gopher-lua-exact-integers-75f4976

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

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

The task

gopher-lua stores every Lua number as a float64, so int64-scale identifiers moving through scripts get corrupted: a large id written as a constant, produced by arithmetic, parsed by tonumber, stepped by a numeric for counter, or read back through the Go accessors silently rounds. We want an opt-in guarantee. Give Options an ExactNumbers bool field, false by default; a state without it keeps every behavior it has tod…

Excerpt only; not a complete executable task specification. Task ID task_5b2abc5cb94d4a75 · 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
GPT-5.6-sol · default (unverified)	5/5 · 100.0% [56.6%, 100.0%]	0 / 5	0	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
Gemini Flash (latest alias) · default (unverified)	0/0	0 / 0	0	GOOD_FAILURE: 0 BAD_FAILURE: 0 GOOD_SUCCESS: 0 BAD_SUCCESS: 0

Difficulty, with uncertainty

Selected-best difficulty: 0.0% [0.0%, 43.4%]. 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

14 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_99cd5b2071244385` GPT-5.6-sol · default (unverified)	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: $2.4843	Not publicly available
`trial_2e2241926d364f85` GPT-5.6-sol · default (unverified)	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: $1.5053	Not publicly available
`trial_ff9041b0f750495c` GPT-5.6-sol · default (unverified)	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: $1.6628	Not publicly available
`trial_a47473d212e9492e` GPT-5.6-sol · default (unverified)	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: $2.6436	Not publicly available
`trial_43c7fd1d57d0439f` Gemini Flash (latest alias) · default (unverified)	Sep 10, 2026 console	0 · excludedsource_evidence_exclusion	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_bd8ffff5a3454d0f` Gemini Flash (latest alias) · default (unverified)	Sep 10, 2026 console	0 · excludedsource_evidence_exclusion	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_9c843c51424f4bb9` Gemini Flash (latest alias) · default (unverified)	Sep 10, 2026 console	0 · excludedsource_evidence_exclusion	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_8e7f01ef123c40e4` Gemini Flash (latest alias) · default (unverified)	Sep 10, 2026 console	0 · excludedsource_evidence_exclusion	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_043bc18400564797` Gemini Flash (latest alias) · default (unverified)	Sep 10, 2026 console	0 · excludedsource_evidence_exclusion	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_3bf8be970180426d` nop@@	Sep 10, 2026 console	0 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_d3ff3a633b564555` oracle@@	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_7e194e6006404ec2` oracle@@	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_2d9e76b5784f485d` oracle@@	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: —	Not publicly available
`trial_4f78218812a54c78` GPT-5.6-sol · default (unverified)	Sep 10, 2026 console	1 · valid	No diagnostic label derived	Tokens: — Turns: — Cost: $1.6900	Not publicly available