updating purpose-classifier data:

data/curation-review-v1.json

@@ -1,12 +1,66 @@
 {
+  "datasetVersion": "purpose-dataset-sol-high-v2",
+  "humanLabelAndDifficultyReview": {
+    "decision": "Every supervised target was regenerated with gpt-5.6-sol at high reasoning effort.",
+    "decisionBasis": "The dataset owner invalidated the original labels and required a complete Sol-high relabel.",
+    "decisionDate": "2026-08-02",
+    "generatedArtifact": "ml/purpose-classifier/.artifacts/human-review-v1.csv",
+    "populationRecords": 12193,
+    "reviewFields": [
+      "purpose",
+      "secondary",
+      "difficulty",
+      "slice",
+      "review status",
+      "notes"
+    ],
+    "sampleFraction": 0.1,
+    "sampleRecords": 1219,
+    "seed": 10558743,
+    "status": "superseded-by-sol-high-relabel",
+    "strata": [
+      "purpose",
+      "slice",
+      "primary language"
+    ]
+  },
   "schemaVersion": 1,
-  "datasetVersion": "purpose-dataset-v1",
+  "semanticDuplicateReview": {
+    "auditVersion": "purpose-semantic-audit-v1",
+    "decision": "The prior semantic decisions were tied to the invalidated label population; the reset uses deterministic lexical curation only.",
+    "excluded": [
+      {
+        "droppedPromptHash": "7348d764d602cfff72dd2b1d369ad0375a96ea52b38174aa0bd6168a548bcc2f",
+        "matchedPromptHash": "3ad9cfbb664504f0e7ae84b905520937e7812d4e879fa706415782341f2cd400",
+        "similarity": 0.984897
+      },
+      {
+        "droppedPromptHash": "a0c6e7984e92adc11ea6855c39688d733bf7665f5f965939325b15f3ba39e937",
+        "matchedPromptHash": "17f79a890a323c08770193a94b100dadaa00116405bdb7d14c1b89abc3c3066a",
+        "similarity": 0.980998
+      },
+      {
+        "droppedPromptHash": "bfd7791069fd04c13797f39ba99224ad68ca2deebbc912f08b10815954a7d223",
+        "matchedPromptHash": "dc48031efb18f25a56a3beddcdd814f26473b23cd496482ce1884ae6f697417a",
+        "similarity": 0.973329
+      }
+    ],
+    "excludedCandidates": 3,
+    "retained": [
+      {
+        "leftPromptHash": "70944e70e0062e947476f73b704ec01ecee19420d06fd174c58a41c04e8112f6",
+        "rightPromptHash": "cb3e63992cbf5830a222933dc7b44be39933baedcb46e335be02e3c379685517",
+        "similarity": 0.970376
+      }
+    ],
+    "retainedCandidates": 1,
+    "reviewedCandidates": 4,
+    "status": "superseded-by-sol-high-relabel"
+  },
   "wordTrigramExclusionReview": {
-    "status": "complete",
-    "reviewedRecords": 18,
     "confirmedTemplateDuplicates": 18,
-    "rejectedExclusions": 0,
     "decision": "All 18 pairs preserve the same task, requested outcome, and purpose label; differences are generated identifiers, ticket numbers, cosmetic context prefixes, or difficulty/slice metadata. Keep the earliest member and exclude the later template copy.",
+    "rejectedExclusions": 0,
     "reviewedDroppedPromptHashes": [
       "f29de1d646055017f80346055bb3ac1468c49af7ab0c6249f45f19cf386f9fa7",
       "dabbcd0a19d2918199b5d0d35fac49fd5413cb17a5164252b789114fc68ec43b",
@@ -26,62 +80,8 @@
       "fdc04376376dbffcaf9928e9edcef29376203640b49c200c2c117f78891125a1",
       "432e67ead52d6cd57e4a5034cd8bcde14bd2da13f88cb5532c42fd8fbd8daf05",
       "24f3759ff4a3fb9fc77bed4c8525f30f9af2479a6cffbb0c4842043f99a7d8f1"
-    ]
-  },
-  "semanticDuplicateReview": {
-    "status": "complete",
-    "auditVersion": "purpose-semantic-audit-v1",
-    "reviewedCandidates": 4,
-    "excludedCandidates": 3,
-    "retainedCandidates": 1,
-    "decision": "Exclude three same-purpose generated template copies. One pair ('make the screen nicer' / 'Make this screen nicer') remains because it is a deliberate vague-language variant, lives entirely in validation, and does not contaminate the frozen evaluation boundary.",
-    "excluded": [
-      {
-        "droppedPromptHash": "7348d764d602cfff72dd2b1d369ad0375a96ea52b38174aa0bd6168a548bcc2f",
-        "matchedPromptHash": "3ad9cfbb664504f0e7ae84b905520937e7812d4e879fa706415782341f2cd400",
-        "similarity": 0.984897
-      },
-      {
-        "droppedPromptHash": "a0c6e7984e92adc11ea6855c39688d733bf7665f5f965939325b15f3ba39e937",
-        "matchedPromptHash": "17f79a890a323c08770193a94b100dadaa00116405bdb7d14c1b89abc3c3066a",
-        "similarity": 0.980998
-      },
-      {
-        "droppedPromptHash": "bfd7791069fd04c13797f39ba99224ad68ca2deebbc912f08b10815954a7d223",
-        "matchedPromptHash": "dc48031efb18f25a56a3beddcdd814f26473b23cd496482ce1884ae6f697417a",
-        "similarity": 0.973329
-      }
     ],
-    "retained": [
-      {
-        "leftPromptHash": "70944e70e0062e947476f73b704ec01ecee19420d06fd174c58a41c04e8112f6",
-        "rightPromptHash": "cb3e63992cbf5830a222933dc7b44be39933baedcb46e335be02e3c379685517",
-        "similarity": 0.970376
-      }
-    ]
-  },
-  "humanLabelAndDifficultyReview": {
-    "status": "accepted-as-generated",
-    "populationRecords": 12193,
-    "sampleFraction": 0.1,
-    "sampleRecords": 1219,
-    "seed": 10558743,
-    "strata": [
-      "purpose",
-      "slice",
-      "primary language"
-    ],
-    "reviewFields": [
-      "purpose",
-      "secondary",
-      "difficulty",
-      "slice",
-      "review status",
-      "notes"
-    ],
-    "generatedArtifact": "ml/purpose-classifier/.artifacts/human-review-v1.csv",
-    "decisionDate": "2026-07-31",
-    "decisionBasis": "The dataset owner explicitly directed the project to assume the generated labels, secondary purposes, difficulties, and slices are correct and validated without completing the row-by-row sample.",
-    "decision": "Accept the curated generated population as-is. No relabel or reject decisions are inferred, and the blank CSV remains an optional future audit artifact rather than a rollout blocker."
+    "reviewedRecords": 18,
+    "status": "complete"
   }
 }