{
  "name": "Wald-Q4B",
  "version": "v1.2",
  "aliases": [
    "Wald-4B"
  ],
  "checkpoint": "02600-f19",
  "description": "Open-weight 4B decision model that returns a calibrated probability for every option through a Jev-compatible POST /v1/systemone API; one pass or optional thinking; self-hosted. Independent, not affiliated with TypeSafe AI. v1.2 is the robustness release: v1.1 plus one merged LoRA stage against distracting and adversarial text.",
  "base_model": "Qwen/Qwen3.5-4B-Base",
  "model_url": "https://huggingface.co/org2ai/Wald-4B",
  "weights_tag": "v1.2",
  "weight_precision": "BF16",
  "parameter_scale": "4B",
  "license": "Apache-2.0 (weights and code); see PROVENANCE.md for source-data usage limitations",
  "use_cases": [
    "tool selection",
    "agent routing",
    "classification",
    "clarification decisions"
  ],
  "endpoint": "POST /v1/systemone",
  "input_fields": [
    "state",
    "questions",
    "effort"
  ],
  "output": "per-option probabilities",
  "default_effort": "none",
  "efforts": {
    "none": {
      "gate": 0,
      "generated_thoughts": 0
    },
    "low": {
      "gate": 0.5,
      "max_thought_tokens": 512
    },
    "medium": {
      "gate": 0.7,
      "max_thought_tokens": 512
    },
    "high": {
      "gate": 1.01,
      "max_thought_tokens": 512
    },
    "high-k2..high-k8": {
      "thoughts": "2..8",
      "max_tokens_per_thought": 512
    }
  },
  "thinking_scope": "2–26 options and sufficient context; wider sets use grouped readout; insufficient thought space retains initial answer",
  "evaluation": {
    "jevadvbench": {
      "questions": 812,
      "attack_types": 9,
      "effort": "none",
      "mean_flip_rate_pct": 4.6,
      "v1_1_mean_flip_rate_pct": 9.2,
      "jev_1_13_mean_flip_rate_pct": 6.1,
      "paired_diff_vs_v1_1_pp": [
        -4.6,
        -5.5,
        -3.6
      ],
      "clean_accuracy_143_human_reviewed_pct": 76.2,
      "v1_1_clean_accuracy_pct": 79.0,
      "clean_paired_diff_vs_v1_1_pp": [
        -2.8,
        -6.2,
        -0.6
      ],
      "harness": "JevAdvBench/JevAdvBench@3218e05 request bytes and analysis code",
      "status": "self-run; not submitted"
    },
    "jevbench_public": {
      "items": 231,
      "effort": "none",
      "correct": 204,
      "accuracy": 0.8831,
      "ece": 0.045,
      "brier": 0.191,
      "hardware": "NVIDIA RTX 5090 32 GB",
      "harness": "fstandhartinger/jevbench@9ec6f15a (jevbench.cli, typesafe adapter, serial, loopback)",
      "status": "self-scored; public items were a development scoreboard, not held out; not submitted",
      "thinking_check": {
        "medium_correct": 198,
        "high_correct": 198,
        "runs_each": 1
      }
    },
    "decision_index_sample": {
      "edition": "0.2.1",
      "requests": 6948,
      "read": "one pass",
      "balanced_skill": 50.03,
      "v1_1_balanced_skill": 49.76,
      "paired_diff": [
        0.27,
        -0.36,
        1.05
      ],
      "status": "sample only; no complete-suite run for v1.2"
    },
    "details": "https://huggingface.co/org2ai/Wald-4B/blob/v1.2/evaluation/v1.2/summary.json"
  },
  "documentation_languages": [
    "en",
    "zh"
  ],
  "docs": {
    "en": "README.md",
    "zh": "docs/readmes/README.zh.md",
    "serving": "RUNBOOK.md",
    "sources": "PROVENANCE.md",
    "evaluation_notes": "CONTAMINATION.md",
    "api": "docs/api.md",
    "citation": "CITATION.cff",
    "llms": "llms.txt"
  },
  "affiliation": "Independent; not affiliated with TypeSafe AI",
  "evaluations": [
    {
      "note": "v1.1 results (not this revision's weights)",
      "decision_index_complete_suite": {
        "benchmark": "Decision Index",
        "edition": "0.2.1",
        "scope": "complete suite",
        "score": 54.59,
        "metric": "balanced_skill",
        "requests": 150317,
        "ok": 150317,
        "effort": "high",
        "hardware": "NVIDIA RTX PRO 6000 96 GB",
        "status": "author-run; maintainer validation pending",
        "submission": "https://github.com/apolinario/decision-index/pull/30"
      },
      "jevbench_public": {
        "benchmark": "JevBench",
        "split": "public",
        "items": 231,
        "effort": "none",
        "correct": 203,
        "accuracy": 0.8788,
        "ece": 0.041,
        "brier": 0.188,
        "latency_p50_ms": 33,
        "latency_p95_ms": 168,
        "hardware": "NVIDIA RTX PRO 6000 96 GB",
        "harness": "fstandhartinger/jevbench@9ec6f15a (jevbench.cli, typesafe adapter, serial, loopback)",
        "status": "self-scored; public items were a development scoreboard, not held out; leaderboard measurement requested",
        "request": "https://github.com/fstandhartinger/jevbench/issues/146"
      }
    }
  ],
  "links": {
    "model": "https://huggingface.co/org2ai/Wald-4B",
    "github": "https://github.com/org2AI/wald-4b",
    "results_dataset": "https://huggingface.co/datasets/org2ai/Wald-Q4B-decision-index-results",
    "decision_index_submission": "https://github.com/apolinario/decision-index/pull/30",
    "jevbench_request": "https://github.com/fstandhartinger/jevbench/issues/146",
    "api": "https://huggingface.co/org2ai/Wald-4B/blob/main/docs/api.md",
    "evaluation_summary": "https://huggingface.co/org2ai/Wald-4B/blob/v1.2/evaluation/v1.2/summary.json"
  },
  "weights_sha256": {
    "model-00001-of-00002.safetensors": "0b15067f769e7388bd598aabafa2ea3211a3a0c4e49e47d07c4f65c65ffc25dd",
    "model-00002-of-00002.safetensors": "7cff102b314edeb3dc5abfa7063f72ad3e888884da237601239dc3582074120a"
  },
  "parent_release": {
    "version": "v1.1",
    "checkpoint": "022D0-f7",
    "tag": "v1.1",
    "revision": "50f94ecd5d6e7e8459e9c198ef811bfaba12a3fe"
  },
  "thinking_note": "v1.2 is a one-pass model. On the JevBench public set it scored 198/231 with medium and with high (one run each) against 204/231 with none. Thinking efforts are evaluated on v1.1.",
  "training_data_note": "perturbed copies of v1.1 training questions; inserted texts written by Claude Haiku (Anthropic) from our templates; targets are v1.1 answers on the clean questions; no JevAdvBench text"
}