IBM · yoavkatz · May 27, 2026 · May 26, 2026 · May 26, 2026 · May 26, 2026
diff --git a/prepare/cards/arc.py b/prepare/cards/arc.py
@@ -7,7 +7,7 @@
 
 for subtask in subtasks:
     card = TaskCard(
-        loader=LoadHF(path="ai2_arc", name=subtask),
+        loader=LoadHF(path="allenai/ai2_arc", name=subtask),
         preprocess_steps=[
             Set({"topic": "science"}),
             Rename(field_to_field={"answerKey": "label", "choices": "_choices"}),

diff --git a/prepare/cards/billsum.py b/prepare/cards/billsum.py
@@ -10,7 +10,7 @@
 n_chars_to_filter_by_list = ["max", 6000, 10000]
 for n_chars_to_filter_by in n_chars_to_filter_by_list:
     card = TaskCard(
-        loader=LoadHF(path="billsum"),
+        loader=LoadHF(path="FiscalNote/billsum"),
         preprocess_steps=[
             SplitRandomMix(
                 {"train": "train[87.5%]", "validation": "train[12.5%]", "test": "test"}

diff --git a/prepare/cards/clinc_oos.py b/prepare/cards/clinc_oos.py
@@ -171,7 +171,7 @@
 
 for subset in ["small", "imbalanced", "plus"]:
     card = TaskCard(
-        loader=LoadHF(path="clinc_oos", name=subset),
+        loader=LoadHF(path="clinc/clinc_oos", name=subset),
         preprocess_steps=[
             Shuffle(page_size=sys.maxsize),
             Rename(field_to_field={"intent": "label"}),

diff --git a/prepare/cards/cnn_dailymail.py b/prepare/cards/cnn_dailymail.py
@@ -9,7 +9,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="cnn_dailymail", name="3.0.0"),
+    loader=LoadHF(path="abisee/cnn_dailymail", name="3.0.0"),
     preprocess_steps=[
         Rename(field_to_field={"article": "document"}),
         Wrap(field="highlights", inside="list", to_field="summaries"),

diff --git a/prepare/cards/copa.py b/prepare/cards/copa.py
@@ -10,7 +10,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="super_glue", name="copa"),
+    loader=LoadHF(path="aps/super_glue", name="copa"),
     preprocess_steps=[
         "splitters.small_no_test",
         ListFieldValues(fields=["choice1", "choice2"], to_field="choices"),

diff --git a/prepare/cards/dbpedia_14.py b/prepare/cards/dbpedia_14.py
@@ -34,7 +34,7 @@
 mappers = {str(i): cls for i, cls in enumerate(classes)}
 
 card = TaskCard(
-    loader=LoadHF(path=f"{dataset_name}"),
+    loader=LoadHF(path="fancyzhx/dbpedia_14"),
     preprocess_steps=[
         Shuffle(page_size=sys.maxsize),
         SplitRandomMix(

diff --git a/prepare/cards/ethos.py b/prepare/cards/ethos.py
@@ -12,7 +12,7 @@
 
 card = TaskCard(
     loader=LoadHF(
-        path="ethos",
+        path="iamollas/ethos",
         revision="refs/convert/parquet",
         data_dir="binary",
         splits=["train"],

diff --git a/prepare/cards/go_emotions.py b/prepare/cards/go_emotions.py
@@ -11,13 +11,13 @@
 dataset_name = "go_emotions"
 subset = "simplified"
 
-ds_builder = load_dataset_builder(dataset_name, subset)
+ds_builder = load_dataset_builder("google-research-datasets/go_emotions", subset)
 classes = ds_builder.info.features["labels"].feature.names
 
 mappers = {str(i): cls for i, cls in enumerate(classes)}
 
 card = TaskCard(
-    loader=LoadHF(path=dataset_name, name=subset),
+    loader=LoadHF(path="google-research-datasets/go_emotions", name=subset),
     preprocess_steps=[
         MapInstanceValues(mappers={"labels": mappers}, process_every_value=True),
         Set(

