datasciresearch/generative-process-two-sample

Task gallery / Data processing / data science / Version 1

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: in-house r3 revision; blind read UNCLEAR (sfdata2-605-r3-blind-tie-read.md)
Aggregate eligibility: Eligible version

The task

Please add generativetest(x, y, times, bandwidths, permutations, proposalpairs, noise, channelweights=None, temperature=1.0) to dcor.homogeneity. We need a reproducible two-sample test using Gaussian generative mixtures and permutation-rank fusion. Document it, preserve the existing energy tests, and commit the change. x and y are finite two-dimensional samples with the same positive column count and at least one ro…

Excerpt only; not a complete executable task specification. Task ID sfdata2/generative-two-sample-r3 · version 1. Selection status: known curated delivery cohort.

repo ↗

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 / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
GPT-6 Astra · medium	0/3 · 0.0% [0.0%, 56.1%] · preliminary	0 / 3	1	GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes

Every recorded run

10 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 / model	Date / source	Reward / eligibility	Diagnostic class / source	Resources	Evidence
`generative-two-sample-r3__EHTC93c` nop@@	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__YqjBSKS` nop@@	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__eWzjPUc` nop@@	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__fz73WrV` oracle@@	Oct 18, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__nE5er9e` oracle@@	Oct 18, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__nn2FmJs` oracle@@	Oct 18, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`generative-two-sample-r3__Sg3NbTB` GPT-6 Astra · medium	Oct 18, 2026 delivery	No reward · excludedno_reward	HARNESS_ERROR derived	Tokens: 7,083 Turns: 13 Cost: —	Not publicly available
`generative-two-sample-r3__XZuGHYk` GPT-6 Astra · medium	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: 16,620 Turns: 39 Cost: —	Not publicly available
`generative-two-sample-r3__fM6psSG` GPT-6 Astra · medium	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: 8,892 Turns: 17 Cost: —	Not publicly available
`generative-two-sample-r3__pRoYPzL` GPT-6 Astra · medium	Oct 18, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: 10,058 Turns: 18 Cost: —	Not publicly available