syncrope/uniseg-bidi-uax9

Task gallery / DeepSWE (long-horizon SWE) / Version 1

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

The task

uniseg (github.com/rivo/uniseg) implements UAX #29 segmentation, UAX #14 line breaking, and monospace width for Unicode 15.0.0, but has no bidirectional-text support. Implement the complete Unicode Bidirectional Algorithm, UAX #9 as of Unicode 15.0.0, in the root uniseg package, without adding module dependencies, with this exact public API: - Constants BidiLTR = 0, BidiRTL = 1, BidiAuto = 2; any other direction val…

Excerpt only; not a complete executable task specification. Task ID task_5c156a1be6db47fc · 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)	1/5 · 20.0% [3.6%, 62.4%]	5 / 5	0	GOOD_FAILURE: 3 BAD_FAILURE: 1 GOOD_SUCCESS: 1 BAD_SUCCESS: 0
GPT-5.6-sol · default (unverified)	4/5 · 80.0% [37.6%, 96.4%]	5 / 5	0	GOOD_FAILURE: 1 BAD_FAILURE: 0 GOOD_SUCCESS: 4 BAD_SUCCESS: 0

Legacy evidence

Model / effort	Verifier result [95% Wilson]	Diagnostic labels / valid	HARNESS_ERROR · excluded	Outcome classes
Claude Opus 4.8 · default (unverified)	4/5 · 80.0% [37.6%, 96.4%]	5 / 5	0	GOOD_FAILURE: 0 BAD_FAILURE: 1 GOOD_SUCCESS: 4 BAD_SUCCESS: 0
Gemini Flash (latest alias) · default (unverified)	0/5 · 0.0% [0.0%, 43.4%]	5 / 5	0	GOOD_FAILURE: 5 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Difficulty, with uncertainty

Selected-best difficulty: 20.0% [3.6%, 62.4%]. 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

20 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_00061402e9ea4dd8` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_4bd0745d998b4341` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	0 · valid	BAD_FAILURE frozen-classifier	Tokens: 112,987 Turns: 80 Cost: $9.4117	Not publicly available
`trial_9a4c9cc3536d4a91` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 69,473 Turns: 50 Cost: $5.5059	Not publicly available
`trial_a903b09911334223` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 84,781 Turns: 54 Cost: $5.8845	Not publicly available
`trial_ffdb209e810845b4` Claude Opus 4.8 · default (unverified)	Aug 29, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 61,766 Turns: 44 Cost: $4.3196	Not publicly available
`trial_2bb7889141254e26` Claude Opus 5 · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 98,983 Turns: 47 Cost: $6.2606	Not publicly available
`trial_5cc96a178b3b4dd6` Claude Opus 5 · default (unverified)	Sep 1, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: 89,237 Turns: 42 Cost: $5.8938	Not publicly available
`trial_5f7c0936744141ae` Claude Opus 5 · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 90,249 Turns: 42 Cost: $5.6872	Not publicly available
`trial_61162f4194784053` Claude Opus 5 · default (unverified)	Sep 1, 2026 console	0 · valid	BAD_FAILURE frozen-classifier	Tokens: 134,785 Turns: 73 Cost: $8.9662	Not publicly available
`trial_c168f0fdf6b3434f` Claude Opus 5 · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: 138,018 Turns: 53 Cost: $8.3929	Not publicly available
`trial_191b94b46e484577` Gemini Flash (latest alias) · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_4b43573139c14a60` Gemini Flash (latest alias) · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_7a8623b119d4412b` Gemini Flash (latest alias) · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_b77f60432fbf4e4d` Gemini Flash (latest alias) · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_b927a9b6d4864489` Gemini Flash (latest alias) · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_094e3b3a2e704fc3` GPT-5.6-sol · default (unverified)	Sep 1, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_16562a66a4b04b92` GPT-5.6-sol · default (unverified)	Sep 1, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_728c55d6e82840db` GPT-5.6-sol · default (unverified)	Sep 1, 2026 console	0 · valid	GOOD_FAILURE frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_e79823c3ea4e4e3f` GPT-5.6-sol · default (unverified)	Sep 1, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available
`trial_f091a9296d8347e7` GPT-5.6-sol · default (unverified)	Sep 1, 2026 console	1 · valid	GOOD_SUCCESS frozen-classifier	Tokens: — Turns: — Cost: —	Not publicly available