graph_expand → biblio_ingest bridge tool¶
biblio_graph_expand produces a graph_candidates.json with 100 candidate references, but there's no tool to filter or promote candidates into the library. The current workflow requires:
1. Read the JSON manually
2. Extract DOIs for relevant papers
3. Call biblio_ingest with the DOI list
Suggested tool: biblio_graph_promote(filter?, top_n?, min_citations?, tags?)¶
- Reads
graph_candidates.json - Optionally filters by keyword, citation count, year range
- Promotes selected candidates to
imported.bibvia the ingest pipeline - Deduplicates against existing library
This would make the citation graph expansion → library building loop fully agentic.
Source context: pixecog¶
PixEcog (pixecog): Neuropixels and ECoG dataset and analysis
Recent commits:
8dc0d9d Pipeline docs: gitignore docs/pipelines/, relocate hand-authored files
96cd1ec Refactor sharpwaveripple/contracts: extract generic helpers to utils/io, remove pipelines __init__.py
36f9326 Add result note directory and sample note
README:
type: readme
Quick Start for Collaborators¶
Follow this checklist to get started with Pixecog documentation and workflows.
🐀 Pixecog Project — Compact Overview¶
Core principles
- One immutable BIDS raw dataset (
raw/) as the canonical baseline - Each analysis pipeline ha
Related Notes¶
- idea-arash-20260409-214919-989861.md — Both propose new biblio MCP tools to close gaps in the DOI/reference ingestion workflow
- idea-arash-20260409-210844-158219.md — Proposes a systematic biblio × questio literature processing bridge — shares the goal of making the graph-expand → library loop fully agentic
- idea-arash-20260326-155537-817950.md — Another biblio feature request (async docling) — same pattern of extending biblio MCP with missing pipeline automation
- idea-arash-20260403-172004-817050.md — Covers skill candidates for the projio ecosystem; biblio_graph_promote would fit as a new projio skill