Skip to content

Commit 134c22f

Browse files
ALikesToCodeALikesToCode
committed
chore: update transfer semantics task data and held-out/eval fixtures
1 parent 4fa0f52 commit 134c22f

8 files changed

Lines changed: 723 additions & 3 deletions

File tree

‎concept-packs/imbalance/transfer/task.json‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"schemaVersion": "1",
3-
"id": "manufacturing-defect-imbalance-01",
3+
"id": "manufacturing-defect-transfer-01",
44
"concept": "class_imbalance_transfer",
55
"title": "Would this inspection model catch rare defects?",
66
"scenario": "A factory evaluated 20,000 parts, including 200 defective parts. The model predicted every part as acceptable and reports 99% accuracy. Decide whether that evidence supports deployment and select the evidence needed to evaluate the rare defective class.",

‎evals/held-out/src/completion.ts‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -497,11 +497,11 @@ export async function runHeldOutCompletion(
497497
selectedStrategy:
498498
input.concept === "entity_leakage"
499499
? "time_ordered_holdout"
500-
: "cost_aware_threshold",
500+
: "reject_accuracy_only",
501501
identifiedRisks:
502502
input.concept === "entity_leakage"
503503
? ["centered_window_reads_future"]
504-
: ["minority_false_negative_cost"],
504+
: ["recall_and_pr_auc"],
505505
},
506506
patchContract: pack.patchContract,
507507
allowedCellIndices: targetCells,

‎fixtures/public/leakage_sample_patch_v1/customer_churn_leakage.patch.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"cellDiff":"--- cell-3-before.py\n+++ cell-3-after.py\n@@ -2,11 +2,12 @@\n from sklearn.impute import SimpleImputer\n\n from sklearn.linear_model import LogisticRegression\n\n from sklearn.metrics import accuracy_score, roc_auc_score\n\n-from sklearn.model_selection import train_test_split\n\n+from sklearn.model_selection import GroupShuffleSplit\n\n from sklearn.pipeline import Pipeline\n\n from sklearn.preprocessing import OneHotEncoder, StandardScaler\n\n \n\n-X = df.drop(columns=['churned'])\n\n+groups = df['customer_id']\n\n+X = df.drop(columns=['churned', 'customer_id', 'observation_id'])\n\n y = df['churned']\n\n categorical = [c for c in X.columns if X[c].dtype == 'object']\n\n numeric = [c for c in X.columns if c not in categorical]\n\n@@ -15,11 +16,17 @@\n ('numeric', Pipeline([('impute', SimpleImputer()), ('scale', StandardScaler())]), numeric),\n\n ])\n\n model = Pipeline([('preprocess', preprocess), ('model', LogisticRegression(C=100, max_iter=2000))])\n\n-X_train, X_test, y_train, y_test = train_test_split(\n\n- X, y, test_size=0.25, random_state=1729, stratify=y\n\n-)\n\n+splitter = GroupShuffleSplit(n_splits=1, test_size=0.25, random_state=1729)\n\n+train_index, test_index = next(splitter.split(X, y, groups=groups))\n\n+X_train, X_test = X.iloc[train_index], X.iloc[test_index]\n\n+y_train, y_test = y.iloc[train_index], y.iloc[test_index]\n\n+train_customers = set(groups.iloc[train_index])\n\n+test_customers = set(groups.iloc[test_index])\n\n+customer_overlap = train_customers.intersection(test_customers)\n\n+assert not customer_overlap\n\n model.fit(X_train, y_train)\n\n probability = model.predict_proba(X_test)[:, 1]\n\n prediction = (probability >= 0.5).astype(int)\n\n-print(f'Random row-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n-print(f'Random row-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n+print(f'Customer group-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n+print(f'Customer group-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n\n+print(f'Train/test customer overlap: {len(customer_overlap)}')","changedCellIndices":[3],"correctedResult":{"dropFeatures":["customer_id"],"entityCounts":{"test":120,"train":360},"entityOverlap":{"count":0,"rate":0.0},"featureSetFingerprint":"9641773fdead963da5fb0582be52c255307fc4d601c4a4b580f5730d088f2362","groupBy":"customer_id","id":"patched_customer_group_split","inputFingerprint":"5c482f39e4e948a92dab61bf9c9f5c6577fbe9fc688fd597c9fefd785ee1be70","kernelVersion":"0.1.0","metrics":{"accuracy":0.625,"rocAuc":0.662186573617},"model":"logistic_regression","pipelineFingerprint":"234782290268e64b80af2e23b2b9b97268db8cd8e8740522834cde57cae78824","resultHash":"df4cbaf93266decd43e51f3fe0bcb9d1d6d3476c1b0e466e0fa87fa8c43aa508","sampleSizes":{"test":720,"train":2160},"schemaVersion":"1","seed":1729,"splitStrategy":"group"},"evaluationCellId":"random-row-split","metadataHash":"ec7a42e85f9a4e8dfb3d29a052953333c70c5fad99a9df166f1c8aa5f504a9b4","patchedFileName":"customer_churn_leakage.patched.ipynb","patchedNotebookSha256":"6aee552e94f2dfbad8366cdd2435dcc5aa0c3c6cd45798a924779ae5008561fc","schemaVersion":"1","sourceNotebookSha256":"d0e9f3238753f1ca55534446d83e36041590f31c607a011def3f1d0db3a5bbc9","status":"VERIFIED","unrelatedCellSourceHashes":[{"afterSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","beforeSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","cellIndex":0,"unchanged":true},{"afterSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","beforeSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","cellIndex":1,"unchanged":true},{"afterSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","beforeSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","cellIndex":2,"unchanged":true},{"afterSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","beforeSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","cellIndex":4,"unchanged":true}],"verification":{"invariants":["VALID_NBFORMAT","EVALUATION_CELL_ONLY","NO_ADDED_DEPENDENCIES","GROUP_OVERLAP_ZERO","IDENTITY_FEATURE_REMOVED","METRICS_RECOMPUTED","DETERMINISTIC_PATCH_BYTES"],"status":"VERIFIED","violations":[]}}

