| Feature | Existing System | ActiveWiki |
|---|---|---|
| Hypotheses per run | 6 | 19 (3.2x) |
| Detection strategies | 5 (Python rules) | 12 (including temporal, counterfactual, meta) |
| Counterfactuals | ❌ | ✅ Challenges strongest beliefs |
| Knowledge Crystallization | ❌ | ✅ 3+ lessons → meta-knowledge |
| Self-Reflection | ❌ | ✅ Auto-tunes decay_rate + max_hypotheses |
| Confidence Scoring | Label only (high/medium/low) | 0-1 numeric, evolves with time |
| Expected Impact | ❌ | ✅ ROI-like score per hypothesis |
| HTML Dashboard | ❌ | ✅ Auto-generated every cycle |
| Research Brief | ❌ | ✅ Auto-published every 7 cycles |
| Wiki Pruning | ❌ | ✅ Intelligent page cleanup |
| Hypothesis Evolution | ❌ | ✅ Evolves old hypotheses into v2.0 |
| Cost | $0 | $0 |
| Dependencies | Custom Python | Zero (pip install activewiki) |
ActiveWiki auto-publishes a mini research paper every 7 cycles. Here's the latest:
ActiveWiki was installed on the same VPS that runs Strategy Arena. It ingested the same data (Darwin Engine results, Living Wiki lessons, nightly logs from 2,530+ experiments). It ran 3 cycles with a simulated backtest engine. No data was modified. The existing system continued running normally.
The comparison is fair: same data, same machine, same moment. The only difference is the framework processing it.
ActiveWiki is an MIT-licensed research framework for closed-loop knowledge experiments. This page reports a bounded historical comparison against a captured corpus of 2,530+ experiment records. Its 3.2x hypothesis count belongs to that benchmark setup; it is not a current production-throughput or autonomous-trading claim. GitHub repository.