{ "datasets": [ { "category": "environment_space", "category_label": "Environment & Space", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 14, "controlled_test_data": false, "dataset_url": "https://www.kaggle.com/datasets/dakshbhalala/uci-air-quality-dataset", "has_published_results": true, "key": "Air-Quality", "label": "Air-Quality", "measurement_eligibility": "eligible", "numeric_column_count": 14, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 9357, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 9357, "shared_metadata_bytes": 158696, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1047984, "source": "Kaggle", "source_order": 1, "source_url": "https://www.kaggle.com/datasets/dakshbhalala/uci-air-quality-dataset", "value_cell_count": 121641, "mean_valid_values_per_numerical_sequence": 9357.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://archive.ics.uci.edu/dataset/515/bar+crawl+detecting+heavy+drinking", "has_published_results": true, "key": "Bar-Crawl", "label": "Bar-Crawl", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 14057567, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 14057567, "shared_metadata_bytes": 228454971, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 449842144, "source": "UCI Machine Learning Repository", "source_order": 2, "source_url": "https://archive.ics.uci.edu/dataset/515/bar+crawl+detecting+heavy+drinking", "value_cell_count": 42172701, "mean_valid_values_per_numerical_sequence": 14057567.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 7, "controlled_test_data": false, "dataset_url": "https://www.kaggle.com/datasets/pulkit8595/movebank-animal-tracking", "has_published_results": true, "key": "Bird-migration", "label": "Bird-migration", "measurement_eligibility": "eligible", "numeric_column_count": 7, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 89867, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 89867, "shared_metadata_bytes": 1464666, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 5032552, "source": "Kaggle", "source_order": 3, "source_url": "https://www.kaggle.com/datasets/pulkit8595/movebank-animal-tracking", "value_cell_count": 539202, "mean_valid_values_per_numerical_sequence": 89867.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://github.com/yhliu918/Learn-to-Compress", "has_published_results": true, "key": "Comments", "label": "Comments", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 11341008, "published_result_row_count_matches_catalog": false, "published_result_scope": "published_measurements", "row_count": 9411727, "shared_metadata_bytes": 152949316, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 301175264, "source": "GitHub", "source_order": 4, "source_url": "https://github.com/yhliu918/Learn-to-Compress", "value_cell_count": 28235181, "mean_valid_values_per_numerical_sequence": 9411727.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 8, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/IGlocations2/tables/IGlocations2_1.table.sql", "has_published_results": true, "key": "IGlocations2", "label": "IGlocations2", "measurement_eligibility": "eligible", "numeric_column_count": 8, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 4341308, "published_result_row_count_matches_catalog": false, "published_result_scope": "published_measurements", "row_count": 4323473, "shared_metadata_bytes": 70273541, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 276702000, "source": "GitHub", "source_order": 5, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/IGlocations2/tables/IGlocations2_1.table.sql", "value_cell_count": 30264311, "mean_valid_values_per_numerical_sequence": 4323468.142857143 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 64, "controlled_test_data": false, "dataset_url": "https://www.meteoblue.com/en/weather/archive/export/basel_switzerland", "has_published_results": true, "key": "meteoblue", "label": "meteoblue", "measurement_eligibility": "eligible", "numeric_column_count": 64, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 143760, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 143760, "shared_metadata_bytes": 2366868, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 73580352, "source": "meteoblue.com", "source_order": 7, "source_url": "https://www.meteoblue.com/en/weather/archive/export/basel_switzerland", "value_cell_count": 9056880, "mean_valid_values_per_numerical_sequence": 143710.85714285713 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://www.kaggle.com/code/ramyahr/metro-interstate-traffic-volume", "has_published_results": true, "key": "Metro-Traffic", "label": "Metro-Traffic", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 48204, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 48204, "shared_metadata_bytes": 787068, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2313792, "source": "Kaggle", "source_order": 8, "source_url": "https://www.kaggle.com/code/ramyahr/metro-interstate-traffic-volume", "value_cell_count": 241020, "mean_valid_values_per_numerical_sequence": 48204.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page", "has_published_results": true, "key": "NYC_Yellow_Taxi_Trip", "label": "NYC_Yellow_Taxi_Trip", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 47248845, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 47248845, "shared_metadata_bytes": 768199379, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 755981520, "source": "nyc.gov", "source_order": 9, "source_url": "https://www.nyc.gov/site/tlc/about/tlc-trip-record-data.page", "value_cell_count": 47248845, "mean_valid_values_per_numerical_sequence": 47248845.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://grouplens.org/datasets/movielens/", "has_published_results": true, "key": "rating", "label": "rating", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 20000263, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 20000263, "shared_metadata_bytes": 325014711, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 640008416, "source": "grouplens.org", "source_order": 10, "source_url": "https://grouplens.org/datasets/movielens/", "value_cell_count": 60000789, "mean_valid_values_per_numerical_sequence": 20000263.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/RealEstate1/tables/RealEstate1_1.table.sql", "has_published_results": true, "key": "RealEstate1", "label": "RealEstate1", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 19531359, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 19531359, "shared_metadata_bytes": 317442361, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 937505232, "source": "GitHub", "source_order": 11, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/RealEstate1/tables/RealEstate1_1.table.sql", "value_cell_count": 97656795, "mean_valid_values_per_numerical_sequence": 19531359.