Evidence pipeline
Literature to framework,
fully traceable.
Select one category or launch all ten sequentially. For each, the pipeline retrieves literature, verifies paragraph evidence, induces a taxonomy branch, and updates three age-specific rubric cards.
Latest activity
Jobs
| Run | Status | Created | Attempt | Mode | Risk category | Actions |
|---|
Agentic evidence-to-framework workflow
Each pipeline invocation processes one F01–F10 category. The ALL option invokes the same workflow ten times in one batch job, retaining a separate evidence store and release per category. Evidence induces a taxonomy branch before alignment to the frozen seed and construction of age-specific rubrics.
Retrieval coverage
Up to 500 results per core engine are shown before eligibility screening. Missing engines remain visible.
Google Scholar coverage & downloads
Checking live provider availability…
Select a run to inspect Scholar coverage.
Source funnel
Dynamic Drop
Screening decisions
Jev checks title and abstract relevance first. Population-first and Risk-first Agents then make independent decisions; material disagreement invokes adjudication.
Ranked papers and Agent probability
| Rank | Family | Paper | Origin | RRF | Citation | Agent p | Jev p | Decision |
|---|
Evidence explorer
Inspect natural-paragraph labeling and verified evidence packages. Public excerpts are limited to 280 characters.
Natural paragraphs and labels
| Paragraph | Page | Label | Scores | Evidence roles | Excerpt |
|---|
Trace an entity
Taxonomy induction
Local type paths are merged globally, hierarchy edges are independently verified, and only then aligned to the frozen seed.
Validated local type paths
Verified taxonomy nodes
Seed and rubric patches
Candidate release
Formal taxonomy and rubric v1 remain unchanged. Public downloads are sanitized allowlisted artifacts.