GREP · Software mentions — V1 (GPU)
ACTIVEcomputer-science · CONTAINER · GPU
Reads scientific PDFs and pulls out every software name, tool and library the authors used, with its location in the text, a type and a purpose. This leaf runs V1, the crowd's first-generation model. GREP runs three independently trained models over the same papers; a mention enters the final record only when at least two of the three find the same span. The GPU build produces exactly the same mentions as the CPU build and clears a unit in two to three minutes instead of twenty. A work unit is about ten papers, roughly 5 MB in and one small JSON out. Every unit goes to three different volunteers and the head accepts it once two produce matching output. Needs an NVIDIA GPU with 4 GB of VRAM, plus 6 GB of free memory and 20 GB of free disk. The model ships inside a one-time 5.6 GB image download, after which the work runs entirely offline.
Measured accuracy (character-level F1; higher is better):
Model dev test Softcite SoFAIR clean ---------------------------------------------------------- f14 0.823 0.819 0.8653 0.8909 f13 0.814 0.807 0.8637 0.8854 V1 0.800 0.781 0.8096 0.7950 <- this leaf crowd (2-of-3) 0.833 0.828 0.8648 0.8940
Throughput
- Queued
- 137
- Running
- 0
- Validated
- 3
- Volunteers
- 0
What your machine needs
The head only sends this leaf's work to machines that meet these.
- CPU cores
- 1 core
- Free memory
- 8,000 MB
- Free disk
- 20,000 MB
- GPU
- NVIDIA · 4,096 MB VRAM
What this task may use
Hard limits enforced on your machine. The task is stopped if it exceeds them.
- Memory limit
- 8,000 MB
- Disk limit
- 4,096 MB
- CPU time limit
- 24 hours
- Network access
- None — runs offline
Execution
- Runtime
- CONTAINER
- Image
- ghcr.io/jring-o/extract2-student:2.1-v1-gpu
Validation
- Redundancy
- 3×
- Comparison
- NUMERIC_TOLERANCE
- Tolerance
- 0.01
- Max retries
- 3
Contribute
To donate compute to this leaf, download the open-source lettuce-volunteer binary for your platform from GitHub releases (per-platform install steps are in the setup guide), then run:
lettuce-volunteer init lettuce-volunteer attach --server infra.scios.tech lettuce-volunteer leafs enable extract2-student-crowd-v1-gpu lettuce-volunteer start
The CLI fetches this leaf's work units, runs them inside the limits above, and submits results with signed credit attestations — all automatically.