mirror of
https://github.com/jung-geun/PSO.git
synced 2026-09-20 14:11:48 +09:00
Migrate the package and examples to the tensor-native PyTorch implementation, add benchmark evidence, and add the guarded post-training convergence protocol with TensorBoard progress monitoring and hash-verified recovery. Constraint: Preserve one-shot official-test sealing and auditable research artifacts Rejected: Commit local .omc runs and downloaded datasets | multi-gigabyte runtime state is machine-local Confidence: high Scope-risk: broad Not-tested: Production CUDA run on pieroot-server
30 KiB
30 KiB
| 1 | variant_id | phase | split_seed | workload_id | baseline_method | baseline_acc | candidate_acc | acc_gain_pp | baseline_nll | candidate_nll | nll_reduction_fraction | state_ratio | score | pass | is_best_observed | candidate_path | evaluation_path |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2 | iteration-0001-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 3 | iteration-0001-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 46.04 | -0.6166669999999996 | 1.677872 | 1.675644 | 0.0013278724479579603 | 0.5 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 4 | iteration-0001-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 5 | iteration-0001-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 45.01 | -3.506667 | 1.490304 | 1.584923 | -0.06348973095422142 | 0.5 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 6 | iteration-0001-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 7 | iteration-0001-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 44.83 | -0.10666700000000162 | 1.665007 | 1.749135 | -0.050527114901018556 | 0.5 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 8 | iteration-0001-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 9 | iteration-0001-development | development | 20260906 | fashion_wide | G5 | 48.37 | 41.193333 | -7.176666999999995 | 1.490657 | 1.707819 | -0.14568207173078723 | 0.5 | -289.2921035434933 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0001-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0001-development.json |
| 10 | iteration-0002-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 11 | iteration-0002-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 45.193333 | -1.4633339999999961 | 1.677872 | 1.733563 | -0.03319144726176963 | 0.5 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 12 | iteration-0002-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 13 | iteration-0002-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 47.223333 | -1.2933340000000015 | 1.490304 | 1.536216 | -0.03080713733573818 | 0.5 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 14 | iteration-0002-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 15 | iteration-0002-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 45.09 | 0.1533330000000035 | 1.665007 | 1.734207 | -0.04156138682900441 | 0.5 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 16 | iteration-0002-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 17 | iteration-0002-development | development | 20260906 | fashion_wide | G5 | 48.37 | 46.813333 | -1.5566669999999974 | 1.490657 | 1.475127 | 0.010418224984016995 | 0.5 | -186.3459040597986 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0002-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0002-development.json |
| 18 | iteration-0003-replica1-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 19 | iteration-0003-replica1-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 44.923333 | -1.7333339999999993 | 1.677872 | 1.728906 | -0.030415907768888223 | 0.5 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 20 | iteration-0003-replica1-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 21 | iteration-0003-replica1-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 47.176667 | -1.3399999999999963 | 1.490304 | 1.56267 | -0.048557878124194744 | 0.5 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 22 | iteration-0003-replica1-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 23 | iteration-0003-replica1-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 42.113333 | -2.8233340000000027 | 1.665007 | 1.713134 | -0.028904983582651624 | 0.5 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 24 | iteration-0003-replica1-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 25 | iteration-0003-replica1-development | development | 20260906 | fashion_wide | G5 | 48.37 | 46.433333 | -1.936667 | 1.490657 | 1.581386 | -0.06086510847230454 | 0.5 | -287.7250973286179 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica1-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica1-development.json |
| 26 | iteration-0003-replica2-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 27 | iteration-0003-replica2-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 46.01 | -0.6466670000000008 | 1.677872 | 1.72888 | -0.0304004119503752 | 0.5 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 28 | iteration-0003-replica2-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 29 | iteration-0003-replica2-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 48.613333 | 0.09666599999999903 | 1.490304 | 1.48049 | 0.006585233616765431 | 0.5 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 30 | iteration-0003-replica2-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 31 | iteration-0003-replica2-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 41.556667 | -3.3800000000000026 | 1.665007 | 1.801698 | -0.08209635154687045 | 0.5 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 32 | iteration-0003-replica2-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 33 | iteration-0003-replica2-development | development | 20260906 | fashion_wide | G5 | 48.37 | 45.913333 | -2.456666999999996 | 1.490657 | 1.516614 | -0.017413127231817923 | 0.5 | -286.97652369317115 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0003-replica2-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0003-replica2-development.json |