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/RealEstate2/tables/RealEstate2_1.table.sql", "has_published_results": true, "key": "RealEstate2", "label": "RealEstate2", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 9487983, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 9487983, "shared_metadata_bytes": 154206244, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 378609928, "source": "GitHub", "source_order": 12, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/RealEstate2/tables/RealEstate2_1.table.sql", "value_cell_count": 37951932, "mean_valid_values_per_numerical_sequence": 9459564.5 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Romance/tables/Romance_1.table.sql", "has_published_results": true, "key": "Romance", "label": "Romance", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 3173176, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 3173176, "shared_metadata_bytes": 51569154, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 93478304, "source": "GitHub", "source_order": 13, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Romance/tables/Romance_1.table.sql", "value_cell_count": 15865880, "mean_valid_values_per_numerical_sequence": 2208926.4 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 46, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Telco/tables/Telco_1.table.sql", "has_published_results": true, "key": "Telco", "label": "Telco", "measurement_eligibility": "eligible", "numeric_column_count": 46, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 2913060, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 2913060, "shared_metadata_bytes": 47355618, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1069926160, "source": "GitHub", "source_order": 14, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Telco/tables/Telco_1.table.sql", "value_cell_count": 131087700, "mean_valid_values_per_numerical_sequence": 2907282.4444444445 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/TrainsUK2/tables/TrainsUK2_1.table.sql", "has_published_results": true, "key": "TrainsUK2", "label": "TrainsUK2", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 31123554, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 31123554, "shared_metadata_bytes": 505818718, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 989810320, "source": "GitHub", "source_order": 15, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/TrainsUK2/tables/TrainsUK2_1.table.sql", "value_cell_count": 62247108, "mean_valid_values_per_numerical_sequence": 30979075.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 18, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Uberlandia/tables/Uberlandia_1.table.sql", "has_published_results": true, "key": "Uberlandia", "label": "Uberlandia", "measurement_eligibility": "eligible", "numeric_column_count": 18, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 7559227, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 7559227, "shared_metadata_bytes": 122862061, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1017931792, "source": "GitHub", "source_order": 16, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Uberlandia/tables/Uberlandia_1.table.sql", "value_cell_count": 105829178, "mean_valid_values_per_numerical_sequence": 7465713.571428572 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 238, "controlled_test_data": false, "dataset_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Wins/tables/Wins_1.table.sql", "has_published_results": true, "key": "Wins", "label": "Wins", "measurement_eligibility": "eligible", "numeric_column_count": 238, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 556067, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 556067, "shared_metadata_bytes": 9135310, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1057996808, "source": "GitHub", "source_order": 17, "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Wins/tables/Wins_1.table.sql", "value_cell_count": 130675745, "mean_valid_values_per_numerical_sequence": 555789.8936170213 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "legacy", "cohort_label": "Existing benchmark collection", "column_count": 9, "controlled_test_data": false, "dataset_url": "https://event.cwi.nl/da/PublicBIbenchmark/", "has_published_results": true, "key": "YaleLanguages", "label": "YaleLanguages", "measurement_eligibility": "eligible", "numeric_column_count": 9, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": 5762082, "published_result_row_count_matches_catalog": true, "published_result_scope": "published_measurements", "row_count": 5762082, "shared_metadata_bytes": 93658600, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 408945480, "source": "event.cwi.nl", "source_order": 18, "source_url": "https://event.cwi.nl/da/PublicBIbenchmark/", "value_cell_count": 46096656, "mean_valid_values_per_numerical_sequence": 5669512.875 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 29, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ETDataset-ett", "has_published_results": true, "key": "ETDataset-ett", "label": "ETDataset-ett", "measurement_eligibility": "eligible", "numeric_column_count": 28, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 174200, "shared_metadata_bytes": 3509250, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 6271200, "source": "GitHub", "source_order": 19, "source_url": "https://github.com/zhouhaoyi/ETDataset", "value_cell_count": 1219400, "mean_valid_values_per_numerical_sequence": 43550.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 34, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/METR-LA", "has_published_results": true, "key": "METR-LA", "label": "METR-LA", "measurement_eligibility": "eligible", "numeric_column_count": 33, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7089543, "shared_metadata_bytes": 142986117, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 243885744, "source": "Hugging Face", "source_order": 20, "source_url": "https://huggingface.co/datasets/witgaw/METR-LA", "value_cell_count": 46792350, "mean_valid_values_per_numerical_sequence": 6850.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 10, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/PEMS-BAY", "has_published_results": true, "key": "PEMS-BAY", "label": "PEMS-BAY", "measurement_eligibility": "eligible", "numeric_column_count": 9, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 16930225, "shared_metadata_bytes": 341155876, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 257344100, "source": "Hugging Face", "source_order": 21, "source_url": "https://huggingface.co/datasets/witgaw/PEMS-BAY", "value_cell_count": 30475575, "mean_valid_values_per_numerical_sequence": 10419.