reward-lens

Reference materials and calibration

Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk

refuted registered

The reading

  1. instrument scorecard AUCs on a real 0.6B trunk match the CPU-organism AUCs within 0.15

    max_abs_auc_difference < 0.15 Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk refuted registered < 0.15 The frozen study "Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk", adjudicated on 19 July 2026 at the registered level of the project's evidence ladder. One frozen study, adjudicated once, on skywork-v2-qwen3-0.6b, over caltransfer-organisms. It does not establish that the same holds on another subject, another dataset or another run. Open the record › refuted

calibration does not transfer toy-to-real; RESULTS opens with this and six cards drop a rung

max_abs_auc_difference >= 0.15 Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk refuted registered < 0.15 The frozen study "Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk", adjudicated on 19 July 2026 at the registered level of the project's evidence ladder. One frozen study, adjudicated once, on skywork-v2-qwen3-0.6b, over caltransfer-organisms. It does not establish that the same holds on another subject, another dataset or another run. Open the record ›

CAL-TRANSFER fired its kill criterion (K-transfer); the registered negative result.
CAL-TRANSFER fired its kill criterion (K-transfer); the registered negative result.

Measurements

per_instrument_auc_differences
Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk refuted registered none registered The frozen study "Instrument calibration transfers from CPU toy trunks to a real 0.6B trunk", adjudicated on 19 July 2026 at the registered level of the project's evidence ladder. One frozen study, adjudicated once, on skywork-v2-qwen3-0.6b, over caltransfer-organisms. It does not establish that the same holds on another subject, another dataset or another run. Nothing was registered against this value in advance, so it is a supporting measurement rather than a tested one. Open the record ›

Provenance

card
CAL-TRANSFER
frozen_at
adjudicated_at
spec_hash
spec:31f5b67bc4168dab4b55ec6a9a588279
study_id
study:campaign-cal-transfer@v1#31f5b67b
Evidence records
b37f71c015ebfd697d7deb2a7efb5f7e
spec_file
campaign-cal-transfer.json