[ File — track record ]
Realized results. Losing buckets included.
Every number below is computed from signals that reached their horizon — no backtests, no cherry-picking. Alpha is the signal's stock return minus its sector ETF over the 60 trading days after the event. We report the median, the typical outcome — means get skewed by a few microcap moonshots. Data revalidates hourly.
Exhibit A
Contract signals, by model rank.
This is the test a ranking model has to pass: outcomes should get monotonically better up the ranks. The top rank beat its sector by +3.0% median with a 58% hit rate; everything the model ranks lower underperforms. That separation — not any single winner — is the evidence the ranking means something.
| Rank | Median α (60d) | Hit rate | n |
|---|---|---|---|
| Top rank | +2.96% | 58% | 489 |
| High | -8.14% | 38% | 337 |
| Mid | -8.73% | 29% | 165 |
| Low | -7.46% | 35% | 470 |
High-conviction actions only fire in the top bucket — that's where the alpha concentrates.
Exhibit B
Event signals, by source.
Post-announcement events — M&A, FDA approvals — are largely efficient by the time they print, and the table says so. We surface them as context and rank them accordingly; the contract track above is where the edge lives. Publishing this distinction is the point: a tool that claims everything works is a tool you can't trust about anything.
| Source | Median α (60d) | Hit rate | n |
|---|---|---|---|
| M&A announcement | -1.55% | 45% | 3416 |
| FDA approval | -0.77% | 47% | 1508 |
| Federal grant | -3.52% | 43% | 142 |
| Recompete | — | — | 72 |
| Contract 8-K | -5.68% | 31% | 58 |
| Sentiment spike | — | — | 52 |
| Budget line | — | — | 42 |
| Subcontract | -9.34% | 15% | 37 |
Exhibit C
Event signals, by model rank.
The same monotonic test, applied to the event track. The separation is thinner than in contracts — consistent with markets pricing announced news faster than they price the federal award pipeline.
| Rank | Median α (60d) | Hit rate | n |
|---|---|---|---|
| Top rank | -3.73% | 45% | 106 |
| High | -1.06% | 47% | 1192 |
| Mid | -1.42% | 44% | 3996 |
| Low | -9.34% | 18% | 33 |
Method, in one paragraph
When a signal fires, we record the stock's price and its sector ETF's price. Sixty trading days later we take the difference in returns — that's the alpha. Hit rate is the share of signals with positive alpha. Buckets are fixed score ranges assigned at signal time, never re-labeled after the fact. Outcomes accrue as signals reach their horizon, so recent signals aren't counted until their window closes.
Audit it yourself, live.
The 7-day trial opens the same feed these outcomes came from. Watch it for a week and check the record against what you saw — then decide.
Start your 7-day free trialSignal infrastructure, not investment advice · past performance does not guarantee future results