gahow/aituner
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Decompose good/bad selection split across frozen surfaces

Browse Source 
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Gahow Wang
2026-07-20 12:05:20 +08:00
parent 18c0b25ae7
commit 39766141fb
54 changed files with 24465 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

230
runs/frontier-split-rootcause-v0/frozen-inputs/q30-trace-pd/summary.json Normal file
View File

@@ -0,0 +1,230 @@
{
"e2e_ms:mean": {
"concordant_pairs": 61,
"discordant_pairs": 5,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.9242424242424242,
"real_ranking": [
"tp4_mns64",
"tp4_mns32",
"tp2_mns32",
"tp2_mns64",
"tp4_mns16",
"tp1_mns32",
"tp1_mns64",
"tp2_mns16",
"tp1_mns16",
"tp4_mns8",
"tp2_mns8",
"tp1_mns8"
],
"real_winner": "tp4_mns64",
"sim_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp4_mns32",
"tp2_mns32",
"tp1_mns64",
"tp4_mns16",
"tp1_mns32",
"tp2_mns16",
"tp4_mns8",
"tp1_mns16",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp4_mns64",
"tied_pairs": 0,
"winner_match": true
},
"e2e_ms:p90": {
"concordant_pairs": 55,
"discordant_pairs": 11,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.8333333333333334,
"real_ranking": [
"tp4_mns64",
"tp4_mns32",
"tp4_mns16",
"tp2_mns32",
"tp2_mns64",
"tp2_mns16",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64",
"tp4_mns8",
"tp2_mns8",
"tp1_mns8"
],
"real_winner": "tp4_mns64",
"sim_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp4_mns32",
"tp2_mns32",
"tp1_mns64",
"tp4_mns16",
"tp1_mns32",
"tp2_mns16",
"tp4_mns8",
"tp1_mns16",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp4_mns64",
"tied_pairs": 0,
"winner_match": true
},
"tpot_ms:mean": {
"concordant_pairs": 64,
"discordant_pairs": 2,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.9696969696969697,
"real_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp2_mns8",
"tp4_mns32",
"tp4_mns64",
"tp2_mns16",
"tp1_mns8",
"tp2_mns32",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"sim_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp4_mns32",
"tp2_mns8",
"tp4_mns64",
"tp2_mns16",
"tp2_mns32",
"tp1_mns8",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns8",
"tied_pairs": 0,
"winner_match": true
},
"tpot_ms:p90": {
"concordant_pairs": 64,
"discordant_pairs": 2,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.9696969696969697,
"real_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp2_mns8",
"tp4_mns32",
"tp4_mns64",
"tp2_mns16",
"tp1_mns8",
"tp2_mns32",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"real_winner": "tp4_mns8",
"sim_ranking": [
"tp4_mns8",
"tp4_mns16",
"tp4_mns32",
"tp2_mns8",
"tp4_mns64",
"tp2_mns16",
"tp2_mns32",
"tp1_mns8",
"tp2_mns64",
"tp1_mns16",
"tp1_mns32",
"tp1_mns64"
],
"sim_winner": "tp4_mns8",
"tied_pairs": 0,
"winner_match": true
},
"ttft_ms:mean": {
"concordant_pairs": 56,
"discordant_pairs": 10,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.8484848484848485,
"real_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp1_mns64",
"tp1_mns32",
"tp2_mns32",
"tp4_mns32",
"tp1_mns16",
"tp2_mns16",
"tp4_mns16",
"tp1_mns8",
"tp2_mns8",
"tp4_mns8"
],
"real_winner": "tp4_mns64",
"sim_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp1_mns64",
"tp4_mns32",
"tp2_mns32",
"tp1_mns32",
"tp4_mns16",
"tp2_mns16",
"tp4_mns8",
"tp1_mns16",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp4_mns64",
"tied_pairs": 0,
"winner_match": true
},
"ttft_ms:p90": {
"concordant_pairs": 56,
"discordant_pairs": 10,
"informative_pairs": 66,
"pairwise_agreement_fraction": 0.8484848484848485,
"real_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp1_mns32",
"tp1_mns64",
"tp2_mns32",
"tp4_mns32",
"tp1_mns16",
"tp4_mns16",
"tp2_mns16",
"tp1_mns8",
"tp2_mns8",
"tp4_mns8"
],
"real_winner": "tp4_mns64",
"sim_ranking": [
"tp4_mns64",
"tp2_mns64",
"tp1_mns64",
"tp4_mns32",
"tp2_mns32",
"tp1_mns32",
"tp4_mns16",
"tp2_mns16",
"tp4_mns8",
"tp1_mns16",
"tp2_mns8",
"tp1_mns8"
],
"sim_winner": "tp4_mns64",
"tied_pairs": 0,
"winner_match": true
}
}