Trajectories that respect your bounds, with audit evidence attached.
Industrial and clinical trajectories have physical limits: pressures that cannot spike, tank levels that cannot cross a valve limit, heart rates that cannot step-change by twenty beats in a tick. A generator that ignores those limits ships data nobody can trust on the downstream side.
Physics Model is the contract-driven post-processor that enforces per-signal envelopes, step-over-step rate limits, and bound-release smoothing on every trajectory you generate. It reads the guardrails from the same sealed contract the generator used, projects the trajectory onto the feasible region, and ships a per-step correction ledger plus a determinism hash inside the evidence bundle — so your auditor sees exactly when and where the projector acted.
- Per-signal envelopes & rate caps
- Bound-recovery smoothing (no flat-line artifacts)
- Per-step correction ledger
- Deterministic under seed + contract
Three buyers, one problem.
A generator that produces physically-impossible data is worse than no generator at all — the downstream model learns the impossible as normal, and the first time a regulator or a plant engineer looks at the dataset they catch it in seconds. Physics Model is the guardrail that keeps generated data inside the limits your real process actually has.
Plant operators and OT integrators
A pump pressure cannot spike to 500 PSI in one scan cycle. A tank level cannot go negative. A valve position cannot jump from 10 % to 90 % without a command. Physics Model enforces those guardrails on every generated trajectory, so the dataset you hand to your SOC or your IDS vendor looks exactly the way real plant telemetry looks — no impossible transitions, no envelope violations, no embarrassment on review.
Technical: per-signal box bounds, step-over-step rate limits, recovery smoothing. Every correction recorded in the evidence bundle with timestamp and magnitude. Deterministic under a sealed seed — regression tests stay stable.
Biostatisticians and clinical-data teams
Heart rate does not step-change by twenty beats in one tick. Serum glucose does not oscillate on a minute scale. A patient's oxygen saturation does not cross 120 %. Physics Model keeps generated clinical time series inside the physiological envelopes your protocol declares, so the synthetic cohort you use for a digital-twin study, a feasibility simulation, or a model-validation run passes a biostatistician's sniff test on first read.
Technical: declarative envelope contracts per signal, recovery handling for transient excursions, full per-step correction ledger for auditability. The evidence bundle ships with the trajectory so a regulator can see exactly where the projector acted.
Risk, fraud, and market-data teams
Portfolio balances do not go negative. Transaction timestamps do not move backwards. A cumulative column does not decrease. Physics Model enforces the monotonicity and sign constraints that downstream risk models implicitly assume, so the synthetic training set you hand to your fraud team behaves the way real books and real tapes behave — no impossible cashflows, no stochastic violations of the accounting identity.
Technical: monotonicity constraints, non-negativity, sum-conservation, and per-column rate caps. Every violation counted, every correction recorded, every run re-runnable byte-for-byte on a different machine a year from now.
The duct-tape scripts your team is maintaining today.
Most teams we talk to are already doing this job — badly — with a rotating stack of Python scripts, pandas clamp statements, ad-hoc rolling means, and "if value > threshold, replace with threshold" fixups. Those scripts work on Monday. They do not work on Thursday when a new operator forgets to run them. They do not produce an audit trail. They do not tell you which rows were corrected, how much, or why. And when a regulator asks how the data was conditioned, the answer is an email thread and a half-remembered Jira ticket.
Physics Model replaces that entire workflow with one declarative envelope contract that travels with the job, one deterministic projector, one auditable correction ledger, and one sealed evidence record per run. The team stops maintaining 600 lines of fragile post-processing and starts shipping data with a guarantee attached.
For the buyer evaluating us: the time-to-value argument is not model sophistication. It is that the people doing this by hand today get back their week, and the data downstream stops being the weakest link in every conversation with your compliance officer.
Every correction, timestamped. Every run, deterministic.
The Physics Model ledger is the artefact your downstream analyst actually consumes. It pairs every correction the projector made with the original value, the corrected value, the contract rule that fired (box bound, rate limit, or recovery smoother), and the exact trajectory step at which the correction was applied. If a regulator asks how the data was conditioned between generation and delivery, the answer is one file — not a Slack thread.
The violation sparkline to the right is the diagnostic view your data-science team looks at before a dataset leaves the platform: it shows the shape of the intervention, so a spike that decays to zero reads as a projector working correctly, and a flat line of violations reads as a contract that needs to be widened or a generator that needs to be retrained. Each run is accompanied by a determinism hash sealed into the evidence bundle, so the exact correction series is reproducible on any machine under the same seed and contract — forever.
Commercial framing: before Physics Model, the value of a "clean" trajectory was an opinion held by whoever wrote the last round of clamp scripts. After Physics Model, it is a verifiable artefact attached to every dataset — which is what regulated buyers, procurement reviewers, and enterprise auditors actually need when they sign the purchase order.
Bounds, rates, recoveries — in your contract.
You declare the guardrails your trajectories must respect — per-signal physical envelopes, step-over-step change limits, recovery handling for bound releases — inside a single contract that travels with your run. Physics Model reads that contract and enforces it.
Real industrial and clinical processes don't step discontinuously at an envelope edge; they ease back. Physics Model recognises that and handles the transition smoothly rather than leaving an unrealistic flat line in your output. Tuning knobs are private to the engine; your contract keeps the envelope declarations only.
# Contract guardrail block (shape only)
{
"constraints": {
"box_bounds": [ /* per-signal envelopes */ ],
"rate_limits": [ /* step-over-step caps */ ],
"recoveries": [ /* bound-release easing */ ]
}
}Violations counted. Corrections recorded.
Every Physics Model run ships a per-step violation count, a total final-violation count, a step count, and a determinism hash inside the sealed evidence bundle.
A separate correction ledger captures when, where, and by how much each value was adjusted, so a downstream analyst can reconstruct exactly where the projector acted. No silent smoothing — every touch is accounted for.
{
"engine": "physics",
"steps_taken": …,
"final_violations": 0,
"constraint_violations_per_step": "/* per-step series */",
"determinism_hash": "/* sealed in evidence */",
"seed": "/* your seed */"
}Post-processor you can trust.
Physics Model runs after another engine produces trajectories and before the evidence bundle is sealed. The contract declares the envelopes; Physics Model enforces them and records every correction.
- Industrial SCADA — physical envelopes for process tags, plus step-over-step ceilings for actuated variables.
- Healthcare time series — vital-sign physiological ranges and between-measurement change limits.
- Financial — non-negative balances, daily-change ceilings, circuit-breaker rules expressed as rate limits.
- Energy grid — substation voltage / frequency bands plus ramp-rate ceilings.
rady physics run \
--contract ./contract.json \
--trajectory ./upstream.ndjson \
--output ./corrected.ndjson
✓ Trajectory loaded, envelopes enforced
✓ Correction ledger written to evidence
✓ Determinism hash sealed in bundle
→ evidence bundle: rady evidence get <job_id>Bounded trajectories, audit-ready.
Physics Model ships alongside our engine, Gaussian Copula, and Tabular Diffusion under one sealed contract. Access is enterprise-contracted.