Discover predictive structure

Structure Discovery evaluates eligible fields and their combinations for predicting a declared target. It can include bounded temporal relationships and expose the resulting rules with supporting and contradicting evidence through induced_structure and learning_state. Declare the target and event boundary before sending completed events.

Minimal configuration

The numeric settings below are example parameters.

{
  "domain_id": "case-structure-demo",
  "session_id": "ignored",
  "description": "Discover observable structure associated with case outcomes.",
  "schema": {
    "event_types": ["resolved_case"]
  },
  "learning": {
    "enabled": true,
    "structure": {
      "enabled": true,
      "event_types": ["resolved_case"],
      "feature_paths": [],
      "targets": [
        {
          "path": "values.outcome",
          "type": "categorical"
        }
      ],
      "representation": {
        "enabled": true,
        "maximum_order": 2,
        "maximum_lag": 3,
        "minimum_support": 12,
        "episode_path": "metadata.episode_id"
      }
    }
  }
}

An empty feature_paths list enables discovery from eligible scalar fields. The target, text, timestamps, identifier-like fields, and most metadata are excluded from automatic raw features.

What Discovery can form

Structure Discovery can use current fields, combinations of fields, and bounded temporal relationships when those patterns are useful for the declared target. The public controls you usually need are:

Field	Meaning
`maximum_order`	Bounds how many fields can participate in one discovered combination
`maximum_lag`	Bounds how far back Discovery can inspect within one episode
`minimum_support`	Requires enough compatible evidence before discovered structure is used
`episode_path`	Separates independent temporal histories

Start with the example parameters. Increase order or lag only when the task actually requires more complex combinations or longer temporal context.

Structure Discovery evaluates the supplied observations against the target declared by the application.

Event shape

curl -sS -X POST \
  "https://rei-neuroadapt-api.reilabs.org/api/v1/domains/case-structure-demo/events" \
  -H "Authorization: Bearer $ADAPT1_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "session_id": "ignored",
    "event_type": "resolved_case",
    "values": {
      "signal_a": true,
      "signal_b": 0.42,
      "noise_probe": 7,
      "outcome": "accept"
    },
    "metadata": {
      "episode_id": "case-stream-001",
      "step": 14
    }
  }'

The episode_id prevents temporal candidates from crossing independent sequences. Use a stable step order inside each episode. If events are independent, assign separate episode IDs or disable temporal representation discovery by omitting representation.

Inspect event admission

The event response includes structure_eligibility. Check whether the event was accepted, whether the sample count changed, which feature and target paths were admitted, and whether representation discovery is ready. Read the selected paths from learner state because they depend on the admitted evidence.

Query induced structure

curl -sS -X POST \
  "https://rei-neuroadapt-api.reilabs.org/api/v1/domains/case-structure-demo/query" \
  -H "Authorization: Bearer $ADAPT1_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "session_id": "ignored",
    "question": "What outcome is supported by this case?",
    "context": {
      "values": {
        "signal_a": true,
        "signal_b": 0.38,
        "noise_probe": 2
      },
      "metadata": {
        "episode_id": "evaluation-001",
        "step": 0
      }
    },
    "return_fields": ["induced_structure", "learning_state"],
    "update_memory_state": false,
    "allow_exploration": false
  }'

induced_structure can expose the current hypotheses, their conditions and predictions, and the evidence that supports or contradicts them. Representation state is available at:

learning_state
  .subsystems
  .autonomous_structure
  .representation

For normal use, inspect readiness, selected paths, active representations, model version, and the supporting or contradicting evidence attached to the current result.

Explicit versus discovered features

If feature_paths is non-empty, those base paths define the authoritative feature surface. Representation discovery can still evaluate combinations and lags derived from those fields.

{
  "feature_paths": [
    "values.signal_a",
    "values.signal_b"
  ],
  "representation": {
    "enabled": true,
    "maximum_order": 2,
    "maximum_lag": 2
  }
}

Use this mixed mode after reviewing automatic discovery or when governance requires an approved input list.

Prevent accidental leakage

Before relying on induced structure:

Confirm the target is absent from query context.
Remove target-derived scores, post-outcome flags, evaluator labels, and correct-action fields.
Partition training and evaluation by entity or episode.
For a frozen comparison, stop learner updates before scoring held-out data.
Compare against a simple single-field or best-feature selector.
Inspect whether a suspicious identifier or timestamp became predictive.
Repeat across seeds or independent streams when reporting performance.

Causal interpretation of a discovered association requires intervention evidence and a valid intervention protocol.

When to pin the structure

Keep discovery active while the feature surface is intentionally open and monitored. Pin base paths when:

The Domain enters a regulated or audited workflow.
Field semantics are versioned by an upstream contract.
Availability changes must produce an explicit failure.
A frozen evaluation requires a stable representation.

The active rules can continue updating from evidence even when the permitted base paths are explicit.

Discovery overview

Review the Discovery paths and their admission requirements.

Transition Discovery

Discover executable input projections and compatible causal bindings.

Sequential Discovery

Discover state-dependent action values and delayed credit across episodes.

Complete examples

Run transition, structural, sequential, and mixed workflows.

Get started

Concepts

Guides

Discovery

Operations

API reference

Minimal configuration

What Discovery can form

Event shape

Inspect event admission

Query induced structure

Explicit versus discovered features

Prevent accidental leakage

When to pin the structure

Discovery overview

Transition Discovery

Sequential Discovery

Complete examples

​Minimal configuration

​What Discovery can form

​Event shape

​Inspect event admission

​Query induced structure

​Explicit versus discovered features

​Prevent accidental leakage

​When to pin the structure

Discovery overview

Transition Discovery

Sequential Discovery

Complete examples

Minimal configuration

What Discovery can form

Event shape

Inspect event admission

Query induced structure

Explicit versus discovered features

Prevent accidental leakage

When to pin the structure