pino-source-code / src /pino /upload_data.py

Commit History

review-response: upload src/pino/upload_data.py
3ae77c2
verified

mattbitzesty commited on

pimt v9 substantivity gbm train publish path
c9282b0

Matthew Ford commited on

Add Fraterworks ingestion and upload data split support
2671b56

Matthew Ford commited on

perf(train): avoid Hugging Face Dataset round-trip during formula-disjoint split
cbadf3b
unverified

mattbitzesty commited on

feat(train): pin 597 single-molecule controls exclusively to training
bd9df8b
unverified

mattbitzesty commited on

fix(upload,train): use load_dataset select and fingerprint-based leakage check
78283bd
unverified

mattbitzesty commited on

feat(upload,train): formula-disjoint split with full corpus recovery
a1355e6
unverified

mattbitzesty commited on

fix(upload,train): enforce strict molecule-disjoint isolation
f63c153
unverified

mattbitzesty commited on

feat(upload,train): directive-compliant molecule-disjoint split
d3bb757
unverified

mattbitzesty commited on

feat(train,upload): multi-task training with InfoNCE and molecule-disjoint upload
a2d3e6a
unverified

mattbitzesty commited on

feat(data): wire structured Poucher profiles into text conditioning pipeline
78fcbf4
unverified

mattbitzesty commited on

fix(upload): cast genre to ClassLabel; align PIMT forward with fused labels and publication metrics
e17936d
unverified

mattbitzesty commited on

feat(pino): literature seed integration, stratified dataset split, registry enrichment, and Space sync
31ee18f
unverified

mattbitzesty commited on