Text Generation
Transformers
Safetensors
English
qwen3
stablecoin
payments
compliance
x402
eip-3009
eip-712
disputes
refunds
agents
agentkit
trl
web3
usdc
fraud-detection
financial-risk
qwen
mcp
ai-agents
prompt-injection
agentic-payments
payment-security
risk-assessment
ofac
conversational
Eval Results (legacy)
Eval Results
text-generation-inference
Instructions to use sriram1983007/SRA-RiskGate-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sriram1983007/SRA-RiskGate-4B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="sriram1983007/SRA-RiskGate-4B") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("sriram1983007/SRA-RiskGate-4B") model = AutoModelForCausalLM.from_pretrained("sriram1983007/SRA-RiskGate-4B", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use sriram1983007/SRA-RiskGate-4B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "sriram1983007/SRA-RiskGate-4B" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sriram1983007/SRA-RiskGate-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/sriram1983007/SRA-RiskGate-4B
- SGLang
How to use sriram1983007/SRA-RiskGate-4B with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "sriram1983007/SRA-RiskGate-4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sriram1983007/SRA-RiskGate-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "sriram1983007/SRA-RiskGate-4B" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "sriram1983007/SRA-RiskGate-4B", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use sriram1983007/SRA-RiskGate-4B with Docker Model Runner:
docker model run hf.co/sriram1983007/SRA-RiskGate-4B
Card: cleaner header, grouped links, long examples folded
Browse files
README.md
CHANGED
|
@@ -92,8 +92,29 @@ model-index:
|
|
| 92 |
---
|
| 93 |
|
| 94 |
|
|
|
|
|
|
|
|
|
|
| 95 |
# 🛡️ SRA-RiskGate-4B
|
| 96 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 97 |
[](https://colab.research.google.com/drive/1R9seZu-En9QUZCklxFeIqxEuSaISg7x6)
|
| 98 |
[](https://www.kaggle.com/datasets/sriram1983007/sra-stablecoin-risk-bench)
|
| 99 |
[](https://www.kaggle.com/code/sriram1983007/try-sra-riskgate-4b-payment-safety-model)
|
|
@@ -122,6 +143,8 @@ model-index:
|
|
| 122 |
[](https://gist.github.com/sriram1983007-dev/1d915320d85c7ed12a6044e42b382a40)
|
| 123 |
[](https://github.com/sriram1983007-dev/sra-riskgate#usdt-usdb-and-usdg-100)
|
| 124 |

|
|
|
|
|
|
|
| 125 |
|
| 126 |
**SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
|
| 127 |
|
|
@@ -142,13 +165,17 @@ Of v2's 3 unsafe approvals, 2 were prompt injections that the companion SDK's de
|
|
| 142 |
|
| 143 |
**This page is v2 (2026-11-13).** The merged weights here, the [GGUF builds](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-GGUF) and the [Q4_K_M file](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF) are v2: SRA score 0.913 → **0.960**, dispute accuracy 77.8% → **90.2%**, wrongful denials 26.0% → **2.1%**, unsafe payment approvals 0.47% → **0.35%** ([v2 results](https://huggingface.co/datasets/sriram1983007/sra-bench-results)). v1 stays available: `from_pretrained("sriram1983007/SRA-RiskGate-4B", revision="v1")`. The Ollama registry model is still v1 until it is updated. For disputes, pass the computed window in the prompt: `dispute_messages()` in `sra-riskgate` 1.3.0+ builds the exact prompt.
|
| 144 |
|
|
|
|
|
|
|
| 145 |
📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl) · [discuss on alphaXiv](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 146 |
|
| 147 |
📝 **Tutorial:** [Stop your AI agent from signing an unlimited USDC approval](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0): three deterministic checks to run before an agent signs, with runnable code.
|
| 148 |
|
| 149 |
📝 **Article:** [No Chargebacks for AI Agents: Check Payments Before They Sign](https://sriram1983007.hashnode.dev/no-chargebacks-for-ai-agents-check-payments-before-they-sign): how ACP, AP2, MPP and x402 compare, and why stablecoin payments need a risk check before the agent signs.
