acsincome-shift-calibration

Task gallery / Machine learning / Version 1

Reference solution (oracle): Pass
No-op resistance check: Pass
QA verdict: Not recorded
Aggregate eligibility: Eligible version

The task

Income scoring that survives a regional shift Train a supervised classification model for high-income status under a distribution shift between regions. The file /app/environment/data/acsincome.csv holds 59071 American Community Survey person records: a stable rowid key, ten survey features, a domain column and target, whether income exceeds the threshold. All 50000 source-domain rows are labeled; of the 9071 target…

Excerpt only; not a complete executable task specification. Task ID task_34c1cb48e1c24aec · version 1. Selection status: not fully recorded.

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
Claude Opus 5 · default (unverified)	3/5 · 60.0% [23.1%, 88.2%]	5 / 5	0	GOOD_FAILURE: 2 BAD_FAILURE: 0 GOOD_SUCCESS: 2 BAD_SUCCESS: 1

Legacy evidence

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

Difficulty, with uncertainty

Selected-best difficulty: 40.0% [11.8%, 76.9%]. 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: no.

Every recorded run

12 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
`trial_4a0a85c2e894408e` nop@@	Oct 11, 2026 console	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_75c9d3f5e7974efa` oracle@@	Oct 11, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_20cf2996b173474d` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_4687e4a0e9b34d92` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_769a642457d947d0` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_7bc11fa4189c41a2` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_81bb76a597fc49b6` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	No reward · excludedno_reward	No diagnostic label No diagnostic source	Tokens: — Turns: — Cost: —	Not publicly available
`trial_d7f739d9d6d44f8c` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_ea22d68d20354e9e` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_b0606825b0834a6f` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_f69278d962454ea0` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_1d28a9337b154bfe` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	BAD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available