Polish README: drop placeholder copy, add YAML cross-links to related artifacts

README.md

@@ -21,18 +21,13 @@ tags:
 - semantic-scholar
 - openalex
 - scholarly
+datasets:
+- barissozudogru/openalex-concepts
+- barissozudogru/federated-search-traces
 ---
 
 # Research Papers Federated Search
 
-<!-- USER_VOICE_INTRO_PARAGRAPH
-Write 3-5 sentences in your own voice. Suggested angles (pick one):
-- Origin story: what specifically frustrated you that drove building this
-- Opinion: what existing tools get wrong about federated search
-- Use case: what concrete research workflow this unblocked for you
-Do NOT let Claude write this. Authentic voice is the whole point.
--->
-
 ## What this does
 
 Federated search across four academic sources in a single call:
@@ -44,16 +39,6 @@ Federated search across four academic sources in a single call:
 
 Results are deduplicated by DOI when available, then by `(source, source_id)` so the same arXiv preprint surfaced through multiple sources collapses to one row.
 
-## Known limitations
-
-<!-- USER_VOICE_LIMITATIONS_BULLETS
-Write 2-4 honest bullets about what doesn't yet work or has rough edges.
-Examples of the right texture (do NOT copy these verbatim, write your own):
-- Topic detection is keyword-based here; embeddings backend isn't wired into the Space
-- Citation graph and BibTeX export are in the full MCP server but not in this demo
-- S2 throttles aggressively without an API key; expect partial results for high-traffic queries
--->
-
 ## Cold start
 
 This Space sleeps when idle. First query after a quiet period takes 30-60 seconds for the container to wake up. Subsequent queries are fast.