chore(deps): Bump github.com/plexusone/structured-evaluation from 0.3.1 to 0.5.0

[dependabot]

Bumps github.com/plexusone/structured-evaluation from 0.3.1 to 0.5.0.

Release notes

Sourced from github.com/plexusone/structured-evaluation's releases.

v0.5.0

Release Notes: v0.5.0

Full Changelog: plexusone/structured-evaluation@v0.4.0...v0.5.0

v0.4.0

Release Notes: v0.4.0

Full Changelog: plexusone/structured-evaluation@v0.3.1...v0.4.0

Changelog

Sourced from github.com/plexusone/structured-evaluation's changelog.

[v0.5.0] - 2026-05-23

Highlights

• Likert scale (1-5) support for human comparison studies
• Inter-rater reliability (IRR) metrics for LLM calibration

Added

• ScaleTypeLikert scale type with configurable anchors and thresholds
• LikertConfig with min/max values and pass/partial thresholds
• LikertAnchor for describing score levels (value, label, description)
• StandardLikert5Anchors() helper for standard 1-5 scale
• WithLikert5() and WithLikert() methods for creating Likert categories
• LikertToCategorical() for converting numeric scores to pass/partial/fail
• Optional NumericScore field on CategoryResult for dual-scale support
• NewCategoryResultWithNumeric() for creating results with both categorical and numeric scores
• NewCategoryResultFromLikert() for creating results from Likert scores
• IRRMetrics type with exact agreement, adjacent agreement, MAD, and Pearson correlation
• ComputeIRR() for computing IRR from rating pairs
• ComputeIRRFromResults() for comparing two sets of CategoryResults
• CategoricalAgreement type with confusion matrix for categorical comparisons
• ComputeCategoricalAgreement() for categorical IRR analysis

Documentation

• Added Likert Scales documentation page
• Added Inter-Rater Reliability documentation page

Tests

• Comprehensive tests for Likert scales and IRR metrics

[v0.4.0] - 2026-05-23

Highlights

• Switch from numeric scores to categorical pass/partial/fail values
• New terminal and markdown renderers for evaluation reports

Added

• render/terminal package with ANSI-colored output and UTF8 icons (cb692fe)
• render/markdown package for Markdown report generation (cb692fe)
• CLI terminal and markdown render format options (8ec8893)

Changed

• Breaking: CategoryScore renamed to CategoryResult with Score field (pass/partial/fail) (2c84023)
• Breaking: ScoreStatus renamed to ScoreValue with values pass/partial/fail (2c84023)

... (truncated)

Commits

• ba1e8fa docs: README.md: update shields
• 004bdc6 docs: update changelog and README for v0.5.0
• 665f0c1 docs: add Likert scales and IRR documentation
• 7e25548 test(evaluation): add tests for Likert scales and IRR metrics
• 98f11eb feat(evaluation): add inter-rater reliability metrics
• 273776a feat(evaluation): add optional numeric score to CategoryResult
• 96e608b feat(evaluation): add Likert scale support for human comparison studies
• c35a8d7 docs: consolidate release notes into docs/releases/
• fd7efa8 docs: add MkDocs documentation site
• 3a21bb5 docs: update changelog and README for v0.4.0
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)