Waterflood. Which change earned the barrels.
Workover, pump-speed and injection changes scored against a counterfactual, with a placebo and an interval. Injector–producer connectivity, unidentifiable pairs flagged. Scored against the open libraries on planted truth; the results stay here. Proposals only; never sets a rate.
Six products. One engine.
Reconcile. Attribute. Propose.
Reconcile
Rates against separator and fiscal totals, first.
a prerequisiteAttribute
The counterfactual, the placebo, the interval.
Uplift · Pair · Tank · PlaceboPropose
Allocation and programmes, as proposals.
Allocate · DoseCapacitance–resistance models with producer coupling, beside staggered difference-in-differences, synthetic control and synthetic difference-in-differences with placebo inference
Wavepin watches a pipeline in seconds. Sweep reads a field over months. No shared physics; the same tournament and honest status.
Tournament t003, 749 intervention and placebo windows on synthetic waterfloods with planted truth (the revised physical counterfactual; earlier runs are in the ledger). The bar and the result are on the proof page. All the numbers →
The whole story in 80 seconds
Built for the assets you run
Mature onshore floods
Rod-pumped producers, decades of data.
Offshore injection
Few wells, expensive changes.
Gas-lift fields
Lift changes as interventions.
Reserves teams
Improved-recovery evidence.
The results stay public.
Every number, against the open libraries, and the ledger are on the proof page. The panel half lives on in the causal engine.