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 482, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/SpatialEpiBench", "has_published_results": true, "key": "SpatialEpiBench", "label": "SpatialEpiBench", "measurement_eligibility": "eligible", "numeric_column_count": 481, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 9845, "shared_metadata_bytes": 307010, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3673904, "source": "Hugging Face", "source_order": 22, "source_url": "https://huggingface.co/datasets/ruiqil/SpatialEpiBench", "value_cell_count": 450736, "mean_valid_values_per_numerical_sequence": 934.2889812889813 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ahr999-dataset", "has_published_results": true, "key": "ahr999-dataset", "label": "ahr999-dataset", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 3218, "shared_metadata_bytes": 67023, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 121032, "source": "Hugging Face", "source_order": 24, "source_url": "https://huggingface.co/datasets/kshift/ahr999-dataset", "value_cell_count": 12872, "mean_valid_values_per_numerical_sequence": 2977.75 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 7, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ast_spacemobile_fleet_data", "has_published_results": true, "key": "ast_spacemobile_fleet_data", "label": "ast_spacemobile_fleet_data", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 147, "shared_metadata_bytes": 6222, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 8232, "source": "Hugging Face", "source_order": 26, "source_url": "https://huggingface.co/datasets/juliensimon/ast-spacemobile-fleet-data/raw/2577a529b22f3ed8ed6b65018bca0a36e373b74e/README.md", "value_cell_count": 882, "mean_valid_values_per_numerical_sequence": 147.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/australia_solar", "has_published_results": true, "key": "australia_solar", "label": "australia_solar", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 105189, "shared_metadata_bytes": 2117875, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1185440, "source": "arXiv", "source_order": 27, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 105189, "mean_valid_values_per_numerical_sequence": 28660.666666666668 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/australian_electricity_demand", "has_published_results": true, "key": "australian_electricity_demand", "label": "australian_electricity_demand", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1155264, "shared_metadata_bytes": 23239922, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 23105280, "source": "Zenodo", "source_order": 28, "source_url": "https://zenodo.org/record/4659727", "value_cell_count": 1155264, "mean_valid_values_per_numerical_sequence": 231052.8 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/auto_production_sf", "has_published_results": true, "key": "auto_production_sf", "label": "auto_production_sf", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 367, "shared_metadata_bytes": 9504, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 4404, "source": "arXiv", "source_order": 29, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 367, "mean_valid_values_per_numerical_sequence": 367.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/azure2019_u", "has_published_results": true, "key": "azure2019_u", "label": "azure2019_u", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 329019, "shared_metadata_bytes": 6887119, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3948228, "source": "arXiv", "source_order": 30, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 329019, "mean_valid_values_per_numerical_sequence": 1406.0641025641025 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/bitcoin", "has_published_results": true, "key": "bitcoin", "label": "bitcoin", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 82443, "shared_metadata_bytes": 1673626, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1648860, "source": "Zenodo", "source_order": 31, "source_url": "https://zenodo.org/record/5121965", "value_cell_count": 82443, "mean_valid_values_per_numerical_sequence": 4580.166666666667 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/bitcoin_price_timeseries", "has_published_results": true, "key": "bitcoin_price_timeseries", "label": "bitcoin_price_timeseries", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1048575, "shared_metadata_bytes": 21086359, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 50331600, "source": "Hugging Face", "source_order": 32, "source_url": "https://huggingface.co/datasets/Farmaanaa/bitcoin_price_timeseries", "value_cell_count": 5242875, "mean_valid_values_per_numerical_sequence": 1048575.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/coastal_t_s", "has_published_results": true, "key": "coastal_t_s", "label": "coastal_t_s", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 4437507, "shared_metadata_bytes": 89316019, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 53249808, "source": "arXiv", "source_order": 34, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 4437507, "mean_valid_values_per_numerical_sequence": 30815.541666666668 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/commodity_import", "has_published_results": true, "key": "commodity_import", "label": "commodity_import", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 5578, "shared_metadata_bytes": 123302, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 66936, "source": "arXiv", "source_order": 35, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 5578, "mean_valid_values_per_numerical_sequence": 697.25 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/commodity_production", "has_published_results": true, "key": "commodity_production", "label": "commodity_production", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 10403, "shared_metadata_bytes": 254384, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 124836, "source": "arXiv", "source_order": 36, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 10403, "mean_valid_values_per_numerical_sequence": 325.09375 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/covid_deaths-monash", "has_published_results": true, "key": "covid_deaths-monash", "label": "covid_deaths-monash", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 56392, "shared_metadata_bytes": 1492923, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1127840, "source": "Zenodo", "source_order": 37, "source_url": "https://zenodo.org/record/4656009", "value_cell_count": 56392, "mean_valid_values_per_numerical_sequence": 212.