‎fixtures/public/leakage_sample_patch_v1/customer_churn_leakage.patched.ipynb‎

Lines changed: 183 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,183 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "markdown",
5+
"id": "counterlab-intro",
6+
"metadata": {},
7+
"source": [
8+
"# Customer churn: does 99% mean new-customer generalization?\n",
9+
"\n",
10+
"This public sample intentionally uses a row-wise split while retaining `customer_id`."
11+
]
12+
},
13+
{
14+
"cell_type": "code",
15+
"execution_count": 1,
16+
"id": "load-fixture",
17+
"metadata": {},
18+
"outputs": [
19+
{
20+
"name": "stdout",
21+
"output_type": "stream",
22+
"text": [
23+
"Loaded 2880 rows across 480 customers\n"
24+
]
25+
}
26+
],
27+
"source": [
28+
"from pathlib import Path\n",
29+
"import pandas as pd\n",
30+
"\n",
31+
"data_path = Path('../public/customer_churn.csv')\n",
32+
"df = pd.read_csv(data_path)\n",
33+
"df[['customer_id', 'churned']].head()"
34+
]
35+
},
36+
{
37+
"cell_type": "markdown",
38+
"id": "evaluation-note",
39+
"metadata": {},
40+
"source": [
41+
"## Reported evaluation\n",
42+
"\n",
43+
"The next cell uses a random row split. Repeated observations from one customer can land on both sides."
44+
]
45+
},
46+
{
47+
"cell_type": "code",
48+
"execution_count": 2,
49+
"id": "random-row-split",
50+
"metadata": {},
51+
"outputs": [
52+
{
53+
"name": "stdout",
54+
"output_type": "stream",
55+
"text": [
56+
"Customer group-split accuracy: 0.625\n",
57+
"Customer group-split ROC AUC: 0.662\n",
58+
"Train/test customer overlap: 0 (0.0%)\n"
59+
]
60+
},
61+
{
62+
"name": "stdout",
63+
"output_type": "stream",
64+
"text": [
65+
"COUNTERLAB_PATCHED_RESULT={\"dropFeatures\":[\"customer_id\"],\"entityCounts\":{\"test\":120,\"train\":360},\"entityOverlap\":{\"count\":0,\"rate\":0.0},\"featureSetFingerprint\":\"9641773fdead963da5fb0582be52c255307fc4d601c4a4b580f5730d088f2362\",\"groupBy\":\"customer_id\",\"id\":\"patched_customer_group_split\",\"inputFingerprint\":\"5c482f39e4e948a92dab61bf9c9f5c6577fbe9fc688fd597c9fefd785ee1be70\",\"kernelVersion\":\"0.1.0\",\"metrics\":{\"accuracy\":0.625,\"rocAuc\":0.662186573617},\"model\":\"logistic_regression\",\"pipelineFingerprint\":\"234782290268e64b80af2e23b2b9b97268db8cd8e8740522834cde57cae78824\",\"resultHash\":\"df4cbaf93266decd43e51f3fe0bcb9d1d6d3476c1b0e466e0fa87fa8c43aa508\",\"sampleSizes\":{\"test\":720,\"train\":2160},\"schemaVersion\":\"1\",\"seed\":1729,\"splitStrategy\":\"group\"}"
66+
]
67+
}
68+
],
69+
"source": [
70+
"from sklearn.compose import ColumnTransformer\n",
71+
"from sklearn.impute import SimpleImputer\n",
72+
"from sklearn.linear_model import LogisticRegression\n",
73+
"from sklearn.metrics import accuracy_score, roc_auc_score\n",
74+
"from sklearn.model_selection import GroupShuffleSplit\n",
75+
"from sklearn.pipeline import Pipeline\n",
76+
"from sklearn.preprocessing import OneHotEncoder, StandardScaler\n",
77+
"\n",
78+
"groups = df['customer_id']\n",
79+
"X = df.drop(columns=['churned', 'customer_id', 'observation_id'])\n",
80+
"y = df['churned']\n",
81+
"categorical = [c for c in X.columns if X[c].dtype == 'object']\n",
