AI developers and agent operators
researchAre my agents independent, or one view repeated?
1 · Who forecasts it
806
forecasters · 6,200,321 forecasts · 108,699 with outcomes
2024-07-21 → 2024-07-21 · 90% interval not measured
2026-09-27 → 2026-09-27 · 90% interval not measured
2026-08-30 → 2026-08-30 · 90% interval not measured
past record · ranked vs panel median · as of 21 Oct 2026
2 · Where they fail together
beats every rival
Confident-miss warnings vs each forecaster's own track record (tree) · +23.1% on confirmation · interval not measured
Confirmation sample: 182,291 forecast rows · independent groups: 4,517. Inventory above is not the test sample.
10 documented dependence links corpus-wide; unknown never means independent.
practice test · not the served model
3 · Should you trust a forecast?
Check a forecast with Zeno. Supported sources can receive a correction; elsewhere it keeps the reference and labels why.
Evidence · ForecastBench
- Inventory source
- frozen v0.80.2 build census + v0.82 practice run. Counts describe the frozen corpus, not independent samples.
- Warning test period
- historical: development and later confirmation slices of past data. Calendar boundaries not supplied in this summary.
- Comparator and method
- each forecaster's own track record (tree); Brier score of confident-miss warnings. CPU tree rehearsal, not the served neural model.
- 90% interval
- Not measured in this export. No interval inferred from row counts or significance values.
- Dependence evidence
- 10 documented links across the corpus, not ForecastBench-specific shared failures. Missing links mean unknown.
- Scoring boundary
- Past record and practice results are not sealed live performance. Check receipts identify the answer actually served.
Served model: v0.57. Research model: not yet promoted.
What runs Zeno
Member of NVIDIA Inception · H200 research training
Job records, not a total of successful runs. GPU hours not verified here. Inception membership is not an endorsement.
Evidence, not affiliation
Forecast seals carry immutable receipts. A seal proves submission timing, not forecasting skill.
On-chain compute receipts: not verified. Celo token presence does not prove model execution or forecast accuracy.