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/cphl", "has_published_results": true, "key": "cphl", "label": "cphl", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 70045, "shared_metadata_bytes": 1414669, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 827340, "source": "arXiv", "source_order": 38, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 70045, "mean_valid_values_per_numerical_sequence": 8343.125 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/crypto", "has_published_results": true, "key": "crypto", "label": "crypto", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 11368, "shared_metadata_bytes": 233252, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 136416, "source": "arXiv", "source_order": 39, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 11368, "mean_valid_values_per_numerical_sequence": 2842.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/crypto_data", "has_published_results": true, "key": "crypto_data", "label": "crypto_data", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 216226, "shared_metadata_bytes": 4689647, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 10378848, "source": "Hugging Face", "source_order": 40, "source_url": "https://huggingface.co/datasets/sebdg/crypto_data", "value_cell_count": 1081130, "mean_valid_values_per_numerical_sequence": 735.4625850340136 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/current_velocity", "has_published_results": true, "key": "current_velocity", "label": "current_velocity", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 3158208, "shared_metadata_bytes": 63856457, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 37897920, "source": "arXiv", "source_order": 41, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 3158208, "mean_valid_values_per_numerical_sequence": 8097.6 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 48, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/deep-space-probes", "has_published_results": true, "key": "deep-space-probes", "label": "deep-space-probes", "measurement_eligibility": "eligible", "numeric_column_count": 47, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 978408, "shared_metadata_bytes": 19686119, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 47209248, "source": "spdf.gsfc.nasa.gov", "source_order": 42, "source_url": "https://spdf.gsfc.nasa.gov/", "value_cell_count": 45985176, "mean_valid_values_per_numerical_sequence": 51818.4 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/dst-index", "has_published_results": true, "key": "dst-index", "label": "dst-index", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 783038, "shared_metadata_bytes": 15743342, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 12528608, "source": "Hugging Face", "source_order": 44, "source_url": "https://huggingface.co/datasets/juliensimon/dst-index", "value_cell_count": 1566076, "mean_valid_values_per_numerical_sequence": 391519.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ecdc_covid", "has_published_results": true, "key": "ecdc_covid", "label": "ecdc_covid", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 12696, "shared_metadata_bytes": 286926, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 150728, "source": "arXiv", "source_order": 45, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 12696, "mean_valid_values_per_numerical_sequence": 491.6 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 46, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/eea_pm25_forecasting", "has_published_results": true, "key": "eea_pm25_forecasting", "label": "eea_pm25_forecasting", "measurement_eligibility": "eligible", "numeric_column_count": 45, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1945153, "shared_metadata_bytes": 39154578, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 715816304, "source": "Hugging Face", "source_order": 46, "source_url": "https://huggingface.co/datasets/cosuleabianca/eea-pm25-forecasting", "value_cell_count": 87531885, "mean_valid_values_per_numerical_sequence": 51188.23684210526 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/electricity_demand", "has_published_results": true, "key": "electricity_demand", "label": "electricity_demand", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1344, "shared_metadata_bytes": 29174, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 32256, "source": "Hugging Face", "source_order": 47, "source_url": "https://huggingface.co/datasets/rajistics/electricity_demand", "value_cell_count": 2688, "mean_valid_values_per_numerical_sequence": 1344.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 371, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/electricity_load_2011_2014", "has_published_results": true, "key": "electricity_load_2011_2014", "label": "electricity_load_2011_2014", "measurement_eligibility": "eligible", "numeric_column_count": 370, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 140256, "shared_metadata_bytes": 2899226, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 208700928, "source": "UCI Machine Learning Repository", "source_order": 48, "source_url": "https://archive.ics.uci.edu/dataset/321/electricityloaddiagrams20112014", "value_cell_count": 51894720, "mean_valid_values_per_numerical_sequence": 140256.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/electricity_production", "has_published_results": true, "key": "electricity_production", "label": "electricity_production", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 397, "shared_metadata_bytes": 10053, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 4764, "source": "Hugging Face", "source_order": 49, "source_url": "https://huggingface.co/datasets/huggingface/electricity-production", "value_cell_count": 397, "mean_valid_values_per_numerical_sequence": 397.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/enedis-with-holidays", "has_published_results": true, "key": "enedis-with-holidays", "label": "enedis-with-holidays", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 96780, "shared_metadata_bytes": 1949444, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2322720, "source": "Hugging Face", "source_order": 50, "source_url": "https://huggingface.co/datasets/theforecastingcompany/enedis-with-holidays", "value_cell_count": 387120, "mean_valid_values_per_numerical_sequence": 32260.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/epf_electricity_price", "has_published_results": true, "key": "epf_electricity_price", "label": "epf_electricity_price", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 262080, "shared_metadata_bytes": 5275718, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3144960, "source": "arXiv", "source_order": 51, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 262080, "mean_valid_values_per_numerical_sequence": 52416.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/eweld_load", "has_published_results": true, "key": "eweld_load", "label": "eweld_load", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 205440, "shared_metadata_bytes": 4142828, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2465280, "source": "arXiv", "source_order": 53, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 205440, "mean_valid_values_per_numerical_sequence": 20544.