diff --git a/prepare/cards/hellaswag.py b/prepare/cards/hellaswag.py
@@ -4,7 +4,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="hellaswag"),
+    loader=LoadHF(path="Rowan/hellaswag"),
     preprocess_steps=[
         "splitters.large_no_test",
         Rename(

diff --git a/prepare/cards/human_eval.py b/prepare/cards/human_eval.py
@@ -15,7 +15,7 @@
     get_asserts = '[t for t in re.findall(r"assert.*?(?=\\n\\s*assert|$)", test.replace("candidate", entry_point), re.DOTALL)]'
 
     card = TaskCard(
-        loader=LoadHF(path="openai_humaneval", split="test"),
+        loader=LoadHF(path="openai/openai_humaneval", split="test"),
         preprocess_steps=[
             ExecuteExpression(
                 expression=get_asserts, imports_list=["re"], to_field="test_list"

diff --git a/prepare/cards/ledgar.py b/prepare/cards/ledgar.py
@@ -10,15 +10,15 @@
 
 dataset_name = "ledgar"
 
-ds_builder = load_dataset_builder("lex_glue", dataset_name)
+ds_builder = load_dataset_builder("coastalcph/lex_glue", dataset_name)
 classlabels = ds_builder.info.features["label"]
 
 mappers = {}
 for i in range(len(classlabels.names)):
     mappers[str(i)] = classlabels.names[i]
 
 card = TaskCard(
-    loader=LoadHF(path="lex_glue", name=f"{dataset_name}"),
+    loader=LoadHF(path="coastalcph/lex_glue", name=f"{dataset_name}"),
     preprocess_steps=[
         MapInstanceValues({"label": mappers}),
         Set(

diff --git a/prepare/cards/mbpp.py b/prepare/cards/mbpp.py
@@ -11,7 +11,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="mbpp", name="full", split="test"),
+    loader=LoadHF(path="google-research-datasets/mbpp", name="full", split="test"),
     preprocess_steps=[
         JoinStr(field_to_field={"test_list": "test_list_str"}, separator=os.linesep),
     ],

diff --git a/prepare/cards/mlsum.py b/prepare/cards/mlsum.py
@@ -12,7 +12,7 @@
 for lang in langs:
     card = TaskCard(
         loader=LoadHF(
-            path="mlsum",
+            path="reciTAL/mlsum",
             revision="refs/convert/parquet",
             data_dir=lang,
             splits=["train", "test", "validation"],

diff --git a/prepare/cards/openbookqa.py b/prepare/cards/openbookqa.py
@@ -4,7 +4,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="openbookqa"),
+    loader=LoadHF(path="allenai/openbookqa"),
     preprocess_steps=[
         Rename(
             field_to_field={"choices/text": "choices_text", "choices/label": "labels"},

diff --git a/prepare/cards/piqa.py b/prepare/cards/piqa.py
@@ -4,7 +4,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="piqa", revision="refs/pr/9"),
+    loader=LoadHF(path="ybisk/piqa", revision="refs/pr/9"),
     preprocess_steps=[
         ListFieldValues(fields=["sol1", "sol2"], to_field="choices"),
         Rename(

diff --git a/prepare/cards/race.py b/prepare/cards/race.py
@@ -7,7 +7,7 @@
 
 for subset in ["all", "high", "middle"]:
     card = TaskCard(
-        loader=LoadHF(path="race", name=subset),
+        loader=LoadHF(path="ehovy/race", name=subset),
         preprocess_steps=[
             Set({"numbering": numbering}),
             IndexOf(search_in="numbering", index_of="answer", to_field="answer"),

diff --git a/prepare/cards/sciq.py b/prepare/cards/sciq.py
@@ -10,7 +10,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="sciq"),
+    loader=LoadHF(path="allenai/sciq"),
     preprocess_steps=[
         ListFieldValues(
             fields=["distractor1", "distractor2", "distractor3", "correct_answer"],

diff --git a/prepare/cards/squad.py b/prepare/cards/squad.py
@@ -4,7 +4,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="squad"),
+    loader=LoadHF(path="rajpurkar/squad"),
     preprocess_steps=[
         "splitters.small_no_test",
         Copy(field="answers/text", to_field="answers"),

diff --git a/prepare/cards/translation/wmt/en_de.py b/prepare/cards/translation/wmt/en_de.py
@@ -3,7 +3,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="wmt16", name="de-en", streaming=True),
+    loader=LoadHF(path="wmt/wmt16", name="de-en", streaming=True),
     preprocess_steps=[
         Copy(
             field_to_field=[

diff --git a/prepare/cards/translation/wmt/en_fr.py b/prepare/cards/translation/wmt/en_fr.py
@@ -3,7 +3,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="wmt14", name="fr-en", streaming=True),
+    loader=LoadHF(path="wmt/wmt14", name="fr-en", streaming=True),
     preprocess_steps=[
         Copy(
             field_to_field=[

diff --git a/prepare/cards/translation/wmt/en_ro.py b/prepare/cards/translation/wmt/en_ro.py
@@ -3,7 +3,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="wmt16", name="ro-en", streaming=True),
+    loader=LoadHF(path="wmt/wmt16", name="ro-en", streaming=True),
     preprocess_steps=[
         Copy(
             field_to_field=[

diff --git a/prepare/cards/trec.py b/prepare/cards/trec.py
@@ -124,7 +124,7 @@
 
 card = TaskCard(
     loader=LoadHF(
-        path="trec", revision="refs/convert/parquet", splits=["train", "test"]
+        path="CogComp/trec", revision="refs/convert/parquet", splits=["train", "test"]
     ),
     preprocess_steps=[
         Shuffle(page_size=sys.maxsize),

diff --git a/prepare/cards/unfair_tos.py b/prepare/cards/unfair_tos.py
@@ -11,15 +11,15 @@
 
 dataset_name = "unfair_tos"
 
-ds_builder = load_dataset_builder("lex_glue", dataset_name)
+ds_builder = load_dataset_builder("coastalcph/lex_glue", dataset_name)
 classlabels = ds_builder.info.features["labels"]
 
 mappers = {}
 for i in range(len(classlabels.feature.names)):
     mappers[str(i)] = classlabels.feature.names[i]
 
 card = TaskCard(
-    loader=LoadHF(path="lex_glue", name=f"{dataset_name}"),
+    loader=LoadHF(path="coastalcph/lex_glue", name=f"{dataset_name}"),
     preprocess_steps=[
         MapInstanceValues(mappers={"labels": mappers}, process_every_value=True),
         Set(

diff --git a/prepare/cards/wiki_bio.py b/prepare/cards/wiki_bio.py
@@ -11,7 +11,7 @@
 
 card = TaskCard(
     loader=LoadHF(
-        path="wiki_bio",
+        path="michaelauli/wiki_bio",
         revision="refs/convert/parquet",
         splits=["train", "validation", "test"],
     ),

diff --git a/prepare/cards/winogrande.py b/prepare/cards/winogrande.py
@@ -6,7 +6,9 @@
 for subtask in ["debiased", "l", "m", "s", "xl", "xs"]:
     card = TaskCard(
         loader=LoadHF(
-            path="winogrande", name=f"winogrande_{subtask}", revision="refs/pr/6"
+            path="allenai/winogrande",
+            name=f"winogrande_{subtask}",
+            revision="refs/pr/6",
         ),
         preprocess_steps=[
             "splitters.small_no_test",

diff --git a/prepare/cards/wsc.py b/prepare/cards/wsc.py
@@ -10,7 +10,7 @@
 from unitxt.test_utils.card import test_card
 
 card = TaskCard(
-    loader=LoadHF(path="super_glue", name="wsc"),
+    loader=LoadHF(path="aps/super_glue", name="wsc"),
     preprocess_steps=[
         "splitters.small_no_test",
         MapInstanceValues(mappers={"label": {"0": "False", "1": "True"}}),

