Published September 9, 2026 | Version 2.0.0

Elicitation format changes zero-shot classification accuracy in a medical vision-language model: code and run records

Authors/Creators

  • 1. University of Florida

Description

Code, configurations, prompts and sealed run records for a two-center evaluation of elicitation format on nine-class colorectal histopathology classification (PathMNIST, MedMNIST v2) with MedGemma-27b-it.

Holding the prompt fixed down to its per-class cue block and varying only the requested response format, asking for a probability over all nine classes rather than a ranked top-3 costs 14.8 accuracy points on validation and 13.4 at an external clinical center. An answer-suppression control locates the cost in the closing sentence forbidding commentary, reasoning and a chosen answer rather than in the requested cardinality.

The served endpoint is not reproducible by a third party, so every raw model response is released: each of the 123 run directories carries its configuration, that configuration's SHA-256, the patch manifest, the raw responses, per-patch token usage, run metadata and a checksum manifest over all of it. Every number in the accompanying article resolves to exactly one entry of the released append-only results log.

No model weights are redistributed.

Notes

The accompanying manuscript is in preparation and is not yet deposited or published; this record archives the code and run data only. Inference ran against one hosted endpoint that a third party cannot reproduce, which is why every raw model response is included: each of the 123 run and analysis directories carries its configuration, that configuration's SHA-256, the patch manifest, the raw responses, per-patch token usage, run metadata and a checksum manifest, and all 66 directories carrying a manifest verify against it in this archive.

Files

Files (18.4 MB)

Name Size
md5:de0b564671ca6d739b41866502b0b04f
18.4 MB Download

Additional details