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 9, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/exchange_rate", "has_published_results": true, "key": "exchange_rate", "label": "exchange_rate", "measurement_eligibility": "eligible", "numeric_column_count": 8, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7588, "shared_metadata_bytes": 155196, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 303520, "source": "Hugging Face", "source_order": 54, "source_url": "https://huggingface.co/datasets/thuml/Time-Series-Library", "value_cell_count": 60704, "mean_valid_values_per_numerical_sequence": 7588.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 10, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/faang_engineered_time_series_features_2013_2025", "has_published_results": true, "key": "faang_engineered_time_series_features_2013_2025", "label": "faang_engineered_time_series_features_2013_2025", "measurement_eligibility": "eligible", "numeric_column_count": 9, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 32545, "shared_metadata_bytes": 668461, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1432560, "source": "Hugging Face", "source_order": 55, "source_url": "https://huggingface.co/datasets/ML-Owl/faang-engineered-time-series-features-2013-2025", "value_cell_count": 146525, "mean_valid_values_per_numerical_sequence": 3256.1111111111113 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/finland_traffic", "has_published_results": true, "key": "finland_traffic", "label": "finland_traffic", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 35136, "shared_metadata_bytes": 707951, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 421632, "source": "arXiv", "source_order": 56, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 35136, "mean_valid_values_per_numerical_sequence": 35136.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/forex_factory_calendar", "has_published_results": true, "key": "forex_factory_calendar", "label": "forex_factory_calendar", "measurement_eligibility": "eligible", "numeric_column_count": 3, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 83427, "shared_metadata_bytes": 2640759, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1002520, "source": "Hugging Face", "source_order": 57, "source_url": "https://huggingface.co/datasets/Tropstan/Forex_Factory_Calendar", "value_cell_count": 250281, "mean_valid_values_per_numerical_sequence": 177.4915254237288 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/fred_md", "has_published_results": true, "key": "fred_md", "label": "fred_md", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 77896, "shared_metadata_bytes": 1698923, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1557920, "source": "Zenodo", "source_order": 58, "source_url": "https://zenodo.org/record/4654833", "value_cell_count": 77896, "mean_valid_values_per_numerical_sequence": 728.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 67, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/freshretailnet_lt", "has_published_results": false, "key": "freshretailnet_lt", "label": "freshretailnet_lt", "measurement_eligibility": "corrected_input_retest_pending", "numeric_column_count": 66, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "replacement_pending", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7939549, "shared_metadata_bytes": 209889129, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 554169332, "source": "Hugging Face", "source_order": 60, "source_url": "https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-LT", "value_cell_count": 74815941, "has_historical_published_measurements": true, "has_published_measurements": false, "current_input_issue": "The old export retained 66/114 table-qualified numeric columns and dropped 48 trailing train columns under the 1 GB cap. All 7,939,549 source rows were retained, but the value-column universe is incomplete.", "mean_valid_values_per_numerical_sequence": 241.03794893591183 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/fulus_lyd_rates_2025", "has_published_results": true, "key": "fulus_lyd_rates_2025", "label": "fulus_lyd_rates_2025", "measurement_eligibility": "eligible", "numeric_column_count": 3, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 15471, "shared_metadata_bytes": 320929, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 495072, "source": "Hugging Face", "source_order": 61, "source_url": "https://huggingface.co/datasets/Binary-ly/fulus-lyd-rates-2025/raw/01b573c4ef5385228f0f2b86d7feb1a919baad9b/README.md", "value_cell_count": 30942, "mean_valid_values_per_numerical_sequence": 1933.875 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/geomagnetic_kp_index", "has_published_results": true, "key": "geomagnetic_kp_index", "label": "geomagnetic_kp_index", "measurement_eligibility": "eligible", "numeric_column_count": 3, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 686, "shared_metadata_bytes": 16243, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 21952, "source": "Hugging Face", "source_order": 62, "source_url": "https://huggingface.co/datasets/juliensimon/geomagnetic-kp-index", "value_cell_count": 2058, "mean_valid_values_per_numerical_sequence": 686.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/global_influenza", "has_published_results": true, "key": "global_influenza", "label": "global_influenza", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 12293, "shared_metadata_bytes": 326747, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 146764, "source": "arXiv", "source_order": 65, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 12293, "mean_valid_values_per_numerical_sequence": 201.75 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/global_price", "has_published_results": true, "key": "global_price", "label": "global_price", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 8520, "shared_metadata_bytes": 250051, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 102016, "source": "arXiv", "source_order": 66, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 8520, "mean_valid_values_per_numerical_sequence": 141.06666666666666 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/gluco_tsfm_benchmark", "has_published_results": true, "key": "gluco_tsfm_benchmark", "label": "gluco_tsfm_benchmark", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2873627, "shared_metadata_bytes": 59084768, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 45978032, "source": "Hugging Face", "source_order": 68, "source_url": "https://huggingface.co/datasets/byluuu/gluco-tsfm-benchmark", "value_cell_count": 