| 34 | iteration-0004-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 35 | iteration-0004-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 44.763333 | -1.8933339999999959 | 1.677872 | 1.698999 | -0.012591544527830428 | 0.5 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 36 | iteration-0004-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 37 | iteration-0004-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 44.816667 | -3.6999999999999957 | 1.490304 | 1.582588 | -0.06192293652838617 | 0.5 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 38 | iteration-0004-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 39 | iteration-0004-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 38.946667 | -5.990000000000002 | 1.665007 | 1.819662 | -0.09288549537629572 | 0.5 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 40 | iteration-0004-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 41 | iteration-0004-development | development | 20260906 | fashion_wide | G5 | 48.37 | 43.9 | -4.469999999999999 | 1.490657 | 1.658117 | -0.11233972671110803 | 0.5 | -390.14004501856266 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0004-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0004-development.json |
| 42 | iteration-0005-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 43 | iteration-0005-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 43.723333 | -2.933334000000002 | 1.677872 | 1.675155 | 0.0016193130346057866 | 0.5 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 44 | iteration-0005-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 45 | iteration-0005-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 45.45 | -3.0666669999999954 | 1.490304 | 1.441667 | 0.03263562333591002 | 0.5 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 46 | iteration-0005-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 47 | iteration-0005-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 42.543333 | -2.393334000000003 | 1.665007 | 1.740544 | -0.04536737683385127 | 0.5 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 48 | iteration-0005-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 49 | iteration-0005-development | development | 20260906 | fashion_wide | G5 | 48.37 | 47.65 | -0.7199999999999989 | 1.490657 | 1.454402 | 0.02432149045689245 | 0.5 | -185.61068572934795 | False | True | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0005-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0005-development.json |
| 50 | iteration-0006-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 51 | iteration-0006-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 42.006667 | -4.649999999999999 | 1.677872 | 1.749895 | -0.04292520525999596 | 0.5 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 52 | iteration-0006-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 53 | iteration-0006-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 49.08 | 0.5633330000000001 | 1.490304 | 1.466855 | 0.015734373657991962 | 0.5 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 54 | iteration-0006-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 55 | iteration-0006-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 40.84 | -4.0966669999999965 | 1.665007 | 1.73617 | -0.04274036085133581 | 0.5 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 56 | iteration-0006-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 57 | iteration-0006-development | development | 20260906 | fashion_wide | G5 | 48.37 | 46.946667 | -1.4233329999999995 | 1.490657 | 1.508747 | -0.012135588535793386 | 0.5 | -186.8633001166316 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0006-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0006-development.json |
| 58 | iteration-0007-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 59 | iteration-0007-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 41.05 | -5.606667000000002 | 1.677872 | 1.794261 | -0.06936703157332626 | 0.5 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 60 | iteration-0007-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 61 | iteration-0007-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 42.513333 | -6.003333999999995 | 1.490304 | 1.615206 | -0.08380974619943303 | 0.5 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 62 | iteration-0007-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 63 | iteration-0007-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 40.666667 | -4.270000000000003 | 1.665007 | 1.764515 | -0.059764313303187405 | 0.5 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 64 | iteration-0007-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 65 | iteration-0007-development | development | 20260906 | fashion_wide | G5 | 48.37 | 39.916667 | -8.453333 | 1.490657 | 1.609595 | -0.07978897895357565 | 0.5 | -391.33742460463645 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0007-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0007-development.json |
| 66 | iteration-0008-development | development | 20260905 | mnist_compact | G8 | 50.713333 | 50.723333 | 0.00999999999999801 | 1.534298 | 1.492805 | 0.0270436381980554 | 0.4918032786885246 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 67 | iteration-0008-development | development | 20260905 | mnist_wide | G5 | 46.656667 | 41.14 | -5.516666999999998 | 1.677872 | 1.748292 | -0.041969828449369154 | 0.5 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 68 | iteration-0008-development | development | 20260905 | fashion_compact | G8 | 46.366667 | 49.576667 | 3.210000000000001 | 1.497844 | 1.400574 | 0.06494000710354347 | 0.4918032786885246 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 69 | iteration-0008-development | development | 20260905 | fashion_wide | G5 | 48.516667 | 45.726667 | -2.789999999999999 | 1.490304 | 1.558163 | -0.04553366293051612 | 0.5 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 70 | iteration-0008-development | development | 20260906 | mnist_compact | G8 | 46.81 | 51.663333 | 4.853332999999999 | 1.58986 | 1.436337 | 0.09656384838916639 | 0.4918032786885246 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 71 | iteration-0008-development | development | 20260906 | mnist_wide | G5 | 44.936667 | 39.596667 | -5.340000000000003 | 1.665007 | 1.763671 | -0.059257408527411654 | 0.5 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 72 | iteration-0008-development | development | 20260906 | fashion_compact | G8 | 44.193333 | 48.753333 | 4.559999999999995 | 1.553097 | 1.375751 | 0.11418861796784104 | 0.4918032786885246 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |
| 73 | iteration-0008-development | development | 20260906 | fashion_wide | G5 | 48.37 | 43.246667 | -5.123332999999995 | 1.490657 | 1.649349 | -0.10645775654627461 | 0.5 | -390.14811518493707 | False | False | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/candidates/iteration-0008-development.json | .omc/autoresearch/heavy-pso-cross-split-robustness/runs/20260903T162504Z/evaluations/iteration-0008-development.json |