hotel-bookings-modeling

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

Booking records from two Portuguese hotels live in /app/environment/data. train.csv carries historical bookings with the label iscanceled; evalfeatures.csv carries a separate, more recent set with the label withheld. codebook.csv describes the columns, and the auxiliary reference/count tables are non-label context only: they do not provide precomputed cancellation rates or held-out outcomes. The environment also inc…

Excerpt only; not a complete executable task specification. Task ID task_6557e1bec8414a9c · 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)	3/3 · 100.0% [43.9%, 100.0%] · preliminary	3 / 3	0	GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 3 BAD_SUCCESS: 0

Legacy evidence

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

Every recorded run

5 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_48cacda2d1fd4868` nop@@	Oct 11, 2026 console	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_888567a018ec4151` oracle@@	Oct 11, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_8b55bec8a74b468f` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 26,697 Turns: 19 Cost: $1.4882	Not publicly available
`trial_f34690a682e74dda` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 49,263 Turns: 37 Cost: $3.0884	Not publicly available
`trial_e32b500ef3624109` Claude Opus 5 · default (unverified)	Oct 11, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 52,298 Turns: 39 Cost: $3.1773	Not publicly available