2873627, "mean_valid_values_per_numerical_sequence": 2716.093572778828 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 119, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/goes_omni_electron_flux_forecasting", "has_published_results": true, "key": "goes_omni_electron_flux_forecasting", "label": "goes_omni_electron_flux_forecasting", "measurement_eligibility": "eligible", "numeric_column_count": 118, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2487522, "shared_metadata_bytes": 50061697, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 376644928, "source": "Hugging Face", "source_order": 69, "source_url": "https://huggingface.co/datasets/snowsadh/goes-omni-electron-flux-forecasting", "value_cell_count": 60699486, "mean_valid_values_per_numerical_sequence": 362652.4328358209 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/greatplains_multisource_2000_2024", "has_published_results": true, "key": "greatplains_multisource_2000_2024", "label": "greatplains_multisource_2000_2024", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1143, "shared_metadata_bytes": 26004, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 32004, "source": "Hugging Face", "source_order": 70, "source_url": "https://huggingface.co/datasets/TaoDerong/GreatPlains-Multisource-2000-2024", "value_cell_count": 5715, "mean_valid_values_per_numerical_sequence": 1143.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 15, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/hourly-stock-data-2023", "has_published_results": true, "key": "hourly-stock-data-2023", "label": "hourly-stock-data-2023", "measurement_eligibility": "eligible", "numeric_column_count": 14, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 11202, "shared_metadata_bytes": 237758, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1344112, "source": "Hugging Face", "source_order": 72, "source_url": "https://huggingface.co/datasets/mdnh/hourly-stock-data-2023", "value_cell_count": 156828, "mean_valid_values_per_numerical_sequence": 1400.107142857143 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/hourly_electricity_demand_brazil", "has_published_results": true, "key": "hourly_electricity_demand_brazil", "label": "hourly_electricity_demand_brazil", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 185280, "shared_metadata_bytes": 3729588, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2223360, "source": "Hugging Face", "source_order": 73, "source_url": "https://huggingface.co/datasets/SamuelM0422/Hourly-Electricity-Demand-Brazil-Dataset", "value_cell_count": 185280, "mean_valid_values_per_numerical_sequence": 46320.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 7, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/indian_stock_hourly_2017_2021", "has_published_results": true, "key": "indian_stock_hourly_2017_2021", "label": "indian_stock_hourly_2017_2021", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 40445, "shared_metadata_bytes": 817531, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2166336, "source": "Hugging Face", "source_order": 75, "source_url": "https://huggingface.co/datasets/calender/indian-stock-hourly-2017-2021", "value_cell_count": 242670, "mean_valid_values_per_numerical_sequence": 7678.233333333334 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/job_claims", "has_published_results": true, "key": "job_claims", "label": "job_claims", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 392, "shared_metadata_bytes": 11275, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 4704, "source": "arXiv", "source_order": 76, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 392, "mean_valid_values_per_numerical_sequence": 196.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/jolts", "has_published_results": true, "key": "jolts", "label": "jolts", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1782, "shared_metadata_bytes": 43971, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 21384, "source": "arXiv", "source_order": 77, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 1782, "mean_valid_values_per_numerical_sequence": 297.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/kaggle_web_traffic", "has_published_results": false, "key": "kaggle_web_traffic", "label": "kaggle_web_traffic", "measurement_eligibility": "corrected_input_retest_pending", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "replacement_pending", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 33860956, "shared_metadata_bytes": 883125686, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 406331472, "source": "Zenodo", "source_order": 79, "source_url": "https://zenodo.org/record/4656080", "value_cell_count": 33860956, "has_historical_published_measurements": true, "has_published_measurements": false, "current_input_issue": "The old export retained only 33,860,956 of 116,476,879 eligible source rows because of the 1 GB cap (82,615,923 rows lost). The one scientific value is FLOAT target; physical Time is the temporal coordinate and TAG fields (including start_timestamp) are metadata, not value payload.", "mean_valid_values_per_numerical_sequence": 802.939957122078 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/kdd_cup_2018", "has_published_results": true, "key": "kdd_cup_2018", "label": "kdd_cup_2018", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2919402, "shared_metadata_bytes": 59041938, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 58388040, "source": "Zenodo", "source_order": 81, "source_url": "https://zenodo.org/record/4656719", "value_cell_count": 2919402, "mean_valid_values_per_numerical_sequence": 10812.6 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 22, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/knowable", "has_published_results": true, "key": "knowable", "label": "knowable", "measurement_eligibility": "eligible", "numeric_column_count": 21, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 902281, "shared_metadata_bytes": 18164110, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 45043088, "source": "Hugging Face", "source_order": 82, "source_url": "https://huggingface.co/datasets/jwlutz/knowable/blob/23a0fccc86d026a4c47dc5fef7c06f538b4a1aca/README.md", "value_cell_count": 3570906, "mean_valid_values_per_numerical_sequence": 40411.153846153844 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 55, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/kraken-trading-data", "has_published_results": true, "key": "kraken-trading-data", "label": "kraken-trading-data", "measurement_eligibility": "eligible", "numeric_column_count": 54, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 676383, "shared_metadata_bytes": 13660003, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 62974352, "source": "Hugging Face", "source_order": 83, "source_url": "https://huggingface.co/datasets/GotThatData/kraken-trading-data", "value_cell_count": 7197562, "mean_valid_values_per_numerical_sequence": 14805.372427983539 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/kuiper_fleet_data", "has_published_results": true, "key": "kuiper_fleet_data", "label": "kuiper_fleet_data", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 144, "shared_metadata_bytes": 5816, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 6912, "source": "Hugging Face", "source_order": 84, "source_url": "https://huggingface.co/datasets/juliensimon/kuiper-fleet-data/blob/d5ab5cc065731c365b29e6e0596a8f13a2da44ee/README.md", "value_cell_count": 720, "mean_valid_values_per_numerical_sequence": 144.