Task gallery / Data processing / data science / Version 1
Reference solution (oracle)
Pass
No-op resistance check
Pass
QA verdict
in-house design (no vendor PR); see docs/reports/datasci-research-v5
Aggregate eligibility
Eligible version

The task

Randomization test with an autoregressive instrument Users of pyfixest run local projections with instruments such as weather, cloud cover or commodity prices, which are persistent over time. Picchetti (2026, arXiv:2610.19075) proposes randomization tests for short panels in which the instrument follows a first-order autoregression with unknown persistence and only its innovations are as good as randomly assigned. T…

Excerpt only; not a complete executable task specification. Task ID sfdata2/pyfixest-picchetti-ri · version 1. Selection status: known curated delivery cohort.

Results by model and effort

This exact task version only. Every rate is passes / valid runs with a Wilson 95% interval; n≤2 remains counts only. Macro aggregation does not apply within a single task. Baselines are summarized in the quality gates, not ranked. A passed no-op resistance check means that doing nothing did not solve the task.

Current evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes
GPT-6 Astra · medium2/20 / 22
GOOD_FAILURE: 0
BAD_FAILURE: 0
GOOD_SUCCESS: 0
BAD_SUCCESS: 0

Legacy evidence

Model / effortVerifier result [95% Wilson]Diagnostic labels / validHARNESS_ERROR · excludedOutcome classes

Every recorded run

28 recorded trials, including controls. Diagnostic labels do not replace verifier reward. Labels and quality checks are source declarations, not independently attested here. Internal evidence remains private; a missing public URL is shown explicitly. Records with invalid or absent rewards are not scored.

Run / modelDate / sourceReward / eligibilityDiagnostic class / sourceResourcesEvidence
pyfixest-picchetti-ri__3A89VBp
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__D6LQQYq
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__PPGRgvw
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__XqL9jFN
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__Z9msops
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__evoHLVt
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__3FhzBmb
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__Ew62dAQ
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__GAhMQKR
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__dxZDuWo
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__r88itvy
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__sHdXGWr
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__CBqXr7j
GPT-6 Astra · medium
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: 22,266
Turns: 40
Cost: —
Not publicly available
pyfixest-picchetti-ri__xq4S5G9
GPT-6 Astra · medium
Oct 18, 2026
delivery
No reward · excludedno_rewardHARNESS_ERROR
derived
Tokens: 6,144
Turns: 7
Cost: —
Not publicly available
pyfixest-picchetti-ri__URrnazM
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__YLUgvSU
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__c5Ep57B
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__hGsLRH4
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__rq9Uy6g
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__sACPma5
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__5oSBAvH
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__9X6EBaB
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__sevxeXk
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__tMvNdCp
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__uF8jZDW
nop@@
Oct 18, 2026
delivery
0 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__zrEzKJW
oracle@@
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: —
Turns: —
Cost: —
Not publicly available
pyfixest-picchetti-ri__Fdi2RJJ
GPT-6 Astra · medium
Oct 18, 2026
delivery
1 · validNo diagnostic label
derived
Tokens: 15,555
Turns: 26
Cost: —
Not publicly available
pyfixest-picchetti-ri__knfBNFa
GPT-6 Astra · medium
Oct 18, 2026
delivery
No reward · excludedno_rewardHARNESS_ERROR
derived
Tokens: 15,868
Turns: 27
Cost: —
Not publicly available