gnumanth/nullspan (v1.2.1)

nullspan v1.2.1 ships two zero-output-token System One neural models in one open-weights MIT repository:

1. NullspanForExtraction (345.3M PyTorch FP32 + 331.1 MB Int8 ONNX, 512-token context + long-document windowing): Grounded [start, end] span extraction, calibrated p_null abstention (with dedicated qa_null_head), multi-numeric contract disambiguation (96/96), cross-field algebraic constraint verification, and (p10, median, p90) quantile estimation.
2. NullspanSystemOneEngine (435M DeBERTa-v3-Large + r=32 LoRA + Cross-Option & Cross-Question Workflow Competition Head, systemone/): Native /v1/systemone calibrated decision model for noul (true/false), choice (options), and ordinal score (min..max) rubrics with 0 generated output tokens.

Verified Public Benchmark Scores (Google Cloud NVIDIA L4 GPU · Zero Test Contamination)

Public Benchmark	Dataset & Split	Score	Calibration & Validity	Latency / Cost (L4 GPU)
LocalLLaMA/typed-decisions	Official test (400 cases · 2,000 decisions)	75.40% Accuracy (Table 2 fitted cross-encoder; #2 vs Hub .eval_results widget)	KL 0.1515 · Brier 0.0770 · ECE 0.0944	78.0 ms/dec (390.0 ms/case) · 0 output tokens
Benchmark Heaven / jevbench	Official Public Suite (231 items via /v1/systemone)	100.0% Easy (48/48) · 62.50% Original (45/72) · 37.84% Hard (42/111)	100.0% Strict Schema Validity (Easy Brier 0.0207, ECE 0.0605)	64.8 ms p50 · $0.00667 / 1k (encoder_classifier_<=0.6B)
Stanford rajpurkar/squad_v2	Zero-overlap validation (N = 500: 250 HasAns + 250 NoAns)	87.00% Exact Match · 89.36% F1	HasAns F1 91.52% · NoAns EM 87.20%	10.30 ms p50 · $0.0017 / 1k
NullspanBench v3.2	N = 500 (336 Open + 164 Sealed: SQuAD2, 96 Contracts, 8 Adversarial)	98.2 Capability · 98.0% Intelligence (95.7 Hybrid Composite)	98.5 Calibration (AUROC 0.9933, ECE 0.0142; Int8 ONNX ECE 0.0127)	10.30 ms CUDA p50 (0.040 ms Hybrid) · $0.0003–$0.0017 / 1k

Training Disclosure: NullspanSystemOneEngine is fine-tuned on the LocalLLaMA/typed-decisions train split alongside public BoolQ, ARC-Challenge, and SciQ train splits plus programmatic synthetic System One rubrics; it is not zero-shot on Typed Decisions. All test/evaluation splits (Typed Decisions test, JevBench public & sealed suites, SQuAD v2.0 validation, and NullspanBench evaluation pools) were strictly untouched during training and post-hoc temperature calibration.

Quick Start — Grounded Extraction (NullspanForExtraction)

from transformers import AutoModel, AutoTokenizer

repo_id = "gnumanth/nullspan"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModel.from_pretrained(repo_id, trust_remote_code=True)

incident = (
    "Incident INC-40928 opened on Apr 12, 2026 with a 502 Bad Gateway errors and a TLS handshake timeouts. "
    "Issued $1240.50 plus $310.25 SLA credit. Severity is sev-1 and customer data loss was false. "
    "Root cause CVE not yet assigned. Cluster stabilized on Apr 19, 2026. Reported by Mira"
)

result = model.extract(
    state=incident,
    fields={
        "incident_id": {"type": "text", "instructions": "Incident ticket identifier"},
        "opened_on": {"type": "date", "instructions": "Date the incident opened"},
        "total_credit": {"type": "number", "decimals": 2, "unit": "USD", "instructions": "Total credit including SLA penalty"},
        "outage_days": {"type": "duration", "unit": "days", "integer": True, "instructions": "Days from incident open to cluster stabilization"},
        "failure_modes": {"type": "list", "items": "text", "instructions": "Each failure mode triggered"},
        "severity": {"type": "enum", "options": ["sev-1", "sev-2", "sev-3"], "instructions": "Incident severity tier"},
        "data_loss": {"type": "boolean", "instructions": "Whether customer data loss occurred"},
        "cve_id": {"type": "text", "instructions": "Assigned CVE identifier if present"},
        "remediation_cost": {"type": "estimate", "unit": "USD", "min": 100, "max": 25000, "scale": "log", "step": 10, "instructions": "Estimated engineering remediation cost"},
    },
    tokenizer=tokenizer,
)
print(result["answers"])

Quick Start — /v1/systemone Typed Decisions (NullspanSystemOneEngine)

from nullspan import decide

res = decide(
    state={"customer_tier": "enterprise", "RefundCapUSD": 500, "RequestedRefundUSD": 420, "FraudFlag": False},
    questions={
        "eligible": {"type": "noul", "instructions": "Is RequestedRefundUSD <= RefundCapUSD with FraudFlag == False?"},
        "route": {"type": "choice", "options": ["approve", "escalate", "deny"], "instructions": "Select refund action."},
        "urgency": {"type": "score", "min": 1, "max": 5, "instructions": "Rate SLA urgency from 1 to 5."},
    },
    model_id="gnumanth/nullspan",
)
print(res["answers"])

Or serve the TypeSafe-compatible /v1/systemone HTTP endpoint directly:

pip install "nullspan[hf]" fastapi uvicorn peft
python serve_systemone.py --model-dir gnumanth/nullspan --port 8010

Repository Contents

• model.safetensors, config.json, modeling_nullspan.py: NullspanForExtraction (345.3M ELECTRA-Large + 2-layer Pre-LN SchemaAdapterBlock + qa_null_head).
• onnx/model_quantized.onnx, onnx/tokenizer.json: 331.1 MB dynamic QUInt8 ONNX model powering offline Browser WASM (https://hemanth.github.io/nullspan/) and CPU inference.
• systemone/, systemone_decision.pt, systemone_decision.py, serve_systemone.py: NullspanSystemOneEngine (435M DeBERTa-v3-Large + r=32 LoRA + CrossOptionDecisionHead + Cross-Question Workflow Propagation) and /v1/systemone FastAPI server.
• .eval_results/typed-decisions.yaml, .eval_results/nullspan-bench.yaml, SCIENCE_REPORT.md: Reproducible benchmark metadata and statistical report.

License

MIT © Hemanth.HM