B
BayesCore
Bayesian evidence scoring for any structured claim
4.3(10,000 件のレビュー)
有料· US$〜20.00/月
2026年にリリース
Sobre
Drop any document with a claim. Bayescore extracts its IS(subject, criterion) hypothesis, derives falsifiable predicates, and scores each using a two-pass adversarial LLM evaluation. Absence of evidence reduces confidence toward zero. Formula locked: score = Σ(weight × confidence) × 100. We ran it on ourselves. 46/100, Grade D. Five failing predicates. Published because it's right, not flattering. bayescore.com/self-eval
長所
- +Extração de hipóteses IS(subject, criterion)
- +Derivação de predicados falsificáveis
- +Evalucação adversarial LLM em duas etapas
短所
- −Limitação de documentação
- −Dependência de LLM