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/london_smart_meters", "has_published_results": true, "key": "london_smart_meters", "label": "london_smart_meters", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 24165773, "shared_metadata_bytes": 490544326, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 289989276, "source": "Zenodo", "source_order": 85, "source_url": "https://zenodo.org/record/4656072", "value_cell_count": 24165773, "mean_valid_values_per_numerical_sequence": 5071.515844700944 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 13, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/m2oe2_timeseries", "has_published_results": true, "key": "m2oe2_timeseries", "label": "m2oe2_timeseries", "measurement_eligibility": "eligible", "numeric_column_count": 12, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 20852953, "shared_metadata_bytes": 420255209, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 251893044, "source": "Hugging Face", "source_order": 86, "source_url": "https://huggingface.co/datasets/MuhaoGuo/M2oE2TimeSeriesData", "value_cell_count": 21404175, "mean_valid_values_per_numerical_sequence": 8541.106425702812 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/metropt_3", "has_published_results": true, "key": "metropt_3", "label": "metropt_3", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 59310, "shared_metadata_bytes": 1194689, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 671352, "source": "Hugging Face", "source_order": 89, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/MetroPT-3/5T/item0.csv", "value_cell_count": 59310, "mean_valid_values_per_numerical_sequence": 8203.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 23, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/multi_model_trading_data", "has_published_results": true, "key": "multi_model_trading_data", "label": "multi_model_trading_data", "measurement_eligibility": "eligible", "numeric_column_count": 22, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7256, "shared_metadata_bytes": 153397, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 694176, "source": "Hugging Face", "source_order": 90, "source_url": "https://huggingface.co/datasets/AdityaaXD/Multi-Model-Trading-Data", "value_cell_count": 79516, "mean_valid_values_per_numerical_sequence": 3614.3636363636365 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 8, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/national_illness", "has_published_results": true, "key": "national_illness", "label": "national_illness", "measurement_eligibility": "eligible", "numeric_column_count": 7, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 966, "shared_metadata_bytes": 22649, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 34776, "source": "Hugging Face", "source_order": 92, "source_url": "https://huggingface.co/datasets/thuml/Time-Series-Library", "value_cell_count": 6762, "mean_valid_values_per_numerical_sequence": 966.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ne_china_wind", "has_published_results": true, "key": "ne_china_wind", "label": "ne_china_wind", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 35056, "shared_metadata_bytes": 707170, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 420672, "source": "Hugging Face", "source_order": 93, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/NE_China_Wind/H/item0.csv", "value_cell_count": 35056, "mean_valid_values_per_numerical_sequence": 8764.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/nifty50_market_regime", "has_published_results": true, "key": "nifty50_market_regime", "label": "nifty50_market_regime", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2235, "shared_metadata_bytes": 47653, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 71520, "source": "Hugging Face", "source_order": 95, "source_url": "https://huggingface.co/datasets/AAdevloper/nifty50-market-regime", "value_cell_count": 11175, "mean_valid_values_per_numerical_sequence": 2235.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/nn5_daily", "has_published_results": true, "key": "nn5_daily", "label": "nn5_daily", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 87801, "shared_metadata_bytes": 1903872, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1756020, "source": "Zenodo", "source_order": 96, "source_url": "https://zenodo.org/record/4656110", "value_cell_count": 87801, "mean_valid_values_per_numerical_sequence": 791.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/oikolab_weather", "has_published_results": true, "key": "oikolab_weather", "label": "oikolab_weather", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 800456, "shared_metadata_bytes": 16104480, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 16009120, "source": "Zenodo", "source_order": 98, "source_url": "https://zenodo.org/record/5184708", "value_cell_count": 800456, "mean_valid_values_per_numerical_sequence": 100057.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/oil_price", "has_published_results": true, "key": "oil_price", "label": "oil_price", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 60420, "shared_metadata_bytes": 1224781, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 712608, "source": "arXiv", "source_order": 99, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 60420, "mean_valid_values_per_numerical_sequence": 4776.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/omie_blockchain_study", "has_published_results": true, "key": "omie_blockchain_study", "label": "omie_blockchain_study", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2367, "shared_metadata_bytes": 51583, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 104148, "source": "Hugging Face", "source_order": 100, "source_url": "https://huggingface.co/datasets/UniversitatdeLleida/omie-blockchain-study/blob/b0498dd9cc3e0fa0334fd54c2517290ad924b55a/README.md", "value_cell_count": 11835, "mean_valid_values_per_numerical_sequence": 1183.5 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/online_retail_2_uci", "has_published_results": true, "key": "online_retail_2_uci", "label": "online_retail_2_uci", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 739, "shared_metadata_bytes": 16940, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 8868, "source": "Hugging Face", "source_order": 101, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/Online_Retail_2_UCI/D/item0.csv", "value_cell_count": 739, "mean_valid_values_per_numerical_sequence": 739.