82+
"numeric = [c for c in X.columns if c not in categorical]\n",
83+
"preprocess = ColumnTransformer([\n",
84+
" ('categorical', OneHotEncoder(handle_unknown='ignore'), categorical),\n",
85+
" ('numeric', Pipeline([('impute', SimpleImputer()), ('scale', StandardScaler())]), numeric),\n",
86+
"])\n",
87+
"model = Pipeline([('preprocess', preprocess), ('model', LogisticRegression(C=100, max_iter=2000))])\n",
88+
"splitter = GroupShuffleSplit(n_splits=1, test_size=0.25, random_state=1729)\n",
89+
"train_index, test_index = next(splitter.split(X, y, groups=groups))\n",
90+
"X_train, X_test = X.iloc[train_index], X.iloc[test_index]\n",
91+
"y_train, y_test = y.iloc[train_index], y.iloc[test_index]\n",
92+
"train_customers = set(groups.iloc[train_index])\n",
93+
"test_customers = set(groups.iloc[test_index])\n",
94+
"customer_overlap = train_customers.intersection(test_customers)\n",
95+
"assert not customer_overlap\n",
96+
"model.fit(X_train, y_train)\n",
97+
"probability = model.predict_proba(X_test)[:, 1]\n",
98+
"prediction = (probability >= 0.5).astype(int)\n",
99+
"print(f'Customer group-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n",
100+
"print(f'Customer group-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n",
101+
"print(f'Train/test customer overlap: {len(customer_overlap)}')"
102+
]
103+
},
104+
{
105+
"cell_type": "markdown",
106+
"id": "learner-claim",
107+
"metadata": {},
108+
"source": [
109+
"**Learner claim to test:** This result proves the model generalizes to customers it has never seen."
110+
]
111+
}
112+
],
113+
"metadata": {
114+
"counterlab": {
115+
"createdAt": "2026-07-14T00:00:00.000Z",
116+
"fixtureSeed": 1729,
117+
"resultHash": "a6ae7652e04e4d70196f991c63b8f7bcb3b76f8c4ab833d3ce2b626df0ab6c94",
118+
"schemaSummary": {
119+
"entityCandidates": [
120+
"customer_id"
121+
],
122+
"fields": [
123+
{
124+
"inferredType": "categorical",
125+
"name": "observation_id",
126+
"privacyClass": "feature"
127+
},
128+
{
129+
"inferredType": "categorical",
130+
"name": "customer_id",
131+
"privacyClass": "entity_identifier"
132+
},
133+
{
134+
"inferredType": "number",
135+
"name": "tenure_months",
136+
"privacyClass": "feature"
137+
},
138+
{
139+
"inferredType": "number",
140+
"name": "monthly_charges",
141+
"privacyClass": "feature"
142+
},
143+
{
144+
"inferredType": "number",
145+
"name": "support_tickets",
146+
"privacyClass": "feature"
147+
},
148+
{
149+
"inferredType": "number",
150+
"name": "activity_days_30d",
151+
"privacyClass": "feature"
152+
},
153+
{
154+
"inferredType": "categorical",
155+
"name": "contract_type",
156+
"privacyClass": "feature"
157+
},
158+
{
159+
"inferredType": "integer",
160+
"name": "churned",
161+
"privacyClass": "target"
162+
}
163+
],
164+
"rowCount": 2880,
165+
"targetCandidates": [
166+
"churned"
167+
]
168+
},
169+
"storedOutputSource": "counterlab-kernel"
170+
},
171+
"kernelspec": {
172+
"display_name": "Python 3",
173+
"language": "python",
174+
"name": "python3"
175+
},
176+
"language_info": {
177+
"name": "python",
178+
"version": "3.14"
179+
}
180+
},
181+
"nbformat": 4,
182+
"nbformat_minor": 5
183+
}

