Pinned Loading

1. IRMB_QNN-P1_DriftArchive_HardwareValidation IRMB_QNN-P1_DriftArchive_HardwareValidation Public

   Preregistered study: a noise model built from a self-collected month of hourly ibm_fez calibration snapshots predicts real hardware behavior of a hybrid quantum neural network to 0.5 pt. Part of th…

   Python 2

2. mtca-research mtca-research Public

   IRMB / MTCA — a research program studying frame-sensitivity in frontier AI reasoning about non-propositional content

   Jupyter Notebook 1

3. HF-IQR-V3 HF-IQR-V3 Public

   Pre-registered confirmatory study of frontier LLM critique behavior under a forced-counterargument intervention. Companion data to osf.io/yhk98.

   Jupyter Notebook 1

4. IRMB_Phase7G_Design5_QuantumCausality IRMB_Phase7G_Design5_QuantumCausality Public

   Pre-registered causal test of quantum-modulated LLM council coordination. IBM ibm_fez (156q) vs 5 conditions including matched classical sampler. 8-model council. Frontier-400 benchmark. REVERSAL o…

   Jupyter Notebook 1

5. hf-critic hf-critic Public

   Fine-tuning open-source LLMs into reasoning-process critics — QLoRA, held-out eval, controlled cross-model comparison. Part of the IRMB program.

   Python 5

6. forge-agent forge-agent Public

   Governed autonomous research agent for evaluating fine-tuned reasoning critics — sandboxed execution, provenance tracking, and blinded adjudication.

   Python 1