Archive verified research artifact: complete.json

artifacts/experiments/runs/test-reranker-scienceqa-s17/complete.json

@@ -0,0 +1,18 @@
+{
+  "files": {
+    "calibration_test_metrics.json": "d4f3e0cfa4bf4413ccb25fd3f13f0b1b8fbd4f7be449ba2288e429313a44656b",
+    "calibrator.json": "a60d451af393f0c06fd9cd5dc199c7180257328c4e5896ff2f3017ed039a89d9",
+    "freeze.json": "ee49dacb698f88a3a19bd9148d19133fb1f4de8102dac25ae04c6a59f21e0fe5",
+    "run.json": "7e2beeb36ec7a82aa577b7b7a4b40127ee759927cd4d98455911c4dbb17c3424",
+    "summary.json": "f4006dfb1e650b7590e8c2751371e8a142309ab0596985bbd90280e4092e1c74",
+    "test/evaluation/per_question.jsonl": "e125633ea60ae04c636d282c66a1875ac2dd94bd636b52d1f49c0366826ab77a",
+    "test/evaluation/summary.json": "ab27057d6304cd1574665e88a67b74dc81852fdbfd5df6eb4b2d71b77aa89a4e",
+    "test/predictions.jsonl": "fd3b9fadc75f1cfcb918595e96c765ef39da46444f54282ad88a0b0d25dc7594",
+    "val_calibration/evaluation/per_question.jsonl": "24cf0eafe77cc9acbca10c8c01c2c9482ec3f0da1eb06ec062c21fc8bc04d74f",
+    "val_calibration/evaluation/summary.json": "b2ba581838170c7dab720197fa7b5617fbcda09319cb0c69478ce1529ed551f9",
+    "val_calibration/predictions.jsonl": "d9300e697186c41ecaf05156a36cf0be3ae30bebdd220ab1e42ccc68ae40fb69",
+    "validation_canaries.json": "94b9f774ae9f1069361ed2deecca544990d6d653ed447f7a12277880568c8c54"
+  },
+  "spec_sha256": "d25b460d7b6776b676e949dc6dc0f668938dc62e5a7fa9b04230b4d3bc31c669",
+  "test_used": true
+}