Skip to content

evaluate ego default depth: L1 dominates L2-L4 on F1 in sweep #64 #94

Description

@nikolay-e

Interim sweep #64 data (123 cells): at budget 8000, mean across 3 test sets —

depth recall precision F1
L1 0.9231 0.2544 0.3562
L2 (current default) 0.9267 0.2128 0.2974
L3 0.9282 0.1925 0.2720
L4 0.9290 0.1913 0.2698

L1 gives up ~0.4pt recall for +6pt precision / +6pt F1 vs the current default depth 2. Same ordering holds at 16k/32k.

To do (no new runs needed — checkpoints from run #64 suffice):

  1. paired bootstrap CI on per-instance recall/F1 deltas L1 vs L2 (benchmarks/stats.py), per test set;
  2. if L1's F1 win is significant and the recall loss CI excludes practically-relevant regressions, change MODE.ego_depth_extended default 2 -> 1;
  3. otherwise document why 2 stays.

Note: depends on the aggregate tables being depth-correct — the falsy-zero get("depth") or -1 mislabeling of L0 rows was fixed in 2cf87d2.

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