Resource use and parsing robustness across PG construction modes on MultiChallenge (56-sample test split) with Gemini 3.5 Flash. Mode 5 (Scratch + Online Evolution) achieves a 45.7% reduction in parsing failures per sample relative to unguided baseline (0.57 vs 1.05), while using 5.05 steps and 92.81s per sample (compared to 8.02 steps and 166.57s for Mode 4). Mode 3 achieves highest overall success (92.86%) at 6.73 steps and 128.50s.

Resource use and parsing robustness across PG construction modes on MultiChallenge (56-sample test split) with Gemini 3.5 Flash. Mode 5 (Scratch + Online Evolution) achieves a 45.7% reduction in parsing failures per sample relative to unguided baseline (0.57 vs 1.05), while using 5.05 steps and 92.81s per sample (compared to 8.02 steps and 166.57s for Mode 4). Mode 3 achieves highest overall success (92.86%) at 6.73 steps and 128.50s. · CiteArk

Measurement results

0/30 assessed

0 supported0 disputed or conflicting30 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Metric and conditions	Reported	Latest observation	Evidence judgment
constructionMode: Unguided Baseline (w/o PG)	87.5%	—	Not assessed
constructionMode: Unguided Baseline (w/o PG)	7,403.98 tokens	—	Not assessed
constructionMode: Unguided Baseline (w/o PG)	7.05 steps	—	Not assessed
constructionMode: Unguided Baseline (w/o PG)	1.05 failures_per_sample	—	Not assessed
constructionMode: Unguided Baseline (w/o PG)	127.59 seconds	—	Not assessed
constructionMode: Mode 1: Hand-crafted Expert	58.93%	—	Not assessed
constructionMode: Mode 1: Hand-crafted Expert	11,039.82 tokens	—	Not assessed
constructionMode: Mode 1: Hand-crafted Expert	6.6 steps	—	Not assessed
constructionMode: Mode 1: Hand-crafted Expert	0.88 failures_per_sample	—	Not assessed
constructionMode: Mode 1: Hand-crafted Expert	117.7 seconds	—	Not assessed
constructionMode: Mode 2: Expert + Static Update	53.57%	—	Not assessed
constructionMode: Mode 2: Expert + Static Update	5,990.79 tokens	—	Not assessed

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results