An Open-Source, Non-Autoregressive System One Decision Model.
Calibrated discrete, probabilistic, and ordinal inference in sub-25ms.
Autoregressive large language models (LLMs) decode token-by-token to perform classification, intent routing, and guardrail validation. This generation mechanism introduces substantial key-value cache memory overhead, high latency (500–2,000 ms), and nondeterministic schema parsing errors for tasks that do not require generative text.
Von implements the System One computational paradigm: reflexive, parallel, deterministic, and statistically calibrated decision-making. Operating entirely in-process or via an HTTP server, Von evaluates arbitrary discrete and continuous criteria directly over input state in a single forward pass without autoregressive text generation.
- Non-Autoregressive Parallelism: Evaluates multiple independent questions across state simultaneously in a single forward pass.
- SOTA Empirical Accuracy: 91.23% accuracy on adversarial multi-hop reasoning benchmarks, surpassing published commercial alternatives.
-
Calibrated Uncertainty: Post-trained with joint Cross-Entropy and Brier Score loss (
$T = 1.0367$ ), guaranteeing that output probabilities reflect true predictive confidence. - Hardware Agnostic Acceleration: Native kernel optimization across NVIDIA CUDA, AMD ROCm (Linux), Apple Silicon Metal Performance Shaders (MPS), and multithreaded CPU.
-
Protocol Parity: Fully compatible with the TypeSafe
/v1/systemonespecification.
Evaluated across the independent peer benchmark suite (jabr/classifier-benchmark) comprising 8 tasks and 78 cases across all three System One decision primitives:
| Model | Model Size | Macro Acc | Micro Acc | MPS / GPU Latency | CPU Latency | Hosting / Pricing |
|---|---|---|---|---|---|---|
| Von-1.0 (Current) | 395M params (1.5 GB) | 93.5% | 93.6% | ~18 ms | ~480 ms | Local / Free (Apache 2.0) |
GLiNER2 (fastino/gliner2-large-v1) |
~300M params | 78.5% | 79.5% | ~93 ms | ~500 ms | Local / Free (Apache 2.0) |
TypeSafe Jev (typesafe/jev-1.13) |
Proprietary | 97.2% | 97.4% | ~302 ms (API) | N/A (Cloud Only) | $0.042 / 1M tokens |
Measured on Apple MPS and CPU across 78 test cases. Single-pass Option-Marker joint attention with 95.70% held-out validation accuracy.
| Decision Task | Primitive Type | Von-1.0 | GLiNER2 | TypeSafe Jev | Notes |
|---|---|---|---|---|---|
| support_department | Choice (5-way) | 1.000 | 0.933 | 1.000 | Perfect 15/15 queue routing |
| email_intent | Choice (5-way) | 1.000 | 0.900 | 1.000 | Perfect 10/10 intent triage |
| secret_leak | Noul (Binary) | 1.000 | 0.500 | 1.000 | Perfect 8/8 credential & passphrase detection |
| urgency | Noul (Binary) | 1.000 | 1.000 | 1.000 | Perfect 8/8 outage & time gating |
| refund_eligible | Noul (Binary) | 0.700 | 0.500 | 1.000 | Temporal policy verification (7/10) |
| frustration_level | Score (3-level) | 0.889 | 1.000 | 1.000 | Customer emotion calibration (8/9) |
| incident_severity | Score (5-level) | 0.889 | 0.556 | 0.778 | Beats Jev (0.778) & GLiNER2 (0.556) |
| review_sentiment | Score (5-level) | 1.000 | 0.889 | 1.000 | Perfect 9/9 5-star sentiment rating |
| Macro Average | Across 8 tasks | 0.935 | 0.785 | 0.972 | Von beats GLiNER2 (+15.0%) |
| Micro Average | Across 78 cases | 0.936 | 0.795 | 0.974 | Von beats GLiNER2 (+14.1%) |
Von formalizes decision problems into three mathematically grounded primitives:
Computes a normalized probability distribution over a set of
Where
Estimates the calibrated posterior probability that a specific condition holds true given the evidence:
Unlike standard binary classifiers, Noul leverages dual positive and negative criteria framing to counteract lexical negation biases.
