mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-05-08 18:01:20 -05:00
0afc384282
Two new pieces close the generation→validation→saturation feedback loop: 1. gemini_cli_llm_judge.py — multi-criteria validator. For each draft, judges math correctness, cell-fit (does it actually target the declared track/zone/level?), scenario realism, uniqueness vs canonical questions, and visual-asset alignment. Returns PASS/NEEDS_FIX/DROP per item. Batched (default 15 per call) for budget efficiency. 2. iterate_coverage_loop.py — drives the full loop: analyze → plan → generate → render → judge → apply → re-analyze. Self-paced: stops when (a) top priority gap drops below threshold, (b) DROP rate exceeds the saturation/hallucination threshold, (c) total API calls exceed budget, or (d) the same cell is top priority for two iterations in a row (convergence). The user no longer specifies "how many questions" — the loop generates until the corpus reaches a measurable steady state. Plus 25 round-1 visual questions generated by the new batched generator (5 batched calls × 5 cells each, zero failures). The loop is the answer to "we need balance, not just volume": every iteration's plan derives from a fresh analysis of where coverage is weakest, so generation can never over-fill an already-saturated cell.
18 lines
744 B
Python
18 lines
744 B
Python
import os
|
|
import matplotlib.pyplot as plt
|
|
fig, ax = plt.subplots(figsize=(8, 4))
|
|
stages = 4
|
|
microbatches = 8
|
|
colors = ['#cfe2f3', '#d4edda']
|
|
for s in range(stages):
|
|
for m in range(microbatches):
|
|
ax.barh(stages - 1 - s, 0.8, left=s+m, height=0.6, color=colors[0], edgecolor='black')
|
|
for m in range(microbatches):
|
|
ax.barh(stages - 1 - s, 0.8, left=stages+s+m+microbatches-2, height=0.6, color=colors[1], edgecolor='black')
|
|
ax.set_yticks(range(stages))
|
|
ax.set_yticklabels([f'Stage {i}' for i in reversed(range(stages))])
|
|
ax.set_xlabel('Time Steps')
|
|
ax.set_title('1F1B Pipeline Schedule Visualization')
|
|
plt.tight_layout()
|
|
out = os.environ.get("VISUAL_OUT_PATH", "out.svg")
|
|
plt.savefig(out, format="svg", bbox_inches="tight") |