Ingestion lifecycle
Current pipeline
No active ingestion job.
System control
Overview
Not refreshed
Idle
Automation
Daily refresh
Source coverage
PDF crawler
Extraction quality
Dataset completeness
Managed operation
Refresh SEC data
Scrape new committee records, resolve and download missing PDFs, parse documents, and rebuild the database as one persisted background job.
Persistent job
Pipeline progress
No ingestion job is currently running.
Crawler diagnostics
Source inventory
Exceptions only
Review queue
Select a proposal
Choose an item from the queue to inspect its source and finalize the extracted record.
Proposal
Review proposal
Controlled action
Train forecasting model
Training uses only source-verified, automatically validated parser rows. Human-finalized exceptions can publish to intelligence without silently changing the model corpus.
Local intelligence
LLM service
Model registry
Recent training runs
Class coverage