Development & Admin
Debugging and administrative pages for the benchmarking website.
Baseline Coverage Gaps
Datasets missing common GNN or MLP baseline families
Baseline Improvements
Papers whose reported results improved over the prior at-publication best (includes baseline and proposed methods)
Extraction Anomalies
Post-extraction anomaly checks over stored results
Missing Datasets
Datasets detected in extraction but not yet mapped into DB
Page of Shame
Papers whose reported model values disagree with best reported performance (today) and at-publication bests
Paper Extraction Status
Overview of extraction status
Skipped Papers
Papers rejected by LLM screening
SOTA Claims
Extracted SOTA claims and unrestricted claim audit
Statistics Sources & Discrepancies
Canonical dataset stats vs paper-reported statistics