Own tickets: Store review triage (BG) v2 r2-jev
Upload 100 to 1000 of your own tickets. Emails, phone numbers, IBANs, card numbers and long digit runs are masked on this server before anything is stored or sent to Claude. Claude labels each ticket twice; you review the labels, freeze the set, and the base model and the served adapter are scored on it.
Status
- Tickets
- 0
- Labelled
- 0
- Unstable
- 0
- Not judged yet
- 0
- Dropped
- 0
Judge usage: 0 requests, 0 input and 0 output tokens.
Own tickets
533 of the shop's own tickets, masked and frozen as a separate slice. They came with labels made by people: the dataset authors Georgieva-Trifonova, Stefanova and Kalchev (Harvard Dataverse, doi:10.7910/DVN/TXIK9P, CC BY 4.0): the 182 test reviews of the MTEB release plus the 351 reviews of the check half of its train split. Neither the judge nor Chirak changed them. The tickets themselves are private to the run owner.
| Model | Accuracy | Macro-F1 | category |
|---|---|---|---|
| Base model | 73.4% | 61.0% | 73.4% |
| Served adapter (iteration 1) | 85.0% | 73.8% | 85.0% |
Accuracy is on the primary field; the field columns are the accuracy of each field on its own.