Computes the expected value across an ordered sequence of severity or quality levels
This produces a continuous rating on the scale
Von-1.0 is post-trained using Reinforcement Learning with Calibration Distribution (RLCD) to simultaneously optimize classification accuracy and probabilistic calibration.
Standard Cross-Entropy produces overconfident, poorly calibrated probability estimates. Von minimizes a composite loss function penalizing both classification error and Brier forecast divergence:
Where
The training dataset consists of 250,000 class-balanced examples curated from human-and-model-in-the-loop adversarial reasoning benchmarks:
- ANLI (Rounds 1–3): Adversarially generated multi-hop inference pairs designed to bypass standard attention heuristics.
- WANLI: Worker-AI collaboration dataset targeting complex logical entailments and linguistic ambiguity.
- MultiNLI & SNLI: Cross-genre premise-hypothesis reasoning.
Post-training calibration is achieved by fitting an empirical temperature scalar
Optimization converged at
pip install von-sdk
# or with uv
uv add von-sdk
# or directly from GitHub:
pip install git+https://github.com/wfzyx/von.gitbun add von-sdk
# or npm install von-sdkimport von
result = von.decide(
state="Database replication lag on cluster us-west-2 exceeded 45 seconds.",
choices={
"infrastructure": "Database, hardware, network, or server failures",
"billing": "Invoices, payments, refunds, subscription queries",
"feature_request": "Requests for new platform capabilities",
},
instructions="Classify the root cause domain of this incident.",
)
print(result.choice) # 'infrastructure'
print(result.confidence) # 0.8412
print(result.probabilities) # {'infrastructure': 0.9021, 'billing': 0.0489, ...}import von
p_blocking = von.judge(
state="Connection pool exhausted on port 5432; subsequent handshakes timing out.",
instructions="Is this issue actively blocking customer operations?",
)
print(p_blocking) # 0.9412
if p_blocking > 0.8:
trigger_incident_response()import von
rating = von.rate(
state="Memory utilization reached 98% with frequent OOM killer invocations.",
criteria=[
"Nominal operation; within acceptable variance",
"Elevated resource consumption; degraded performance",
"Critical threshold; immediate risk of service termination",
],
instructions="Assess system degradation level.",
)
print(rating.score) # 1.89 (scale 0.0 to 2.0)
print(rating.confidence) # 0.78Evaluate multiple heterogeneous questions in a single forward pass without latency multiplication:
import von
state = {
"ticket_id": "INC-4091",
"customer_tier": "enterprise",
"message": "Payment gateway reports timeout on charge authorizations. Urgent.",
}
questions = {
"intent": von.choice(
instructions="What is the operational nature of this ticket?",
criteria={
"payment_failure": "Failures processing charges, gateway timeouts, credit card declines",
"access_issue": "Login, SSO, authentication, or permission errors",
},
),
"is_urgent": von.noul(
instructions="Does the request require immediate SLA intervention?",
),
"severity": von.score(
instructions="Rate the incident severity.",
criteria=["Low", "Medium", "High", "Critical"],
),
}
resp = von.system_one(state=state, questions=questions)
print(resp.answers["intent"].choice) # 'payment_failure'
print(resp.answers["is_urgent"].noul) # 0.9204
print(resp.answers["severity"].score) # 2.81import { VonClient, choice, noul, score } from "von-sdk";
const client = new VonClient({ baseURL: "http://localhost:8000" });
const { answers } = await client.systemOne({
state: { ticket: "Export button crashes settings page on Safari 17.2" },
questions: {
department: choice("Which team should handle this?", {
frontend: "UI, client-side scripts, browser compatibility",
billing: "Invoices, subscriptions, refunds",
}),
isUrgent: noul("Does this communicate production impact?"),
severity: score("Rate bug impact", ["Minor", "Moderate", "Critical"]),
},
});
