GitHub PR trajectories extracted by operation-prometheus for SE model training.
🔄 In a Training Loop
Raul Cardenas Montoya
rmems
·
AI & ML interests
Early-career AI/ML experimental systems and Agentic systems
Recent Activity
new activity about 14 hours ago
rmems/oracle-grounded-neuromorphic-20261006:Metadata: size_categories, contributor name, collection new activity about 14 hours ago
rmems/python-function-repair-20261006:Metadata: size_categories, provenance replay wording, contributor name, collection new activity about 15 hours ago
rmems/python-function-repair-20261006:Card: disclose partial replay coverage and outcome/oracle splitsOrganizations
None yet
Preserved for evaluation, provenance, quality analysis, and cross-generator research. No downstream model-training or weight-update
My experimental spiking neural network, built from scratch: the SNN model, its supervisor trajectory + telemetry datasets, and the routing research.
Deterministic project-owned synthetic data: oracle simulation records and verified code-repair batches.
Preserved for evaluation, provenance, quality analysis, and cross-generator research. No downstream model-training or weight-update
Structural parse of open Grok-1 + route-preservation ternary GOZ1 quant experiments (Grok Build: Grok 4.5 high).
GitHub PR trajectories extracted by operation-prometheus for SE model training.
Deterministic project-owned synthetic data: oracle simulation records and verified code-repair batches.
Preserved for evaluation, provenance, quality analysis, and cross-generator research. No downstream model-training or weight-update
Preserved for evaluation, provenance, quality analysis, and cross-generator research. No downstream model-training or weight-update
My experimental spiking neural network, built from scratch: the SNN model, its supervisor trajectory + telemetry datasets, and the routing research.
Structural parse of open Grok-1 + route-preservation ternary GOZ1 quant experiments (Grok Build: Grok 4.5 high).