# Label hit-rates

> Published backtest calibration for convergence labels, including baseline and missing-data states.

Canonical: https://highsignal.app/track-record/labels

[← high signal](https://highsignal.app/)


Backtest-derived calibration for the `breakout` and `divergence` labels rendered on [/convergence](https://highsignal.app/convergence). Hit = a published signal landed for that entity within 24h of the label being computed. Generated by `scripts/backtest-convergence-labels.py`; re-run to refresh.

backtest window: 14d · generated 2026-10-26 15:34 utc

baseline — any converged entity (≥3 sources, 24h window)

0.0% 0 / 61 entity-days had a signal in the next 24h

| label | n | hits | rate | lift | vs baseline |
| --- | --- | --- | --- | --- | --- |
| breakout    ≥3 sources fire AND attention surging ≥15% — mainstream catching up | 7 | 0 | 0.0% | — |  |
| divergence    ≥3 sources fire AND attention dropping — pre-news lead-time | 23 | 0 | 0.0% | — |  |
| unlabeled-converged    ≥3 sources fire but no attention trend / flat — the residual | 31 | 0 | 0.0% | — |  |

Bar: solid = label hit-rate, vertical tick = baseline. To the right of the tick means the label produces signal above what you'd get from any converged entity at random.