{
  "map_id": "atlas/qwen3-0.6b-4bit/probes/v2",
  "map_type": "probes",
  "model_id": "mlx-community/Qwen3-0.6B-4bit",
  "model_hash": "392e8d466d56100ada00eb82031fb854297fc9e389b7d303eba3af114e87bce2",
  "quantization": "q4 (mlx)",
  "commit": "1dcd820126ca96fe99c1b473947f3c7e54038500",
  "config": "results/expA_probe_reliability/20260812T063856Z/results.json",
  "created": "2026-08-12",
  "hardware_manifest": {
    "author": "Simon-Pierre Boucher",
    "contact": "contact@spboucher.ai",
    "website": "https://modelmap.io",
    "chip": {
      "brand": "Apple M5 Max",
      "cores_total": 18,
      "cores_performance": 6,
      "cores_efficiency": 12
    },
    "memory": {
      "unified_gb": 48.0,
      "pagesize": 16384
    },
    "os": {
      "system": "Darwin",
      "version": "27.0",
      "arch": "arm64"
    },
    "software": {
      "python": "3.14.4",
      "numpy": "2.5.2",
      "mlx": "0.32.0",
      "torch": "2.13.0",
      "safetensors": "0.8.0"
    }
  },
  "confidence_level": 1,
  "regenerate_command": ".venv/bin/python benchmarks/promptsets/make_promptsets_v2.py && .venv/bin/python experiments/micro/expA_probe_reliability/implementation/benchmark_v2.py && .venv/bin/python experiments/micro/expA_probe_reliability/implementation/make_mapcard_v2.py",
  "seeds": [
    0,
    1,
    2,
    3,
    4
  ],
  "prompt_sets": [
    "agreement_A.jsonl#622c5e0966d2b8e8",
    "agreement_B.jsonl#243b85e2c207be6c",
    "arith_valid_A.jsonl#a4bb4c645b3f1797",
    "arith_valid_B.jsonl#adc68ef876a823ec",
    "word_order_A.jsonl#9052b924930aa5cd",
    "word_order_B.jsonl#3012db3b5053ba5d"
  ],
  "controls": [
    "shuffled-label (every probe)",
    "random-init architecture twin",
    "BH-FDR q=0.05",
    "v1 positive control (ceiling check)",
    "class token-overlap certificates in promptset manifest"
  ],
  "methods_in_agreement": [],
  "interventions": [
    "layer-skip ablation (expC run #1, 2026-08-12): top-5 differential layers NOT confirmed — damage below random-5 mean; see experiments/micro/expC_causal_verification/analysis.md"
  ],
  "replication_rate": 0.5366,
  "per_dataset_agreement": null,
  "ablation_schemes": [],
  "featurizer_class": "natural-basis (mean-pooled + last-token residual)",
  "intervention_protocol": "none (observational map — Level 1 by design)",
  "negative_result": false,
  "notes": "DIFFERENTIAL map (real minus random-init twin), per the doctrine adopted after v1. Mixed outcome by property: agreement and arith_valid carry trained-model signal above the architecture prior; word_order is null-dominated and flagged as such. Strict twin gate (<0.05) still fails on word_order/agreement — only differential claims are published. CAUSAL CHECK: expC run #1 layer-skip ablation did NOT confirm the top differential layers (survival 0/1); map remains Level 1 and its layer ranking must not be read as causal.",
  "author": "Simon-Pierre Boucher",
  "contact": "contact@spboucher.ai",
  "website": "https://modelmap.io",
  "schema_version": "0.1"
}