|
| 150 |
|
| 151 |
-
🔁
|
|
|
|
|
|
|
| 152 |
|
| 153 |
- **Base Sepolia, independently re-checked:** an approved 0.01 USDC payment ([tx](https://sepolia.basescan.org/tx/0xf12e9084becefd94fa6e26e54761fbfc8f3c04215d7fc724d0fca6077ba084fc)) was read back from the chain and verified, and a 2.00 USDC payment to an unknown payee was held before signing. Flow Executor, an independent agent settlement verifier, re-checked both from the chain ([log](https://gist.github.com/sriram1983007-dev/35eab0e934a512346193bcdb5b12d9cf) · [Flow Executor's page](https://flow-kg4x.vercel.app/row)).
|
| 154 |
- **Circle Gateway on Arc testnet:** one agent task, three proposed payments. One was approved, accepted by Gateway and settled to the payee (agent 0.09 → 0.08 USDC, payee 0.01 → 0.02); an unlimited approval was held and a look-alike payee rejected, neither signed ([log](https://gist.github.com/sriram1983007-dev/8cd44e78adec20a0157368ec38c2fb42)).
|
|
@@ -263,6 +290,9 @@ pip install "sra-riskgate[agentkit]>=0.8.0"
|
|
| 263 |
|
| 264 |
Register `RiskGateActionProvider` as the payment provider on your AgentKit instance. It checks chain support, policies, and peg deviations, executing safe ERC-20 transfers only after approval:
|
| 265 |
|
|
|
|
|
|
|
|
|
|
| 266 |
```python
|
| 267 |
from coinbase_agentkit import AgentKit, AgentKitConfig, CdpEvmWalletProvider, CdpEvmWalletProviderConfig
|
| 268 |
from sra_riskgate.integrations.agentkit import RiskGateActionProvider
|
|
@@ -295,6 +325,8 @@ agent_kit = AgentKit(AgentKitConfig(
|
|
| 295 |
))
|
| 296 |
```
|
| 297 |
|
|
|
|
|
|
|
| 298 |
> **Security Guardrail:** To ensure the firewall cannot be bypassed by an autonomous agent, register `RiskGateActionProvider` as the **sole** payment action provider. Do not register generic native transfer or unconstrained ERC-20 providers alongside it.
|
| 299 |
|
| 300 |
### Deterministic Pre-Execution Rules
|
|
@@ -324,6 +356,9 @@ The model was trained on a specific prompt format, and it only performs as bench
|
|
| 324 |
|
| 325 |
Disputes use a different system prompt and user template. See the `prompt` column of the dataset's [`sft` split](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench) for exact dispute examples.
|
| 326 |
|
|
|
|
|
|
|
|
|
|
| 327 |
```python
|
| 328 |
import json
|
| 329 |
from datetime import datetime, timezone
|
|
@@ -482,6 +517,8 @@ verdict = parse_verdict(raw_output)
|
|
| 482 |
print(json.dumps(verdict, indent=2))
|
| 483 |
```
|
| 484 |
|
|
|
|
|
|
|
| 485 |
### Example Output (`risk_gate`)
|
| 486 |
|
| 487 |
For the request above, the expected verdict is a hold: the payee's trusted attestation rates it high risk, and the payer's attestation comes from an attester that is not on the policy's trusted list.
|
|
@@ -510,7 +547,7 @@ For the request above, the expected verdict is a hold: the payee's trusted attes
|
|
| 510 |
ollama run sriram1983007/sra-riskgate
|
| 511 |
```
|
| 512 |
|
| 513 |
-
The Ollama
|
| 514 |
|
| 515 |
For **dispute adjudication**, pass the dispute system prompt in your request (it replaces the built-in one). The exact text is in the `prompt` column of the dataset's [`sft` split](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench).
