| name | progress-curve-construction |
| description | Build performance-over-time progress curves with inflection detection |
| execution | tactic |
| dependencies | {"sops":["baseline-synthesis","headroom-estimation","progress-curve-fitting"]} |
Progress Curve Construction
Purpose
Transform historical performance data into temporal progress curves that reveal the rate of improvement, paradigm shifts, and saturation trends. Enables quantitative headroom analysis and identifies where the field needs breakthroughs vs. incremental refinement.
Stages
Stage 1: Time-Series Arrangement
Organize all historical scores into chronological sequences:
- Group by (dataset, metric) pairs
- Assign dates from paper publication or submission
- Track the SOTA frontier (envelope of best scores over time)
- Identify the method responsible for each SOTA advance
Yield: Chronological score sequences per benchmark.
Stage 2: Curve Fitting
Fit parametric models to the SOTA frontier:
- Logarithmic: diminishing returns pattern
- Linear: steady improvement
- Sigmoid: approaching saturation
- Stepped: punctuated equilibrium (paradigm shifts)
- Compute goodness-of-fit metrics for model selection
Yield: Fitted curves with parameters and confidence bands.
Stage 3: Inflection Point Detection