‎fixtures/public/leakage_sample_patch_v1/patch-kernel-result.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"cellDiff":"--- cell-3-before.py\n+++ cell-3-after.py\n@@ -2,11 +2,12 @@\n from sklearn.impute import SimpleImputer\n\n from sklearn.linear_model import LogisticRegression\n\n from sklearn.metrics import accuracy_score, roc_auc_score\n\n-from sklearn.model_selection import train_test_split\n\n+from sklearn.model_selection import GroupShuffleSplit\n\n from sklearn.pipeline import Pipeline\n\n from sklearn.preprocessing import OneHotEncoder, StandardScaler\n\n \n\n-X = df.drop(columns=['churned'])\n\n+groups = df['customer_id']\n\n+X = df.drop(columns=['churned', 'customer_id', 'observation_id'])\n\n y = df['churned']\n\n categorical = [c for c in X.columns if X[c].dtype == 'object']\n\n numeric = [c for c in X.columns if c not in categorical]\n\n@@ -15,11 +16,17 @@\n ('numeric', Pipeline([('impute', SimpleImputer()), ('scale', StandardScaler())]), numeric),\n\n ])\n\n model = Pipeline([('preprocess', preprocess), ('model', LogisticRegression(C=100, max_iter=2000))])\n\n-X_train, X_test, y_train, y_test = train_test_split(\n\n- X, y, test_size=0.25, random_state=1729, stratify=y\n\n-)\n\n+splitter = GroupShuffleSplit(n_splits=1, test_size=0.25, random_state=1729)\n\n+train_index, test_index = next(splitter.split(X, y, groups=groups))\n\n+X_train, X_test = X.iloc[train_index], X.iloc[test_index]\n\n+y_train, y_test = y.iloc[train_index], y.iloc[test_index]\n\n+train_customers = set(groups.iloc[train_index])\n\n+test_customers = set(groups.iloc[test_index])\n\n+customer_overlap = train_customers.intersection(test_customers)\n\n+assert not customer_overlap\n\n model.fit(X_train, y_train)\n\n probability = model.predict_proba(X_test)[:, 1]\n\n prediction = (probability >= 0.5).astype(int)\n\n-print(f'Random row-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n-print(f'Random row-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n+print(f'Customer group-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n+print(f'Customer group-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n\n+print(f'Train/test customer overlap: {len(customer_overlap)}')","changedCellIndices":[3],"correctedResult":{"dropFeatures":["customer_id"],"entityCounts":{"test":120,"train":360},"entityOverlap":{"count":0,"rate":0.0},"featureSetFingerprint":"9641773fdead963da5fb0582be52c255307fc4d601c4a4b580f5730d088f2362","groupBy":"customer_id","id":"patched_customer_group_split","inputFingerprint":"5c482f39e4e948a92dab61bf9c9f5c6577fbe9fc688fd597c9fefd785ee1be70","kernelVersion":"0.1.0","metrics":{"accuracy":0.625,"rocAuc":0.662186573617},"model":"logistic_regression","pipelineFingerprint":"234782290268e64b80af2e23b2b9b97268db8cd8e8740522834cde57cae78824","resultHash":"df4cbaf93266decd43e51f3fe0bcb9d1d6d3476c1b0e466e0fa87fa8c43aa508","sampleSizes":{"test":720,"train":2160},"schemaVersion":"1","seed":1729,"splitStrategy":"group"},"metadataFile":"fixtures/public/leakage_sample_patch_v1/customer_churn_leakage.patch.json","metadataHash":"ec7a42e85f9a4e8dfb3d29a052953333c70c5fad99a9df166f1c8aa5f504a9b4","originalSha256":"d0e9f3238753f1ca55534446d83e36041590f31c607a011def3f1d0db3a5bbc9","patchFile":"fixtures/public/leakage_sample_patch_v1/customer_churn_leakage.patched.ipynb","patchedSha256":"6aee552e94f2dfbad8366cdd2435dcc5aa0c3c6cd45798a924779ae5008561fc","schemaVersion":"1","status":"VERIFIED","unrelatedCellSourceHashes":[{"afterSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","beforeSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","cellIndex":0,"unchanged":true},{"afterSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","beforeSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","cellIndex":1,"unchanged":true},{"afterSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","beforeSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","cellIndex":2,"unchanged":true},{"afterSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","beforeSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","cellIndex":4,"unchanged":true}],"verification":{"invariants":["VALID_NBFORMAT","EVALUATION_CELL_ONLY","NO_ADDED_DEPENDENCIES","GROUP_OVERLAP_ZERO","IDENTITY_FEATURE_REMOVED","METRICS_RECOMPUTED","DETERMINISTIC_PATCH_BYTES"],"status":"VERIFIED","violations":[]},"verified":true}

