diff --git "a/index.html" "b/index.html" --- "a/index.html" +++ "b/index.html" @@ -1,19 +1,3357 @@ - - - - - - My static Space - - - -
-

Welcome to your static Space!

-

You can modify this app directly by editing index.html in the Files and versions tab.

-

- Also don't forget to check the - Spaces documentation. -

-
- - + + + + + + Agentic Reproducibility Engine | Research Intelligence + + + +
+
+
+ +
+ AGENTIC ENGINE + Research Reproducibility Intelligence +
+
+
+ + + + + + + + + +
+
+ +
+ + +
+ + +
+
+ Audit Pipeline + 0 events + 0 evidence +
+
+ score pending + +
+
+ +
+
+
+ Analysis Trace + SSE + REST +
+
+
No trace events yet.
+
+
+
+
+ Evidence + live resolvers +
+
+
No live evidence resolved yet.
+
+
+
+
+ + +
+ +
+
+
+
+
Workspace dashboard
+

Agentic Reproducibility Engine

+

Submit papers, monitor multi-agent audits, inspect resolver-backed evidence, and package audit-ready reproducibility reports from one operational workspace.

+
+
+ + +
+
+ +
+
+
+
+
Evidence-first audit orchestration
+

The engine turns a paper into validated evidence, reproducibility risk scores, consistency challenges, and an audit-ready report.

+

Every run streams structured reasoning artifacts, approved tool calls, resolver outputs, critique loops, and report provenance as the workflow executes.

+
+ + +
+
+
+
+
+ Live Execution Stream + SSE +
+
+
Run an audit to stream model calls, tool calls, consistency checks, and report assembly here.
+
+
+
+
+ + + +
+
+
+
Recent audits
+

Library preview

+
+ +
+
+
+ +
+
Resolver Coverage
+
+
+
+
+ +
+
+
+
New audit
+

Submit a paper and configure autonomy

+

Paste an arXiv ID, DOI, URL, or paper notes. The frontend fills the live audit payload and the backend handles the agent/tool execution.

+
+
+ + +
+
+ +
+
+
+
+ + +
+
+ + +
+
+ + +
+
+ + +
+
+ + +
+
+
+ + +
+
+ +
+
+
+
Audit results
+

Verifier-backed reproducibility report

+

Run an audit to replace this with live model, evidence, and report data.

+
+
+ + + +
+
+ +
+
+
+
+
+
+
+
+
+
Evidence Explorer
+
+
+ +
+
+ + + + +
+
+
+
+
+ +
+
+
+
Audit library
+

Saved audit runs

+

Search completed local runs and saved drafts by title, arXiv ID, decision, or evidence source.

+
+
+ + +
+
+
+
+
+ + +
+
+ + + + +
+
+
+
+
+ +
+
+
+
Benchmarks and insights
+

Evidence discipline for reproducibility scoring

+

Benchmarks expose resolver coverage, score distribution, tool availability, and AMD/Qwen deployment proof points for judges.

+
+
+ + +
+
+
+
+
Score Distribution
+
+
+
+
+
+
+
Tool and deployment readiness
+
+
+
+
+
+ + + + +
+ + + +