Train the NSR Machine on examples

Trains the neural-symbolic system using input-output pairs. The system learns to map inputs to outputs through both neural perception and symbolic program…

POST /api/v1/nsr/train

cURL

curl --request POST \
  --url 'https://api.nsr.stateset.com/api/v1/nsr/train' \
  --header "X-API-Key: $STATESET_NSR_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "epochs": 5,
  "examples": [
    {
      "inputs": [
        {
          "type": "text",
          "value": "walk"
        }
      ],
      "output": {
        "type": "list",
        "value": [
          {
            "type": "string",
            "value": "WALK"
          }
        ]
      }
    },
    {
      "inputs": [
        {
          "type": "text",
          "value": "run"
        }
      ],
      "output": {
        "type": "list",
        "value": [
          {
            "type": "string",
            "value": "RUN"
          }
        ]
      }
    }
  ]
}'

200

{
  "final_loss": 0.023,
  "programs_learned": 3,
  "successful_abductions": 8,
  "total_examples": 10,
  "training_time_ms": 1250
}

Trains the neural-symbolic system using input-output pairs. The system learns to map inputs to outputs through both neural perception and symbolic program synthesis. Training Process

1. Neural perception maps inputs to symbol distributions
2. Parser constructs syntactic structures
3. Abductive reasoning synthesizes programs that explain the examples
4. Library learning extracts reusable program components Example

curl -X POST 'https://api.nsr.stateset.com/api/v1/nsr/train' \
-H 'X-API-Key: your-api-key' \
-H 'Content-Type: application/json' \
-d '{
'examples': [
{'inputs': [{'type': 'text', 'value': 'walk'}], 'output': {'type': 'list', 'value': [{'type': 'string', 'value': 'WALK'}]}},
{'inputs': [{'type': 'text', 'value': 'run'}], 'output': {'type': 'list', 'value': [{'type': 'string', 'value': 'RUN'}]}}
],
'epochs': 5
}'

Required scope: models:manage

Request body

NSRTrainRequest

epochs · integer

Number of epochs (optional, default 1)

examples · TrainingExampleRequest[] · required

Training examples

Response

NSRTrainResponse

final_loss · number (double) · required

Final training loss

programs_learned · integer · required

Programs learned during training

successful_abductions · integer · required

Successful abductions

total_examples · integer · required

Total examples processed

training_time_ms · integer (int64) · required

Training time in milliseconds

Status codes

Code	Meaning
200	Training completed successfully
400	Invalid request - empty examples or validation failed
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	Internal server error - training failed
504	Training budget exhausted before completion

cURL

curl --request POST \
  --url 'https://api.nsr.stateset.com/api/v1/nsr/train' \
  --header "X-API-Key: $STATESET_NSR_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
  "epochs": 5,
  "examples": [
    {
      "inputs": [
        {
          "type": "text",
          "value": "walk"
        }
      ],
      "output": {
        "type": "list",
        "value": [
          {
            "type": "string",
            "value": "WALK"
          }
        ]
      }
    },
    {
      "inputs": [
        {
          "type": "text",
          "value": "run"
        }
      ],
      "output": {
        "type": "list",
        "value": [
          {
            "type": "string",
            "value": "RUN"
          }
        ]
      }
    }
  ]
}'

200

{
  "final_loss": 0.023,
  "programs_learned": 3,
  "successful_abductions": 8,
  "total_examples": 10,
  "training_time_ms": 1250
}