Provenance, rescue and receipt

Added in 0.3. The matching producer capability for the receipt is receipt.

"provenance": { "kind": "designed", "chooser": "loopmath" },
"receipt": {
  "before": {
    "rec": "rec_ex01",
    "fit": "fit_ex_20260923",
    "predicted": {
      "p_success": { "mean": 0.78, "lo": 0.66, "hi": 0.88, "level": 0.8 },
      "cost_usd": { "mean": 2.9, "lo": 1.9, "hi": 4.4 },
      "tokens": { "mean": 900000, "lo": 600000, "hi": 1400000 }
    }
  },
  "after": {
    "cost_usd": 3.52,
    "tokens": 1376000,
    "signals": ["sig_review_2", "sig_tests_ci"],
    "fit_after": "fit_ex_20260923b"
  }
}

The values are made up.

Provenance

run.provenance says how the configuration came to run. A logged run was observed as it happened, with the configuration the user’s habit chose. A designed run had its configuration chosen for it, by a recommender, the user or a planner. The difference matters to a learner: logged runs show what a user tends to pick, designed runs are closer to a controlled comparison.

enum

required

logged: the run was observed as it happened, configuration chosen by the user’s habit. designed: the configuration was chosen for the run (by loopmath, the user or a planner).One of: logged, designed.

string

Who chose the configuration.Recommended values (open set): habit, loopmath, user, planner.At most 100 characters.

Ext

Rescue

A workflow’s control.rescue is the plan for a run that ends without acceptance: redo the task with another configuration, hand it to a person, or nothing. run.rescue records the fallback that was actually used, and what it cost. Present when the run ended without acceptance and a fallback was used.

string

required

Recommended values (open set): configuration, person, none.At most 100 characters.

string

At most 200 characters.

number

enum

measured: the fallback ran and was priced. expected: an estimate.One of: measured, expected.

Ext

run.rescue is present only when the run ended without acceptance and a fallback was used.
basis is measured when the fallback ran and was priced, and expected when the cost is an estimate.

Receipt

A receipt sets a prediction made before the run against what happened. before holds what a recommender predicted for this configuration on this task: the chance of an accepted result, the cost in dollars and tokens, and for an exploration pick, what it expected to gain per run and what the exploration would cost. after holds the actual cost and tokens, the signals the result was scored on, and how the fit moved. Predicted against actual. Written only by loopmath (W196 when another producer writes one).

object

Show properties

string

The recommendation id.At most 200 characters.

string

The fit the prediction came from.At most 200 characters.

object

Show properties

Interval

any

Per-run gain of an exploration pick: {usd, success_pp, cost_pct, score}, or null.

number | null

Ext

object

Show properties

number | null

integer | null

array

The signals the result was scored on (ids or copies).

any

How the fit moved after this run (written by loopmath).

string | null

At most 200 characters.

Ext

Every predicted quantity is an interval: A predicted quantity: mean and an 80 percent interval unless level says otherwise.

number

required

number

Central coverage of [lo, hi]; 0.8 when absent.

Only loopmath writes receipts, and a checker warns when another producer writes one (W196). The receipt’s contents follow loopmath’s model.
A consumer MAY ignore the receipt.

Specification

The document

The observation

Conformance

Reference

Provenance

Rescue

Receipt

​Provenance

​Rescue

​Receipt

Provenance

Rescue

Receipt