diff --git a/prepare/cards/xnli.py b/prepare/cards/xnli.py
@@ -29,7 +29,7 @@
 
 for lang in langs:
     card = TaskCard(
-        loader=LoadHF(path="xnli", name=lang),
+        loader=LoadHF(path="facebook/xnli", name=lang),
         preprocess_steps=[
             "splitters.small_no_test",
             Rename(field_to_field={"premise": "text_a", "hypothesis": "text_b"}),

diff --git a/prepare/cards/yahoo_answers_topics.py b/prepare/cards/yahoo_answers_topics.py
@@ -30,7 +30,7 @@
 mappers = {str(i): cls for i, cls in enumerate(classes)}
 
 card = TaskCard(
-    loader=LoadHF(path=f"{dataset_name}"),
+    loader=LoadHF(path="community-datasets/yahoo_answers_topics"),
     preprocess_steps=[
         Shuffle(page_size=sys.maxsize),
         SplitRandomMix(

diff --git a/src/unitxt/catalog/cards/ai2_arc/arc_challenge.json b/src/unitxt/catalog/cards/ai2_arc/arc_challenge.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "ai2_arc",
+        "path": "allenai/ai2_arc",
         "name": "ARC-Challenge"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/ai2_arc/arc_easy.json b/src/unitxt/catalog/cards/ai2_arc/arc_easy.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "ai2_arc",
+        "path": "allenai/ai2_arc",
         "name": "ARC-Easy"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/billsum.json b/src/unitxt/catalog/cards/billsum.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "billsum"
+        "path": "FiscalNote/billsum"
     },
     "preprocess_steps": [
         {

diff --git a/src/unitxt/catalog/cards/billsum_document_filtered_to_10000_chars.json b/src/unitxt/catalog/cards/billsum_document_filtered_to_10000_chars.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "billsum"
+        "path": "FiscalNote/billsum"
     },
     "preprocess_steps": [
         {

diff --git a/src/unitxt/catalog/cards/billsum_document_filtered_to_6000_chars.json b/src/unitxt/catalog/cards/billsum_document_filtered_to_6000_chars.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "billsum"
+        "path": "FiscalNote/billsum"
     },
     "preprocess_steps": [
         {

diff --git a/src/unitxt/catalog/cards/clinc_oos/imbalanced.json b/src/unitxt/catalog/cards/clinc_oos/imbalanced.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "clinc_oos",
+        "path": "clinc/clinc_oos",
         "name": "imbalanced"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/clinc_oos/plus.json b/src/unitxt/catalog/cards/clinc_oos/plus.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "clinc_oos",
+        "path": "clinc/clinc_oos",
         "name": "plus"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/clinc_oos/small.json b/src/unitxt/catalog/cards/clinc_oos/small.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "clinc_oos",
+        "path": "clinc/clinc_oos",
         "name": "small"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/cnn_dailymail.json b/src/unitxt/catalog/cards/cnn_dailymail.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "cnn_dailymail",
+        "path": "abisee/cnn_dailymail",
         "name": "3.0.0"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/copa.json b/src/unitxt/catalog/cards/copa.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "super_glue",
+        "path": "aps/super_glue",
         "name": "copa"
     },
     "preprocess_steps": [

diff --git a/src/unitxt/catalog/cards/dbpedia_14.json b/src/unitxt/catalog/cards/dbpedia_14.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "dbpedia_14"
+        "path": "fancyzhx/dbpedia_14"
     },
     "preprocess_steps": [
         {

diff --git a/src/unitxt/catalog/cards/ethos_binary.json b/src/unitxt/catalog/cards/ethos_binary.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "ethos",
+        "path": "iamollas/ethos",
         "revision": "refs/convert/parquet",
         "data_dir": "binary",
         "splits": [

diff --git a/src/unitxt/catalog/cards/go_emotions/simplified.json b/src/unitxt/catalog/cards/go_emotions/simplified.json
@@ -2,7 +2,7 @@
     "__type__": "task_card",
     "loader": {
         "__type__": "load_hf",
-        "path": "go_emotions",
+        "path": "google-research-datasets/go_emotions",
         "name": "simplified"
     },
     "preprocess_steps": [