Reward thermodynamics

Same-recipe scale ladder with frozen 8B extrapolation

mixed registered

The reading

  1. at least 2 of 3 capture-only internal quantities land in their pre-frozen 8B intervals

    ladder_8b_metrics_in_interval >= 2 0.65 Same-recipe scale ladder with frozen 8B extrapolation mixed registered >= 2 The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. It does not establish that the same holds on another subject, another dataset or another run. Open the record › confirmed

  2. the extrapolation beats a no-trend (equal-to-4B) baseline

    ladder_extrap_minus_flat_error < 0 Same-recipe scale ladder with frozen 8B extrapolation mixed registered confidence interval -0.5311824800459731 to 2.4359016583798008 < 0 The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. It does not establish that the same holds on another subject, another dataset or another run. Open the record › refuted

LADDER against its frozen predictions: mixed.
LADDER against its frozen predictions: mixed.

Measurements

ladder_extrap_minus_flat_error_ci_low
Same-recipe scale ladder with frozen 8B extrapolation mixed registered confidence interval -0.5311824800459731 to 2.4359016583798008 < 0 The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. It does not establish that the same holds on another subject, another dataset or another run. Open the record ›
ladder_extrap_minus_flat_error_ci_high
Same-recipe scale ladder with frozen 8B extrapolation mixed registered confidence interval -0.5311824800459731 to 2.4359016583798008 < 0 The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. It does not establish that the same holds on another subject, another dataset or another run. Open the record ›
ladder_8b_crystallization_in_interval
Same-recipe scale ladder with frozen 8B extrapolation mixed registered none registered The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. 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 ›
ladder_8b_chi_teacher_in_interval
Same-recipe scale ladder with frozen 8B extrapolation mixed registered none registered The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. 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 ›
ladder_8b_snr_in_interval
Same-recipe scale ladder with frozen 8B extrapolation mixed registered none registered The frozen study "Same-recipe scale ladder with frozen 8B extrapolation", 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 and skywork-v2-qwen3-1.7b and skywork-v2-qwen3-4b and skywork-v2-qwen3-8b, over rb2-full. 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
LADDER
frozen_at
adjudicated_at
spec_hash
spec:0023527a360de5b616a0aa5a7bb6c3cf
study_id
study:campaign-ladder@v1#0023527a