Skip to content

swebench file-recall is saturated (1.000 for all methods) — promote fragment/line metrics for it #97

Description

@nikolay-e

In sweep #64, file_recall on swebench_verified is 1.000 for every method at every budget >= 8000 — by construction the gold files are inside the diff, so at non-trivial budgets selection never drops them. File-level recall carries zero discriminating power on this test set (B=0 -> 0.000 sanity bound still works).

The discriminating signal there is fragment_recall / fragment_precision / line_f1, which the evaluator already computes and the checkpoints already store (n_with_fragment_gold etc.), but SWEEP_TABLE's headline matrix and the per-test-set tables lead with file recall only.

To do: in aggregate_sweep.render_sweep_table (or a sibling section), render fragment-level recall/precision for test sets where file recall is saturated (mean file_recall >= 0.995 across methods), so the paper's swebench column says something. Data exists; no new runs needed.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions