SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery
Scientific work increasingly spans heterogeneous artifacts -- papers, code, datasets, scientific file formats, model outputs, figures, manuscripts, and team decisions -- yet general-purpose AI assistants rarely preserve these objects as a coherent, auditable research state. We present SciForge, a multimodal research-native AI workbench that reserves the graphical interface for human judgment while search, parsing, model routing, workflow execution, plotting, writing, and presentation generation run as modular agent-accessible services. SciForge is built around five pillars: (i) \emph{goal-scop
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzySimilar title/name (fuzzy) · 87%CodeForge-15B →
“Fuzzy title match (0.94): “SciForge: An AI-Native, Multimodal Workbench for Scientific ” ≈ “CodeForge-15B””
- FuzzyOverlapping authors or contributors · 62%marimo-team/marimo →
“Shared author/contributor keys: team”
- FuzzyOverlapping authors or contributors · 62%recommenders-team/recommenders →
“Shared author/contributor keys: team”
- FuzzyOverlapping authors or contributors · 62%google-research/google-research →
“Shared author/contributor keys: sun”
- FuzzyOverlapping authors or contributors · 62%modular/modular →
“Shared author/contributor keys: liu”
- LinkedLinked via arxiv author · 85%SciForge Team →
“SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery”
- LinkedLinked via arxiv author · 85%Zhangyang Gao →
“SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery”
- LinkedLinked via arxiv author · 85%Minghao Fang →
“SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery”