{
  "architecture": {
    "data": "datasets/synthetic-v1",
    "output": "models/v001-no-lexical",
    "encoder": "mean",
    "no_lexical": true,
    "epochs": 16,
    "width": 64,
    "seed": 1729
  },
  "parameter_count": 128900,
  "threads": 2,
  "device": "cpu",
  "training_seconds": 12.955676199984737,
  "dataset_manifest": {
    "train": {
      "count": 2400,
      "seed": 101,
      "templates": [
        "fieldset",
        "grid",
        "stack"
      ],
      "sha256": "3f24899383d914465232cfaac27f654eae7217ed3fb37894cf07e551120c56e5"
    },
    "validation": {
      "count": 480,
      "seed": 202,
      "templates": [
        "fieldset",
        "grid",
        "stack"
      ],
      "sha256": "1cf777e5703257e3471c3f67b2e421fd3de505de429fbf57223f452648c477a8"
    },
    "test": {
      "count": 480,
      "seed": 303,
      "templates": [
        "nested",
        "table"
      ],
      "sha256": "849ccce76126296a01ee5ef756f2790470dea0e87fad94802d66c6e43fee20ac"
    },
    "novel_wording": {
      "count": 480,
      "seed": 404,
      "templates": [
        "nested",
        "table"
      ],
      "sha256": "8b467567370321ad5fbe604b282b89de6ceaaa4b679621fa0f3685708fa6e1c2"
    },
    "limitations": "Single-step generated tasks; test layouts held out but vocabulary shared. No arbitrary-site claim."
  },
  "history": [
    {
      "epoch": 1,
      "loss": 1.8550479796371961,
      "validation": {
        "samples": 480,
        "action_accuracy": 0.9937499761581421,
        "target_accuracy": 0.987500011920929,
        "joint_step_accuracy": 0.981249988079071,
        "action_ece": 0.22044784342870116,
        "target_ece": 0.08088003582088277,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 2,
      "loss": 0.13040124958283023,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9916666746139526,
        "joint_step_accuracy": 0.9916666746139526,
        "action_ece": 0.023255654115928337,
        "target_ece": 0.019387029227800667,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 3,
      "loss": 0.03187196495893754,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9937499761581421,
        "joint_step_accuracy": 0.9937499761581421,
        "action_ece": 0.009927280319971032,
        "target_ece": 0.017200253321789205,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 4,
      "loss": 0.020266119047607247,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9958333373069763,
        "joint_step_accuracy": 0.9958333373069763,
        "action_ece": 0.005972087383270264,
        "target_ece": 0.013500098619260825,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 5,
      "loss": 0.015120483456963771,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9958333373069763,
        "joint_step_accuracy": 0.9958333373069763,
        "action_ece": 0.004333853721618652,
        "target_ece": 0.011335330316796899,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 6,
      "loss": 0.012618166559964027,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0032119154930114746,
        "target_ece": 0.01193898159544915,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 7,
      "loss": 0.010871525761965466,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9979166388511658,
        "action_ece": 0.002561211585998535,
        "target_ece": 0.008569607511162758,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 8,
      "loss": 0.009834559493404078,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0020296573638916016,
        "target_ece": 0.00988478772342205,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 9,
      "loss": 0.009429128966171686,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.001741647720336914,
        "target_ece": 0.009122428484261036,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 10,
      "loss": 0.008508781761568236,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9979166388511658,
        "action_ece": 0.0014414191246032715,
        "target_ece": 0.006898644263856113,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 11,
      "loss": 0.008215879133020184,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9979166388511658,
        "action_ece": 0.0012744665145874023,
        "target_ece": 0.0062636364018544555,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 12,
      "loss": 0.007625874571538971,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9979166388511658,
        "action_ece": 0.0011022090911865234,
        "target_ece": 0.006032466189935803,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 13,
      "loss": 0.007468186484306659,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9958333373069763,
        "joint_step_accuracy": 0.9958333373069763,
        "action_ece": 0.0009830594062805176,
        "target_ece": 0.005840523226652294,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 14,
      "loss": 0.007115490947494675,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0009055733680725098,
        "target_ece": 0.007445826369803399,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 15,
      "loss": 0.0072767319369105325,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 1.0,
        "joint_step_accuracy": 1.0,
        "action_ece": 0.0007951259613037109,
        "target_ece": 0.007434688042849302,
        "candidate_recall": 1.0
      }
    },
    {
      "epoch": 16,
      "loss": 0.006822081766777525,
      "validation": {
        "samples": 480,
        "action_accuracy": 1.0,
        "target_accuracy": 0.9979166388511658,
        "joint_step_accuracy": 0.9979166388511658,
        "action_ece": 0.0007377266883850098,
        "target_ece": 0.005158267740625888,
        "candidate_recall": 1.0
      }
    }
  ],
  "evaluation": {
    "validation": {
      "samples": 480,
      "action_accuracy": 1.0,
      "target_accuracy": 1.0,
      "joint_step_accuracy": 1.0,
      "action_ece": 0.0,
      "target_ece": 0.003159351646900177,
      "candidate_recall": 1.0
    },
    "test": {
      "samples": 480,
      "action_accuracy": 1.0,
      "target_accuracy": 0.9979166388511658,
      "joint_step_accuracy": 0.9979166388511658,
      "action_ece": 0.0,
      "target_ece": 0.0007791288735461421,
      "candidate_recall": 1.0
    },
    "novel_wording": {
      "samples": 480,
      "action_accuracy": 0.5583333373069763,
      "target_accuracy": 0.8395833373069763,
      "joint_step_accuracy": 0.5062500238418579,
      "action_ece": 0.4301142507465556,
      "target_ece": 0.14861262904014438,
      "candidate_recall": 1.0
    }
  },
  "limitations": "Synthetic single-step action/target prediction; not arbitrary-site task success.",
  "production_promoted": false
}