README.md

---
tags:
- ml-intern
---
# Oracle-Credit-Compute (OCC) Stack

A minimal, open-source research prototype for **agentic compute allocation** where agents earn and spend non-transferable, decaying credits based on verified marginal impact.

## Quickstart

```bash
git clone https://huggingface.co/narcolepticchicken/occ-stack
cd occ-stack
pip install -r requirements.txt

# Simulated benchmarks (CPU)
python benchmarks/benchmark_code.py              # Code compute allocation
python benchmarks/benchmark_retrieval_qa.py    # Retrieval QA
python benchmarks/benchmark_debate_v2.py         # Multi-agent debate

# Ablations + anti-gaming (CPU, ~5 min)
python eval_runner.py

# Real LLM benchmark (GPU, requires T4+)
python jobs/run_real_llm_standalone_v7.py

# Unit tests
python tests/test_oracle.py
python tests/test_ledger.py
```

## Architecture

```
┌─────────────┐    ┌─────────────────┐    ┌──────────────┐
│  Agent      │───▶│  ResourceBroker │───▶│  Compute     │
│  (requests  │    │  (allow/deny/   │    │  (model call,│
│   resource) │◄───│   downgrade)    │◄───│   retrieval) │
└─────────────┘    └─────────────────┘    └──────────────┘
       │                   │
       ▼                   ▼
┌─────────────┐    ┌─────────────────┐
│ CreditLedger│◄───│  ImpactOracle   │
│ (earn/spend/│    │  (score action  │
│  decay)     │    │   on verified   │
└─────────────┘    │   impact)       │
                   └─────────────────┘
```

## Key Results (Simulated)

- **52.3% compute reduction at iso-accuracy** on code benchmark (OCC tiered escalation vs fixed budget)
- **76% accuracy with 40% adversarial agents** in debate (OCC credit-filtering vs 56% naive confidence voting)
- **All anti-gaming attacks contained:** hidden-test gaming, collusion, over-abstention, spam

## Status

| Component | Status |
|-----------|--------|
| Impact Oracle | ✅ Working |
| Credit Ledger | ✅ Working |
| Resource Broker | ✅ Working |
| GRPO/RL Hook | ✅ Factory ready |
| Simulated benchmarks | ✅ Complete |
| Ablations (10 conditions) | ✅ Complete |
| Anti-gaming tests | ✅ Complete |
| Real LLM benchmark | 🔄 V7 in progress |
| GRPO training | 🔄 Not yet run |

## Repo Structure

```
occ/
  oracle/          # ImpactOracle — rule-based scoring
  ledger/          # CreditLedger — non-transferable, decaying credits
  broker/          # ResourceBroker — capability-based access control
  rl/              # RewardHook, OfflineComparator — TRL GRPO integration
  benchmarks/      # 3 benchmark scripts + real LLM variants
  tests/           # Unit tests
  reports/         # Reports, results, blog post
  jobs/            # Self-contained GPU job scripts
```

## Citation

```bibtex
@misc{occ2026,
  title={Oracle-Credit-Compute: A Minimal Stack for Agentic Compute Allocation},
  author={narcolepticchicken},
  year={2026},
  url={https://huggingface.co/narcolepticchicken/occ-stack}
}
```

<!-- ml-intern-provenance -->
## Generated by ML Intern

This model repository was generated by [ML Intern](https://github.com/huggingface/ml-intern), an agent for machine learning research and development on the Hugging Face Hub.

- Try ML Intern: https://smolagents-ml-intern.hf.space
- Source code: https://github.com/huggingface/ml-intern

## Usage

```python
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = 'narcolepticchicken/occ-stack'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
```

For non-causal architectures, replace `AutoModelForCausalLM` with the appropriate `AutoModel` class.