syncrope/nonconformist-kernel-quantile-path

Task gallery / Data processing / data science / Version 2

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: REVISE (#604 v2 ledger: 24 FAIL incl. S04/S16/S18/S22)
Aggregate eligibility: Eligible version

The task

Add kernel conditional conformal regression to the nonconformist checkout at /repo. We need the complete regularized kernel quantile solution paths so we can examine smoothness and invert the augmented test-score fit without repeatedly fitting a quantile model on a score grid. Integrate this with the repository's nonconformity scorers and regression workflow. Computation is CPU-only; dependencies are installed and i…

Excerpt only; not a complete executable task specification. Task ID sfdata2/nonconformist-kernel-quantile-path-v2 · version 2. 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	0/5 · 0.0% [0.0%, 43.4%]	5 / 5	0	GOOD_FAILURE: 5 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

Difficulty, with uncertainty

Selected-best difficulty: 100.0% [56.6%, 100.0%]. This is one minus the best measured current-row pass rate among rows with at least five valid runs.

The maximum is selected from the observed rows, so the estimate is optimistic. Its Wilson interval is not adjusted for model selection. “Hard” requires qualifying GOOD_FAILURE evidence; the threshold flag additionally requires the interval and recorded quality gates to meet the documented rule. This is not independent validation. Threshold flag: yes.

Every recorded run

17 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
`nonconformist-kernel-quantile-pa__9Qf9Rks` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__RRgeDeX` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__ZGk2fSq` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__bmaikz7` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__fer86An` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__iLTyfaM` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__7ZZRHYL` GPT-6 Astra · medium	Oct 20, 2026 delivery	0 · valid	GOOD_FAILURE independent-review	Tokens: 22,948 Turns: 47 Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__GmkkJW2` GPT-6 Astra · medium	Oct 20, 2026 delivery	0 · valid	GOOD_FAILURE independent-review	Tokens: 23,386 Turns: 53 Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__jnDHZnK` GPT-6 Astra · medium	Oct 20, 2026 delivery	0 · valid	GOOD_FAILURE independent-review	Tokens: 26,782 Turns: 65 Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__6uio5my` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__7PWvMQm` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__M8VwqfH` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__S69KBw4` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__k2MZk2o` nop@@	Oct 20, 2026 delivery	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__xeTV5mb` oracle@@	Oct 20, 2026 delivery	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__McUsivq` GPT-6 Astra · medium	Oct 20, 2026 delivery	0 · valid	GOOD_FAILURE independent-review	Tokens: 20,863 Turns: 51 Cost: —	Not publicly available
`nonconformist-kernel-quantile-pa__pJBCjV5` GPT-6 Astra · medium	Oct 20, 2026 delivery	0 · valid	GOOD_FAILURE independent-review	Tokens: 14,740 Turns: 27 Cost: —	Not publicly available