|
| 516 |
|
|
@@ -518,11 +555,11 @@ For **dispute adjudication**, pass the dispute system prompt in your request (it
|
|
| 518 |
|
| 519 |
| Repo | What's in it |
|
| 520 |
| --- | --- |
|
| 521 |
-
| [SRA-RiskGate-4B-Q4_K_M-GGUF](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF) | Official Q4_K_M (2.5 GB),
|
| 522 |
-
| [SRA-RiskGate-4B-GGUF](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-GGUF) | Official GGUF builds |
|
| 523 |
-
| [mradermacher/SRA-RiskGate-4B-i1-GGUF](https://huggingface.co/mradermacher/SRA-RiskGate-4B-i1-GGUF) | Community imatrix quants by mradermacher, usually the better choice at small sizes |
|
| 524 |
-
| [mradermacher/SRA-RiskGate-4B-GGUF](https://huggingface.co/mradermacher/SRA-RiskGate-4B-GGUF) | Community static quants by mradermacher |
|
| 525 |
-
| [tinyopsec/SRA-RiskGate-4B-GGUF](https://huggingface.co/tinyopsec/SRA-RiskGate-4B-GGUF) | Community quants by tinyopsec, Q2_K to F16 (builds below Q4 not evaluated) |
|
| 526 |
|
| 527 |
The benchmark figures below are for the full-precision model. The v2 GGUF files were checked on 12 benchmark cases (12 of 12 correct for both Q8_0 and Q4_K_M) but have not yet been run on the full benchmark. The full-benchmark quantized results here are for the **v1** builds (measured 2026-11-11; still available at revision `v1`): **Q8_0 matches full precision** on every safety metric; **Q4_K_M keeps the payment gate** (99.3% accuracy, no legitimate payment blocked, unsafe approvals 0.83% vs 0.47%) **but is weaker on disputes** (67.4% vs 77.8%), mostly from false "outside the dispute window" claims that `check_dispute_verdict` corrects (wrongful denials 0.85% with the check, on every build). Use Q4_K_M for payment checks and Q8_0 or full precision for disputes; all predictions are in [sra-bench-results](https://huggingface.co/datasets/sriram1983007/sra-bench-results).
|
| 528 |
|
|
|
|
| 92 |
---
|
| 93 |
|
| 94 |
|
| 95 |
+
<!-- card layout 2026-11-13 -->
|
| 96 |
+
<div align="center">
|
| 97 |
+
|
| 98 |
# 🛡️ SRA-RiskGate-4B
|
| 99 |
|
| 100 |
+
**An open safety check for stablecoin payments made by AI agents (x402, USDC, MCP). Runs on a laptop.**
|
| 101 |
+
|
| 102 |
+
[](https://huggingface.co/spaces/sriram1983007/sra-riskgate-demo)
|
| 103 |
+
[](https://ollama.com/sriram1983007/sra-riskgate)
|
| 104 |
+
[](https://pypi.org/project/sra-riskgate/)
|
| 105 |
+
[](https://pypi.org/project/sra-riskgate-mcp/)
|
| 106 |
+
[](https://doi.org/10.5281/zenodo.23715017)
|
| 107 |
+
[](https://huggingface.co/datasets/sriram1983007/sra-bench-results)
|
| 108 |
+
|
| 109 |
+
**v2 · 2026-11-13** · 99.6% payment decisions correct · 0.35% unsafe approvals · 90.2% dispute outcomes correct · 227 of 227 on real Base payments
|
| 110 |
+
|
| 111 |
+
[Try it](#try-it) · [Python SDK](#📦-python-sdk-one-call-before-every-payment-pypi) · [MCP](#🔌-use-it-from-an-ai-agent-mcp) · [Quickstart](#🚀-transformers-quickstart) · [Benchmark](#📊-benchmark-evaluation-held-out-test-split-measured-by-the-author) · [Limitations](#⚠️-limitations--verification-scope)
|
| 112 |
+
|
| 113 |
+
</div>
|
| 114 |
+
|
| 115 |
+
<details>
|
| 116 |
+
<summary><b>All links and badges</b> (notebooks, integrations, demos, on-chain proofs)</summary>
|
| 117 |
+
|
| 118 |
[](https://colab.research.google.com/drive/1R9seZu-En9QUZCklxFeIqxEuSaISg7x6)
|
| 119 |
[](https://www.kaggle.com/datasets/sriram1983007/sra-stablecoin-risk-bench)
|
| 120 |
[](https://www.kaggle.com/code/sriram1983007/try-sra-riskgate-4b-payment-safety-model)
|
|
|
|
| 143 |
[](https://gist.github.com/sriram1983007-dev/1d915320d85c7ed12a6044e42b382a40)
|
| 144 |
[](https://github.com/sriram1983007-dev/sra-riskgate#usdt-usdb-and-usdg-100)
|
| 145 |

|
| 146 |
+
|
| 147 |
+
</details>
|
| 148 |
|
| 149 |
**SRA-RiskGate-4B checks a stablecoin payment before an AI agent sends it, and answers `approve`, `hold` or `reject`** with reason codes. It is a 4B model, fine-tuned from `Qwen/Qwen3-4B-Instruct-2507`, that runs on a laptop.