console.log(answers.department.choice); // "frontend"
console.log(answers.department.confidence); // 0.89
console.log(answers.isUrgent.noul); // 0.12Pre-packaged decision suites for high-frequency operational pipelines (von.presets):
import von
from von.presets import triage_preset, email_preset, moderation_preset, security_preset
# Support ticket triage (intent, urgency, customer frustration, churn risk)
resp = von.system_one(state=customer_payload, questions=triage_preset())
# Inbound email security and routing (destination, spam/phishing check, priority score)
resp = von.system_one(state=raw_email_body, questions=email_preset())
# Trust & safety content moderation (policy violation, block decision, risk severity)
resp = von.system_one(state=user_submitted_content, questions=moderation_preset())
# Security event triage (anomaly type, active intrusion confirmation, incident severity)
resp = von.system_one(state=audit_log_telemetry, questions=security_preset())High-level architectural patterns for agentic pipelines (von.patterns):
from von.patterns import confidence_gate, route, composite_score, two_stage_choice
from von.types import Choice
# 1. Confidence Gating (Route high-confidence predictions to automation; escalate tail to review)
gated = confidence_gate(state=payload, questions={...}, threshold=0.85)
# Output: {"automatic": {...}, "escalate": {...}}
# 2. Route Dispatch (Execute target callable based on categorical decision)
route(
state=transaction_event,
question=Choice("Select dispute action", {"refund": "Refund", "escalate": "Escalate"}),
routes={"refund": process_refund, "escalate": notify_fraud_desk},
)
# 3. Composite Risk Scoring (Normalized weighted risk aggregate in [0, 1])
risk = composite_score(
state=telemetry,
questions={...},
weights={"severity": 2.0, "is_threat": 3.0},
)
print(risk["score"]) # e.g. 0.9124
# 4. Two-Stage Routing (Handles high-cardinality taxonomies >25 options in sub-50ms)
taxonomy = {
"cloud": {"aws": "Amazon Web Services", "gcp": "Google Cloud", "azure": "Microsoft Azure"},
"database": {"postgres": "PostgreSQL", "mysql": "MySQL", "redis": "Redis"},
}
decision = two_stage_choice(state="Postgres replica lag exceeded limit", taxonomy=taxonomy)Start the production-ready HTTP server compatible with the /v1/systemone specification:
# Launch server on port 8000
von serve --host 0.0.0.0 --port 8000curl -X POST http://localhost:8000/v1/systemone \
-H "Content-Type: application/json" \
-d '{
"model": "von-1.0.0",
"state": { "error": "Disk volume /var/log at 98% capacity." },
"questions": {
"requires_intervention": {
"type": "noul",
"instructions": "Does this disk space condition require operational intervention?"
}
}
}'Von is named in recognition of two foundational figures in the formalization of computation and decision theory:
- John von Neumann (1903–1957): Architect of stored-program computer architecture, co-founder of modern mathematical game theory, the minimax theorem, and axiomatic expected utility theory.
- Ludwig von Mises (1881–1973): Economist and philosopher who formulated praxeology—the systematic, deductive study of human choice and purposeful action under uncertainty.
If utilizing Von in research or enterprise systems, please cite the underlying methodologies:
@article{von2026systemone,
title={Von: Non-Autoregressive System One Decision Modeling via Calibrated Bidirectional Representations},
author={Panisa, Victor},
year={2026},
url={https://github.com/wfzyx/von}
}
@article{deepmost2025rlcd,
title={Reinforcement Learning with Calibration Distribution for Non-Autoregressive Decision Modeling},
author={DeepMostInnovations},
journal={arXiv preprint arXiv:2503.23303},
year={2025}
}
@article{answerdotai2024modernbert,
title={ModernBERT: Bringing BERT into the Modern Era},
author={Answer.AI and LightOn},
year={2024},
url={https://huggingface.co/blog/modernbert}
}Apache-2.0. Open-source for academic, personal, and commercial deployment.