Back to Report Blocks

AcceptanceRateTimeline

Trend
Report block

Tracks score-result acceptance rate over time for stakeholder-friendly monitoring.

What It Answers

  • Are reviewers accepting more AI decisions over time?
  • Did acceptance improve after a score release?
  • Which periods had weak acceptance?

Use When

  • Reporting product progress.
  • Monitoring high-level reviewer trust.
  • Comparing before/after release windows.

Avoid When

  • You need confusion matrix detail; use FeedbackAlignment.
  • You need per-topic failure modes; use FeedbackContradictions.

Run From The CLI

Direct report commands are the simplest path for one-off usage. Saved report configurations use `plexus report config create` and `plexus report run`.

plexus feedback report acceptance-rate-timeline \
  --scorecard "Customer Service QA" \
  --score "Medication Review: Dosage" \
  --bucket-type calendar_week \
  --bucket-count 6
plexus report config create --name "AcceptanceRateTimeline Example" --file acceptance-rate-timeline.md
plexus report run --config "AcceptanceRateTimeline Example"

Minimal Configuration

class: AcceptanceRateTimeline
scorecard: "Customer Service QA"
score: "Medication Review: Dosage"
bucket_type: calendar_week
bucket_count: 6

Live Rendered Example

Rendered with the same dashboard component used by generated reports.

AcceptanceRateTimeline Example

Score-result acceptance over complete historical buckets

Score-Result Acceptance Rate
86.00%
Accepted Score Results
344 / 400
Feedback Edits
88
Valid: 84
Value changed: 56
Score Results With Feedback
400
Scorecard: Customer Service QA • Score: Medication Review: Dosage • Buckets: calendar_week • Feedback edits: 84/88 • Value-changing edits: 56
Bucket Metrics
BucketWindowAcceptanceAccepted / TotalCorrectedFeedback (valid/total)Value Changed
Mar 23/2/2026 - 3/9/202682.00%82 / 1001819/2018
Mar 93/9/2026 - 3/16/202685.00%81 / 951422/2214
Mar 163/16/2026 - 3/23/202687.60%92 / 1051321/2313
Mar 233/23/2026 - 3/30/202689.00%89 / 1001122/2311

How To Interpret It

  • This is good for trend communication, but it does not explain which class is wrong.
  • Compare with feedback volume before claiming a meaningful improvement.