|
| 150 |
|
|
|
|
| 165 |
|
| 166 |
**This page is v2 (2026-11-13).** The merged weights here, the [GGUF builds](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-GGUF) and the [Q4_K_M file](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF) are v2: SRA score 0.913 → **0.960**, dispute accuracy 77.8% → **90.2%**, wrongful denials 26.0% → **2.1%**, unsafe payment approvals 0.47% → **0.35%** ([v2 results](https://huggingface.co/datasets/sriram1983007/sra-bench-results)). v1 stays available: `from_pretrained("sriram1983007/SRA-RiskGate-4B", revision="v1")`. The Ollama registry model is still v1 until it is updated. For disputes, pass the computed window in the prompt: `dispute_messages()` in `sra-riskgate` 1.3.0+ builds the exact prompt.
|
| 167 |
|
| 168 |
+
### 📚 Paper and articles
|
| 169 |
+
|
| 170 |
📄 **Paper:** [SRA-RiskGate: A Benchmark and a 4B Model for Gating Stablecoin Payments Made by AI Agents](https://doi.org/10.5281/zenodo.23715017) (preprint, Zenodo) · [full write-up on Ready Tensor](https://app.readytensor.ai/publications/sra-riskgate-a-benchmark-and-a-4b-model-for-gating-stablecoin-payments-made-by-ai-agents-wihp3WytOoKOc1g7NXFsl) · [discuss on alphaXiv](https://www.alphaxiv.org/abs/2610.sra-riskgate-stablecoin-payment-safety)
|
| 171 |
|
| 172 |
📝 **Tutorial:** [Stop your AI agent from signing an unlimited USDC approval](https://dev.to/sriram1983007/stop-your-ai-agent-from-signing-an-unlimited-usdc-approval-10c0): three deterministic checks to run before an agent signs, with runnable code.
|
| 173 |
|
| 174 |
📝 **Article:** [No Chargebacks for AI Agents: Check Payments Before They Sign](https://sriram1983007.hashnode.dev/no-chargebacks-for-ai-agents-check-payments-before-they-sign): how ACP, AP2, MPP and x402 compare, and why stablecoin payments need a risk check before the agent signs.
|
| 175 |
|
| 176 |
+
### 🔁 Verified in the open (November 2026)
|
| 177 |
+
|
| 178 |
+
The companion `sra-riskgate` library's checks, in front of real agents:
|
| 179 |
|
| 180 |
- **Base Sepolia, independently re-checked:** an approved 0.01 USDC payment ([tx](https://sepolia.basescan.org/tx/0xf12e9084becefd94fa6e26e54761fbfc8f3c04215d7fc724d0fca6077ba084fc)) was read back from the chain and verified, and a 2.00 USDC payment to an unknown payee was held before signing. Flow Executor, an independent agent settlement verifier, re-checked both from the chain ([log](https://gist.github.com/sriram1983007-dev/35eab0e934a512346193bcdb5b12d9cf) · [Flow Executor's page](https://flow-kg4x.vercel.app/row)).
|
| 181 |
- **Circle Gateway on Arc testnet:** one agent task, three proposed payments. One was approved, accepted by Gateway and settled to the payee (agent 0.09 → 0.08 USDC, payee 0.01 → 0.02); an unlimited approval was held and a look-alike payee rejected, neither signed ([log](https://gist.github.com/sriram1983007-dev/8cd44e78adec20a0157368ec38c2fb42)).
|
|
|
|
| 290 |
|
| 291 |
Register `RiskGateActionProvider` as the payment provider on your AgentKit instance. It checks chain support, policies, and peg deviations, executing safe ERC-20 transfers only after approval:
|
| 292 |
|
| 293 |
+
<details>
|
| 294 |
+
<summary>Show the AgentKit example (Python)</summary>
|
| 295 |
+
|
| 296 |
```python
|
| 297 |
from coinbase_agentkit import AgentKit, AgentKitConfig, CdpEvmWalletProvider, CdpEvmWalletProviderConfig
|
| 298 |
from sra_riskgate.integrations.agentkit import RiskGateActionProvider
|
|
|
|
| 325 |
))
|
| 326 |
```
|
| 327 |
|
| 328 |
+
</details>
|
| 329 |
+
|
| 330 |
> **Security Guardrail:** To ensure the firewall cannot be bypassed by an autonomous agent, register `RiskGateActionProvider` as the **sole** payment action provider. Do not register generic native transfer or unconstrained ERC-20 providers alongside it.
