yogsoth-ai Multi-Criteria Ranking
Multi-dimensional weighted scoring and ranking: decompose the composite question "which gap is better" into several independent dimensions, score each separately, then recombine into a final ranking via weighted summation.
When to Use
- The number of gaps is between 5 and 20
- A systematic, explainable basis for ranking is needed
- Decision-makers need to see each dimension's score (rather than a black-box ranking)
- You will later need to explain to others why a particular gap was chosen
Thinking Framework
Core principle: the reliability of complex judgments comes from decomposition, not holistic intuition.
Break "which gap is most worth attacking" into four independent sub-questions:
- Importance: once this gap is filled, how far will the field advance?
- Feasibility: with existing resources and methods, can it be solved within a reasonable time?
- Novelty: is this gap genuinely under-explored?
- Impact: how broad are the downstream effects after solving it?
Each dimension is scored independently (1–5) to avoid cross-contamination between dimensions. Weights are set by AHP (Analytic Hierarchy Process) or specified by the user. Final score = Σ(dimension score × dimension weight).
Sensitivity check: perturb weights by ±20%; if the ranking is unchanged the conclusion is robust; if the ranking flips it must be flagged as "weight-sensitive".
Budget Gate
| Tier | Gap count | Scoring dimensions | Sensitivity check | Final output |
|---|---|---|---|---|
| S | 5–8 | ≥3 dimensions | Optional | Ranking table + attack suggestions for top 2 gaps |
| M | 9–15 | ≥4 dimensions | Required | Ranking table + attack suggestions for top 3 gaps |
| L | 16–20 | ≥5 dimensions | Required (multi-weight scenarios) | Ranking table + attack suggestions for top 5 gaps + weight-sensitivity report |
Default Reference Flow
- Call the
gap-normalizationSOP: normalize input gaps into a standard format (ID, title, one-sentence description) - Call the
ahp-weightingSOP: determine each dimension's weight (default: importance 0.35, feasibility 0.25, novelty 0.20, impact 0.20) - Call the four scoring SOPs in parallel (
importance-scoring,feasibility-scoring,novelty-scoring,impact-scoring) - Call the
scoring-matrix-constructiontactic: aggregate into a scoring matrix - Call the
priority-sensitivity-testingtactic: perturb weights and check ranking robustness - Call the
priority-synthesisSOP: produce the final ranking + attack suggestions
context-checkpoint
After each round, record:
- The current scoring matrix (all gaps × all dimensions)
- The current weight vector
- The sensitivity-check result (robust / weight-sensitive, annotating any flipped gap pairs)
- The current top-N ranking
Available Tactics
Optional, no fixed order; the final leaf is always a sop.
| Tactic | When to use |
|---|---|
| hypothesis-formation-scoring-matrix-construction | Tactic: orchestrate multi-dimensional scoring SOPs to build a comprehensive assessment matrix for all gaps |
| priority-sensitivity-testing | Tactic: perturb scoring weights to test the robustness of the gap ranking against weight choice |
Available SOPs
Optional, no fixed order; the final leaf is always a sop.
| SOP | When to use |
|---|---|
| gap-normalization | SOP: Unify gaps from different sources into the standard GapRecord format |