Perform backward chaining to prove a goal

Perform backward-chaining proof search. Required scope: write

POST /api/v1/backward-chain

cURL

curl --request POST \
  --url 'https://api.nsr.stateset.com/api/v1/backward-chain' \
  --header "X-API-Key: $STATESET_NSR_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "goal_args": [
    "string"
  ],
  "goal_predicate": "string",
  "max_depth": 1,
  "use_belief_guard": true
}'

200

{
  "belief_actions": [
    "string"
  ],
  "proofs": [
    {
      "confidence": 7.5,
      "steps": [],
      "substitution": {}
    }
  ],
  "proved": true,
  "total_proofs": 1
}

Perform backward-chaining proof search.

Required scope: write

Request body

BackwardChainRequest

goal_args · string[] · required

Arguments for the goal

goal_predicate · string · required

The goal to prove

max_depth · integer

Maximum proof depth

use_belief_guard · boolean

Route the proof through the AGM belief guard: consult entrenchment before search, expand/revise the belief base with each proof.

Response

BackwardChainResponse

belief_actions · string[]

Audit log of AGM belief-base mutations (present iff use_belief_guard).

proofs · ProofInfo[] · required

Show ProofInfo

confidence · number (float) · required

steps · string[] · required

substitution · object · required

proved · boolean · required

total_proofs · integer · required

Status codes

Code	Meaning
200	Backward chaining completed
400	Invalid request
401	Unauthorized — missing or invalid credentials
403	Forbidden — the key/token lacks the required scope
429	Rate limited — see Retry-After / X-RateLimit-Reset
500	Backward chaining failed

cURL

curl --request POST \
  --url 'https://api.nsr.stateset.com/api/v1/backward-chain' \
  --header "X-API-Key: $STATESET_NSR_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "goal_args": [
    "string"
  ],
  "goal_predicate": "string",
  "max_depth": 1,
  "use_belief_guard": true
}'

200

{
  "belief_actions": [
    "string"
  ],
  "proofs": [
    {
      "confidence": 7.5,
      "steps": [],
      "substitution": {}
    }
  ],
  "proved": true,
  "total_proofs": 1
}