage": "S11", | ||
| "failures": 5, | ||
| "share": 0.23809523809523808 | ||
| }, | ||
| { | ||
| "stage": "S5", | ||
| "failures": 4, | ||
| "share": 0.19047619047619047 | ||
| } | ||
| ] | ||
| } | ||
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🟡 Suggestion: The regression-gate contract above (lines 231–235) still says the gate "fails if the measured pass rate drops below
modes.<mode>.pass_rate", but the published reference haspass_rate: 0for both arms — that rule can never fire, so the committed contract is a no-op gate. This paragraph itself explains why the full-funnel floor is partly structural (S2's PUT leg is unobservable, S8 reads secret-masked); the consumption rule should be updated in the same PR to key onfirst_pass_rate_meanand/orper_stage.failures, or to state explicitly thatpass_rategating is inert until S2/S8 are instrumented. (confidence: high)