DRAM-Native &|~ Classification

Leaderboard — Ensemble Subset Selection

Public challenge leaderboard — 2026-08-31

Status: OPENING. The challenge is live, the score corpora and the reference search tool are published. First submissions are accepted via GitHub — we validate them independently on the .ens corpora and add them to this table. See the full challenge specification →

Reference Baselines (INT32 bit-exact)

All baselines run on Fashion-MNIST (10,000 test samples) via merge-ensemble.exe over the published .ens score archives. The standard member cap is |S| ≤ 12; the greedy run is uncapped.

#Methodevalmembersconfig / notes
1Greedy forward selection91.84%17full pool 24,192, --greedy
2Beam search (30/50) + filter92.32%12H392-OT8, --beam 30 --max 12 --eff --filter m1th eq 105 --filter eval gt 66%
3Beam 20 + filter eval gt 20%92.96%12H196-OT8, --max --filter eval gt 20%
4Row 2 + --exclude 6 (Shirt omitted)94.24–94.83%12–18⚠️ proviso: 9-class accuracy, class 6 removed from train+eval

⚠️ Row 4 is a 9-class result (proviso: omitting class "Shirt"). It quantifies how much the single problem class costs (−2.4 to −3.0pp) and is not comparable to the 10-class rows 1–3. See the Fashion-MNIST paper.

Community Submissions

#Methodevalmemberssubmitterdate
— open for submissions —

How to Submit

  1. Read the challenge: ensemble-selection-challenge.html — problem statement, corpus access, submission protocol (§6).
  2. Produce a subset: your algorithm must output a subset of member indices (or a reproducible ranking) over one of the published .ens corpora.
  3. Report: accuracy, #members, wall-time, hillclimb/test split used, determinism, and the exact command line / seed.
  4. Send: open an issue or PR on github.com/aotto1968/forward-prop. We re-run it independently on the corpora and publish the verified numbers here.

Evaluation Rules

Forward-Prop Research — DRAM-native bit-logic classification. Leaderboard opened 2026-08-31. Baselines INT32 bit-exact, reproducible via run-grep --date-start 2026-08-30 | run-sort eval.