feat: Add evaluation

[rmitsch]

Description

Adds evaluation capabilities to predictive tasks.

Related Issues

-

Changes Made

• Adds evaluation capabilities (precise or with LLM judges) to all predictive tasks.
• Standardize score instead of confidence in terminology and prompts.

Checklist

• Tests have been extended to cover changes in functionality
• Existing and new tests succeed
• Documentation updated (if applicable)
• Related issues linked

Screenshots/Examples (if applicable)

[codecov]

Codecov Report

❌ Patch coverage is 87.79221% with 47 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
sieves/tasks/predictive/classification/core.py	83.95%	13 Missing ⚠️
sieves/tasks/predictive/core.py	84.00%	8 Missing ⚠️
sieves/tasks/predictive/ner/core.py	83.33%	5 Missing ⚠️
sieves/tasks/predictive/evaluation.py	80.00%	4 Missing ⚠️
...es/tasks/predictive/information_extraction/core.py	91.83%	4 Missing ⚠️
sieves/tasks/predictive/schemas/classification.py	70.00%	3 Missing ⚠️
sieves/tasks/predictive/sentiment_analysis/core.py	90.00%	3 Missing ⚠️
sieves/pipeline/core.py	83.33%	2 Missing ⚠️
sieves/tasks/predictive/pii_masking/core.py	92.59%	2 Missing ⚠️
...ieves/tasks/predictive/relation_extraction/core.py	92.59%	2 Missing ⚠️
... and 1 more

Additional details and impacted files

@@            Coverage Diff             @@
##             main     #247      +/-   ##
==========================================
- Coverage   92.80%   92.70%   -0.11%     
==========================================
  Files          78       79       +1     
  Lines        4087     4413     +326     
==========================================
+ Hits         3793     4091     +298     
- Misses        294      322      +28     

Files with missing lines	Coverage Δ
sieves/data/doc.py	96.22% <100.00%> (+0.07%)	⬆️
sieves/tasks/predictive/classification/bridges.py	94.40% <100.00%> (ø)
sieves/tasks/predictive/question_answering/core.py	94.36% <100.00%> (+0.92%)	⬆️
sieves/tasks/predictive/schemas/summarization.py	100.00% <100.00%> (ø)
...ves/tasks/predictive/sentiment_analysis/bridges.py	98.37% <100.00%> (ø)
sieves/tasks/predictive/summarization/core.py	96.61% <100.00%> (+0.69%)	⬆️
sieves/tasks/predictive/translation/core.py	96.61% <100.00%> (+0.69%)	⬆️
sieves/tasks/core.py	96.00% <75.00%> (-1.83%)	⬇️
sieves/pipeline/core.py	92.64% <83.33%> (-0.91%)	⬇️
sieves/tasks/predictive/pii_masking/core.py	95.69% <92.59%> (-1.36%)	⬇️
... and 8 more

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.