원클릭으로
knowledge-acquisition
knowledge-acquisition에는 yogsoth-ai에서 수집한 skills 80개가 있으며, 저장소 수준 직업 범위와 사이트 내 skill 상세 페이지를 제공합니다.
이 저장소의 skills
SOTA Performance Baseline Campaign — 5 strategies for systematically collecting, standardizing, and analyzing performance data across methods. Produces standardized comparison tables, progress curves, and headroom analysis.
Assess systematic biases in the evidence body — publication bias, reporting bias, and selective outcome reporting. Budget: 40 studies, 40 effect sizes, 40 web searches.
Track evidence accumulation over time — cumulative meta-analysis protocol design. Budget: 40 studies, 40 effect sizes, 30 web searches.
Design structured data extraction form for systematic meta-analysis data collection
Systematically extract effect sizes and conditions from papers for meta-analytic synthesis
Determine effect size types and calculation methods for meta-analytic synthesis
Build evidence network graph for network meta-analysis — nodes, edges, geometry assessment
Plan the statistical synthesis approach — model selection, heterogeneity strategy, and reporting
Explain why different studies reach different conclusions — heterogeneity investigation protocol. Budget: 30 studies, 30 effect sizes, 50 web searches.
Identify and classify sources of between-study heterogeneity (clinical, methodological, statistical)
Define inclusion/exclusion criteria for systematic study selection in meta-analysis
Cross-Study Statistical Synthesis Campaign — 5 strategies for systematic collection and methodological planning of multi-study evidence synthesis. Covers pairwise, network, cumulative meta-analysis, heterogeneity investigation, and bias detection. Stops at protocol design (no computation).
Produce final meta-analysis protocol document assembling all planning outputs into PRISMA-compliant protocol
Compare N methods simultaneously including indirect evidence — network meta-analysis protocol design. Budget: 50 studies, 80 effect sizes, 60 web searches.
Compare two methods across multiple studies — paired meta-analysis protocol design. Budget: 30 studies, 30 effect sizes, 40 web searches.
Construct PICO/PECO framework for the meta-analysis research question
Plan funnel plots, Egger's test, trim-and-fill, p-curve, and selection model analyses for publication bias
Methodological quality and bias risk assessment of included studies using validated tools
Assess methodological bias using RoB2, PROBAST, or QUADAS-2 validated tools
Design leave-one-out, influence diagnostics, subgroup analyses, and robustness checks
Detect annotation artifacts and shortcuts in benchmarks
Evaluation Methodology Archaeology Campaign — 5 strategies for systematic analysis of AI/ML benchmarks, metrics, and leaderboards. Reveals construct validity issues, saturation, data contamination, and evaluation protocol inconsistencies.
Systematic quality assessment using BetterBench 46-criterion framework — 5 benchmarks, 30 papers, 40 web searches
Identify and catalog all relevant benchmarks in target domain
Produce final structured audit report
Build capability taxonomy, map existing benchmark coverage
Evaluate whether benchmark measures its claimed capability
Detect train-test data leakage and memorization artifacts
Map evaluation coverage, identify untested capability dimensions — 20 benchmarks, 30 papers, 50 web searches
Assess documentation completeness against BetterBench/Datasheets standards
Compare implementation differences of same benchmark across papers
Analyze leaderboard score distributions, compression, selective reporting
Decompose composite metrics into constituent signals, analyze polarity and ceiling effects
Extract evaluation protocol parameters from papers
Analyze evaluation protocol differences across papers for same benchmark — 5 benchmarks, 60 papers, 30 web searches
Track score trajectories, detect saturation/failure points — 15 benchmarks, 50 papers, 60 web searches
Collect historical scores, fit saturation curves, detect inflection points
Challenge construct validity — does benchmark measure claimed capability? — 3 benchmarks, 40 papers, 30 web searches
Patent claim syntax parsing — independent/dependent relationships and element extraction
Determine patent legal status — active, expired, pending, lapsed, or revoked