Merge nucleic/sleek-ember-seal-uady into dev

data/dataset-v1-manifest.json

@@ -1,12 +1,15 @@
 {
   "curation": {
     "excludedDuplicates": {
-      "near": 18
+      "near": 18,
+      "semantic-reviewed": 3
     },
     "inputRecords": 12214,
     "nearDuplicateMethod": "word-trigram Jaccard after SimHash LSH candidate search",
     "nearDuplicateThreshold": 0.92,
-    "retainedRecords": 12196,
+    "retainedRecords": 12193,
+    "reviewPath": "ml/purpose-classifier/data/curation-review-v1.json",
+    "reviewSha256": "2db763df027b545b4fd654108dcadb0717f9c9c0a63555bf8cea26b791cda370",
     "vagueEvalPolicy": "validation/test only"
   },
   "datasetVersion": "purpose-dataset-v1",
@@ -23,7 +26,7 @@
     "shippedFixturesPath": "Tests/NucleicCoreTests/Fixtures/purpose-prompts.json",
     "shippedFixturesSha256": "6c8f0eedce35f9da7a407934009e87737b5e85c7371f6a118982d9fae2ea7aae",
     "syntheticPath": "ml/purpose-classifier/data/frozen-test-v1.jsonl",
-    "syntheticSha256": "e5a6b501a43ce256092932ab05b0af01ff9137aee42d85b7d58bb4ce65f2943f"
+    "syntheticSha256": "5d34c8ac3d39c5b4e2e739c4c9058093beb6f790a42a1397cedefae6271654ab"
   },
   "ratios": {
     "test": 0.1,
@@ -50,7 +53,7 @@
       "distribution": {
         "language": {
           "de": 7,
-          "en": 1111,
+          "en": 1110,
           "es": 9,
           "fr": 5,
           "ja": 3,
@@ -63,7 +66,7 @@
           "frontendImpl": 157,
           "planning": 132,
           "quickFix": 140,
-          "refactor": 137,
+          "refactor": 136,
           "review": 127,
           "writing": 129
         },
@@ -72,19 +75,19 @@
           "core": 507,
           "mixed": 80,
           "pasted-context": 84,
-          "vague-eval": 292
+          "vague-eval": 291
         }
       },
-      "hardSyntheticRecords": 635,
-      "logicalRecords": 1229,
-      "sha256": "e5a6b501a43ce256092932ab05b0af01ff9137aee42d85b7d58bb4ce65f2943f",
-      "syntheticRecords": 1142
+      "hardSyntheticRecords": 634,
+      "logicalRecords": 1228,
+      "sha256": "5d34c8ac3d39c5b4e2e739c4c9058093beb6f790a42a1397cedefae6271654ab",
+      "syntheticRecords": 1141
     },
     "train": {
       "distribution": {
         "language": {
           "de": 100,
-          "en": 9326,
+          "en": 9324,
           "es": 100,
           "fr": 81,
           "ja": 77,
@@ -92,24 +95,24 @@
           "zh": 72
         },
         "purpose": {
-          "backendImpl": 1225,
+          "backendImpl": 1226,
           "debugging": 1245,
-          "frontendImpl": 1235,
+          "frontendImpl": 1234,
           "planning": 1223,
           "quickFix": 1230,
-          "refactor": 1225,
+          "refactor": 1223,
           "review": 1230,
           "writing": 1213
         },
         "slice": {
-          "boundary": 2065,
-          "core": 5820,
+          "boundary": 2066,
+          "core": 5818,
           "mixed": 906,
-          "pasted-context": 1035
+          "pasted-context": 1034
         }
       },
-      "records": 9826,
-      "sha256": "ca0ec9fe6fef6bc4013bf09bdfed5877327f69c98f8e5552c082cbb4e76d9b7d"
+      "records": 9824,
+      "sha256": "40a5064c2a95d4394d71b3edbad7d03dce7d67b2e5ba9ab9320476e35e3a4953"
     },
     "validation": {
       "distribution": {
@@ -123,25 +126,25 @@
           "zh": 7
         },
         "purpose": {
-          "backendImpl": 184,
+          "backendImpl": 183,
           "debugging": 157,
           "frontendImpl": 168,
           "planning": 141,
           "quickFix": 151,
-          "refactor": 148,
+          "refactor": 149,
           "review": 140,
           "writing": 139
         },
         "slice": {
-          "boundary": 196,
+          "boundary": 195,
           "core": 541,
           "mixed": 83,
           "pasted-context": 95,
-          "vague-eval": 313
+          "vague-eval": 314
         }
       },
       "records": 1228,
-      "sha256": "7eca32f98105eec1c1a34c324851d52004d8dc720ca5853a1e91fa0a0dd620f4"
+      "sha256": "3d0a3730931db360dd8346cf12d03901ac139acf5be1d9e84975ac591186c588"
     }
   }
 }