|
| 331 |
|
| 332 |
### Deterministic Pre-Execution Rules
|
|
|
|
| 356 |
|
| 357 |
Disputes use a different system prompt and user template. See the `prompt` column of the dataset's [`sft` split](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench) for exact dispute examples.
|
| 358 |
|
| 359 |
+
<details>
|
| 360 |
+
<summary>Show the full Python example: prompt, generation and fail-closed parsing</summary>
|
| 361 |
+
|
| 362 |
```python
|
| 363 |
import json
|
| 364 |
from datetime import datetime, timezone
|
|
|
|
| 517 |
print(json.dumps(verdict, indent=2))
|
| 518 |
```
|
| 519 |
|
| 520 |
+
</details>
|
| 521 |
+
|
| 522 |
### Example Output (`risk_gate`)
|
| 523 |
|
| 524 |
For the request above, the expected verdict is a hold: the payee's trusted attestation rates it high risk, and the payer's attestation comes from an attester that is not on the policy's trusted list.
|
|
|
|
| 547 |
ollama run sriram1983007/sra-riskgate
|
| 548 |
```
|
| 549 |
|
| 550 |
+
The Ollama registry model is still **v1** until it is updated (the GGUF files below are v2). It has the **payment risk-gate system prompt** built in, plus `temperature 0` and an 8K context. Send the user message in the training format shown in the Quickstart (`Evaluate this stablecoin payment.` followed by the `<context>`, `<payload>` and `<tool_results>` blocks).
|
| 551 |
|
| 552 |
For **dispute adjudication**, pass the dispute system prompt in your request (it replaces the built-in one). The exact text is in the `prompt` column of the dataset's [`sft` split](https://huggingface.co/datasets/sriram1983007/sra-stablecoin-risk-bench).
|
| 553 |
|
|
|
|
| 555 |
|
| 556 |
| Repo | What's in it |
|
| 557 |
| --- | --- |
|
| 558 |
+
| [SRA-RiskGate-4B-Q4_K_M-GGUF](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-Q4_K_M-GGUF) | Official Q4_K_M (2.5 GB), v2 |
|
| 559 |
+
| [SRA-RiskGate-4B-GGUF](https://huggingface.co/sriram1983007/SRA-RiskGate-4B-GGUF) | Official GGUF builds: Q8_0, Q6_K, Q5_K_M, Q4_K_M (v2) |
|
| 560 |
+
| [mradermacher/SRA-RiskGate-4B-i1-GGUF](https://huggingface.co/mradermacher/SRA-RiskGate-4B-i1-GGUF) | Community imatrix quants by mradermacher, usually the better choice at small sizes (made from v1) |
|
| 561 |
+
| [mradermacher/SRA-RiskGate-4B-GGUF](https://huggingface.co/mradermacher/SRA-RiskGate-4B-GGUF) | Community static quants by mradermacher (made from v1) |
|
| 562 |
+
| [tinyopsec/SRA-RiskGate-4B-GGUF](https://huggingface.co/tinyopsec/SRA-RiskGate-4B-GGUF) | Community quants by tinyopsec, Q2_K to F16, made from v1 (builds below Q4 not evaluated) |
|
| 563 |
|
| 564 |
The benchmark figures below are for the full-precision model. The v2 GGUF files were checked on 12 benchmark cases (12 of 12 correct for both Q8_0 and Q4_K_M) but have not yet been run on the full benchmark. The full-benchmark quantized results here are for the **v1** builds (measured 2026-11-11; still available at revision `v1`): **Q8_0 matches full precision** on every safety metric; **Q4_K_M keeps the payment gate** (99.3% accuracy, no legitimate payment blocked, unsafe approvals 0.83% vs 0.47%) **but is weaker on disputes** (67.4% vs 77.8%), mostly from false "outside the dispute window" claims that `check_dispute_verdict` corrects (wrongful denials 0.85% with the check, on every build). Use Q4_K_M for payment checks and Q8_0 or full precision for disputes; all predictions are in [sra-bench-results](https://huggingface.co/datasets/sriram1983007/sra-bench-results).
|
| 565 |
|