{
  "code_termination_diagnostic": {
    "among_outputs_reaching_execution": {
      "control": {
        "executed": 103,
        "pass_percent": 15.53,
        "passed": 16
      },
      "winner": {
        "executed": 46,
        "pass_percent": 21.74,
        "passed": 10
      }
    },
    "interpretation": "The full-code result is dominated by severe termination/extraction pathology and is not a clean latent-code estimate.",
    "winner_generations_hitting_512_token_cap": 376,
    "winner_generations_total": 421
  },
  "comparison": {
    "benign_kl": {
      "control": 0.0,
      "strict_limit": 0.05,
      "winner": 0.093614
    },
    "capability_macro_percent": {
      "control": 17.6859,
      "winner": 21.0086
    },
    "exact_prompt_echoes": {
      "control": 2,
      "leakage_detected": true,
      "winner": 3
    },
    "full_code_passes": {
      "control": 16,
      "denominator": 421,
      "winner": 10
    },
    "harmful_hard_refusal_percent": {
      "control": 43.2,
      "winner": 0.0
    },
    "harmful_soft_deflection_percent": {
      "control": 14.6,
      "winner": 0.2
    },
    "harmful_substantive_response_percent": {
      "control": 47.0,
      "winner": 99.4
    },
    "held_out_loss_ratio": {
      "control": 1.0,
      "limit": 1.05,
      "winner": 1.024478
    },
    "human_eval_percent": {
      "control": 7.9268,
      "winner": 4.2683
    },
    "incoherence_percent": {
      "control": 2.7692,
      "strict_winner_limit": 2.7692,
      "winner": 4.3077
    },
    "long_form_pass_percent": {
      "control": 54.1667,
      "winner": 62.5
    },
    "max_repeated_4gram_fraction_percent": {
      "strict_limit": 5.0,
      "winner": 5.8632
    },
    "mmmu30_correct": {
      "control": 9,
      "denominator": 30,
      "winner": 11
    }
  },
  "evaluation_provenance": {
    "kind": "self-run_frozen_local_benchmarks",
    "note": "Results were produced by this project on a frozen local evaluation suite. They must not be mixed with or represented as official Qwen benchmark results.",
    "official_qwen_benchmarks": false,
    "release_report_frozen_at": "2026-08-22T00:01:48.742409+00:00"
  },
  "lineage": {
    "abliterix_version": "1.12.2",
    "base_model": "Qwen/Qwen3.8-27B",
    "method": "Reasoning QLoRA merge followed by one selected Abliterix pass for the winner; control received no Abliterix residual-writer edits.",
    "reasoning_control": "control-bf16",
    "seed": 42,
    "winner": "abliterix-pass1-bf16"
  },
  "native_mlx_proof": {
    "control_mtp_statistics": {
      "accepted_drafts_per_round": 1.73,
      "accepted_tokens_per_round": 2.73,
      "average_draft": 2.0,
      "drafted_percent": 86.5,
      "rounds": 37
    },
    "mtp_exact_answer": {
      "control": "323",
      "winner": "323"
    },
    "ordinary_exact_answer": {
      "control": "323",
      "winner": "323"
    },
    "runtime": "mlx-vlm on arm64 macOS/Metal",
    "speed_note": "MTP speed is workload-dependent; positive acceptance and exact-answer agreement are the correctness evidence.",
    "winner_mtp_statistics": {
      "accepted_drafts_per_round": 1.78,
      "accepted_tokens_per_round": 2.78,
      "average_draft": 2.0,
      "drafted_percent": 88.8,
      "rounds": 76
    },
    "winner_quantization": {
      "bits": 8,
      "group_size": 64,
      "scheme": "affine"
    }
  },
  "release_family": "Qwen3.8-27B Opus Personal Model v1",
  "schema_version": 1,
  "selection": {
    "all_preregistered_strict_gates_passed": false,
    "control_variant": "control-bf16",
    "selected_variant": "abliterix-pass1-bf16",
    "status": "selected_practical_winner_with_measured_deviations",
    "summary": "Practical personal-model selection with measured deviations; not universal dominance."
  },
  "strict_deviations": [
    {
      "metric": "benign_kl",
      "passed": false,
      "strict_limit": 0.05,
      "winner": 0.093614
    },
    {
      "metric": "incoherence_percent",
      "passed": false,
      "strict_limit": 2.7692,
      "winner": 4.3077
    },
    {
      "control": 7.9268,
      "metric": "human_eval_percent",
      "passed": false,
      "strict_delta_floor": -3.0,
      "winner": 4.2683,
      "winner_delta_points": -3.6585
    },
    {
      "control": "16/421",
      "metric": "full_code_passes",
      "passed": false,
      "winner": "10/421"
    },
    {
      "metric": "max_repeated_4gram_fraction_percent",
      "passed": false,
      "strict_limit": 5.0,
      "winner": 5.8632
    },
    {
      "control_exact_echoes": 2,
      "metric": "prompt_leakage",
      "passed": false,
      "winner_exact_echoes": 3
    }
  ],
  "tensor_integrity": {
    "native_mtp_tensors": 15,
    "total_tensor_keys": 1199,
    "unexpected_changes": 0,
    "vision_tensors_preserved": 333,
    "winner_abliterix_residual_writer_edits": 74
  },
  "training": {
    "dataset_preparation": {
      "accepted_rows": 12614,
      "duplicates_removed": 208,
      "invalid_rows_removed": 20,
      "processed_manifest_sha256": "6e0a36ad20732c5f98ff592c4565a4c86876fead4e9f94bc6ceedfad1339a94d",
      "raw_rows": 12842,
      "rows_published": false,
      "source_rows": {
        "high-reasoning-250x": 250,
        "opus-10000x": 9633,
        "opus-3000x": 2326,
        "reasoning-700x": 633
      },
      "split_sha256": {
        "test.jsonl": "a2b6b46ce8b054166b0e392701e49390a44e391b56d25a0a25e9b8a9000257d9",
        "train.jsonl": "c7e691bcabd945e1259537f74119bce4c2c8f5fa4d2fba2e626b95bc04176ad3",
        "validation.jsonl": "589a05d0cf2fededff1febb065d6b3c8c947d29e948495c1567bcd9f5c44f364"
      },
      "splits": {
        "test": 138,
        "train": 12349,
        "validation": 127
      }
    },
    "dtype_after_merge": "bfloat16",
    "final_validation_loss": 0.23739749,
    "hardware": "NVIDIA H200-class run; the sealed Abliterix environment recorded NVIDIA H200, CUDA 13.0, driver 580.159.03, Python 3.11.15.",
    "optimizer_steps": 1544,
    "rows": 12349,
    "token_accuracy_percent": 91.7594,
    "trainable_lora_parameters": 108789760
  }
}