‎fixtures/public/leakage_sample_patch_v1/patch-verification.json‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
{"candidateSha256":"6aee552e94f2dfbad8366cdd2435dcc5aa0c3c6cd45798a924779ae5008561fc","cellDiff":"--- cell-3-before.py\n+++ cell-3-after.py\n@@ -2,11 +2,12 @@\n from sklearn.impute import SimpleImputer\n\n from sklearn.linear_model import LogisticRegression\n\n from sklearn.metrics import accuracy_score, roc_auc_score\n\n-from sklearn.model_selection import train_test_split\n\n+from sklearn.model_selection import GroupShuffleSplit\n\n from sklearn.pipeline import Pipeline\n\n from sklearn.preprocessing import OneHotEncoder, StandardScaler\n\n \n\n-X = df.drop(columns=['churned'])\n\n+groups = df['customer_id']\n\n+X = df.drop(columns=['churned', 'customer_id', 'observation_id'])\n\n y = df['churned']\n\n categorical = [c for c in X.columns if X[c].dtype == 'object']\n\n numeric = [c for c in X.columns if c not in categorical]\n\n@@ -15,11 +16,17 @@\n ('numeric', Pipeline([('impute', SimpleImputer()), ('scale', StandardScaler())]), numeric),\n\n ])\n\n model = Pipeline([('preprocess', preprocess), ('model', LogisticRegression(C=100, max_iter=2000))])\n\n-X_train, X_test, y_train, y_test = train_test_split(\n\n- X, y, test_size=0.25, random_state=1729, stratify=y\n\n-)\n\n+splitter = GroupShuffleSplit(n_splits=1, test_size=0.25, random_state=1729)\n\n+train_index, test_index = next(splitter.split(X, y, groups=groups))\n\n+X_train, X_test = X.iloc[train_index], X.iloc[test_index]\n\n+y_train, y_test = y.iloc[train_index], y.iloc[test_index]\n\n+train_customers = set(groups.iloc[train_index])\n\n+test_customers = set(groups.iloc[test_index])\n\n+customer_overlap = train_customers.intersection(test_customers)\n\n+assert not customer_overlap\n\n model.fit(X_train, y_train)\n\n probability = model.predict_proba(X_test)[:, 1]\n\n prediction = (probability >= 0.5).astype(int)\n\n-print(f'Random row-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n-print(f'Random row-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n+print(f'Customer group-split accuracy: {accuracy_score(y_test, prediction):.3f}')\n\n+print(f'Customer group-split ROC AUC: {roc_auc_score(y_test, probability):.3f}')\n\n+print(f'Train/test customer overlap: {len(customer_overlap)}')","changedCellIndices":[3],"correctedResult":{"dropFeatures":["customer_id"],"entityCounts":{"test":120,"train":360},"entityOverlap":{"count":0,"rate":0.0},"featureSetFingerprint":"9641773fdead963da5fb0582be52c255307fc4d601c4a4b580f5730d088f2362","groupBy":"customer_id","id":"patched_customer_group_split","inputFingerprint":"5c482f39e4e948a92dab61bf9c9f5c6577fbe9fc688fd597c9fefd785ee1be70","kernelVersion":"0.1.0","metrics":{"accuracy":0.625,"rocAuc":0.662186573617},"model":"logistic_regression","pipelineFingerprint":"234782290268e64b80af2e23b2b9b97268db8cd8e8740522834cde57cae78824","resultHash":"df4cbaf93266decd43e51f3fe0bcb9d1d6d3476c1b0e466e0fa87fa8c43aa508","sampleSizes":{"test":720,"train":2160},"schemaVersion":"1","seed":1729,"splitStrategy":"group"},"schemaVersion":"1","status":"VERIFIED","unrelatedCellSourceHashes":[{"afterSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","beforeSha256":"209a116d9976e05001b46a3741a321daef5e28df283bd313341875564f97d665","cellIndex":0,"unchanged":true},{"afterSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","beforeSha256":"acf23811d7e111ee37be71dd4182e90ed69719f090586d66721882ec0f664abf","cellIndex":1,"unchanged":true},{"afterSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","beforeSha256":"a9461d19533c078644bd72d4f6004b051f9332a9489ba02709927e575869e28f","cellIndex":2,"unchanged":true},{"afterSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","beforeSha256":"0ec8bac100acc27b608fe93e584296e8d9f9fa80004238c706d318495ea8b3eb","cellIndex":4,"unchanged":true}],"verified":true,"violations":[]}

0 commit comments

Comments
 (0)