Report — group 2 (E17–E28, confidence): is confidence a second axis or a restatement of max(p)?

E17–E28 · REPORT, AS WRITTEN

12 experiments, 5,875 records and 8,215,046 input tokens.

C

Confirmed

7

F

Falsified

4

M

Mixed

1

This group tested what Jev's confidence number is good for: telling right answers from wrong ones, warning when an answer might flip, and deciding when a gate should let an answer through on its own.

Reading the record…

Experiments in this group

Exp

Verdict

Question

E17

C

Confirmed

Does a high confidence score mean an answer is more likely correct?

E18

C

Confirmed

Is confidence a repeat of the model's top probability, or new information?

E19

F

Falsified

Out of five ways to measure how sure an answer is, which works best?

E20

M

Mixed

Where should a confidence cutoff be set, and does it pay off?

E21

C

Confirmed

Is confidence a better warning sign than adding a yes/no check question?

E22

F

Falsified

If a question is reworded without changing its meaning, does confidence hold steady?

E23

C

Confirmed

Does low confidence warn you that an answer might flip on a repeat?

E24

C

Confirmed

Can how a question is written push confidence up or down?

E25

C

Confirmed

Does confidence mean the same thing with 3 answer options as with 40?

E26

F

Falsified

Can a confidence cutoff be picked from old answers instead of new tests?

E27

F

Falsified

If you ask the same judgment three ways, do their certainty scores agree?

E28

C

Confirmed

Does a confidence-based pause button actually change what an automated loop does?

108 experiments, 38,194 API responses logged, 45,861,280 input tokens, $1.9262 at $0.042 per million.

Compiled from dependency-docs-reference/jev/notes/12-experiments on 2026-09-19.