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 13, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/ooni_censorship_historical", "has_published_results": true, "key": "ooni_censorship_historical", "label": "ooni_censorship_historical", "measurement_eligibility": "eligible", "numeric_column_count": 12, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1661061, "shared_metadata_bytes": 34883501, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 105707616, "source": "Hugging Face", "source_order": 102, "source_url": "https://huggingface.co/datasets/emperor-mew/ooni-censorship-historical", "value_cell_count": 11552391, "mean_valid_values_per_numerical_sequence": 1547.540656396517 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/openelectricity_nem", "has_published_results": true, "key": "openelectricity_nem", "label": "openelectricity_nem", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 434880, "shared_metadata_bytes": 8754048, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 5218560, "source": "Hugging Face", "source_order": 103, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/OpenElectricity_NEM/5T/item0.csv", "value_cell_count": 434880, "mean_valid_values_per_numerical_sequence": 43488.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 44, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/orbital_chaos_nasa_ssc", "has_published_results": true, "key": "orbital_chaos_nasa_ssc", "label": "orbital_chaos_nasa_ssc", "measurement_eligibility": "eligible", "numeric_column_count": 43, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 4825802, "shared_metadata_bytes": 97037941, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 372690324, "source": "Hugging Face", "source_order": 104, "source_url": "https://huggingface.co/datasets/datamatters24/orbital-chaos-nasa-ssc/blob/e6348dde60a08b78d6f6661c052b7ba991c70214/README.md", "value_cell_count": 52988423, "mean_valid_values_per_numerical_sequence": 1004331.7441860465 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/pedestrian_counts", "has_published_results": true, "key": "pedestrian_counts", "label": "pedestrian_counts", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 3132346, "shared_metadata_bytes": 63037054, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 62646920, "source": "Zenodo", "source_order": 105, "source_url": "https://zenodo.org/record/4656626", "value_cell_count": 3132346, "mean_valid_values_per_numerical_sequence": 47459.78787878788 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 26, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/phenology_normal_hawaii", "has_published_results": true, "key": "phenology_normal_hawaii", "label": "phenology_normal_hawaii", "measurement_eligibility": "eligible", "numeric_column_count": 25, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 10945, "shared_metadata_bytes": 231376, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1248280, "source": "Hugging Face", "source_order": 106, "source_url": "https://huggingface.co/datasets/imageomics/phenology-normal-hawaii", "value_cell_count": 273625, "mean_valid_values_per_numerical_sequence": 2058.76 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 16, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/polymarket_crypto_5m_15m", "has_published_results": true, "key": "polymarket_crypto_5m_15m", "label": "polymarket_crypto_5m_15m", "measurement_eligibility": "eligible", "numeric_column_count": 15, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 3792347, "shared_metadata_bytes": 76269054, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 44869144, "source": "Hugging Face", "source_order": 107, "source_url": "https://huggingface.co/datasets/bmoney1321/polymarket-crypto-5m-15m/blob/511752d5ebe9380626c90d3eac7d3643c1a0b5e7/README.md", "value_cell_count": 14207576, "mean_valid_values_per_numerical_sequence": 30271.6 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/port_activity", "has_published_results": true, "key": "port_activity", "label": "port_activity", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 481338, "shared_metadata_bytes": 10151869, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 5776056, "source": "arXiv", "source_order": 108, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 481338, "mean_valid_values_per_numerical_sequence": 1215.5 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 11, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/quitobench", "has_published_results": true, "key": "quitobench", "label": "quitobench", "measurement_eligibility": "eligible", "numeric_column_count": 10, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 12502844, "shared_metadata_bytes": 252208851, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 600136512, "source": "Hugging Face", "source_order": 109, "source_url": "https://huggingface.co/datasets/hq-bench/quitobench", "value_cell_count": 62514220, "mean_valid_values_per_numerical_sequence": 9692.127131782945 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 43, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/reg_forecasting_v2", "has_published_results": true, "key": "reg_forecasting_v2", "label": "reg_forecasting_v2", "measurement_eligibility": "eligible", "numeric_column_count": 42, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 103079, "shared_metadata_bytes": 2084292, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 35459176, "source": "Hugging Face", "source_order": 110, "source_url": "https://huggingface.co/datasets/wachawich/REG-Forecasting_v2", "value_cell_count": 4329318, "mean_valid_values_per_numerical_sequence": 51539.5 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/rideshare", "has_published_results": true, "key": "rideshare", "label": "rideshare", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1246464, "shared_metadata_bytes": 28434764, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 24929280, "source": "Zenodo", "source_order": 111, "source_url": "https://zenodo.org/record/5122114", "value_cell_count": 1246464, "mean_valid_values_per_numerical_sequence": 541.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/salesforecastingwomartstore", "has_published_results": true, "key": "salesforecastingwomartstore", "label": "salesforecastingwomartstore", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 210605, "shared_metadata_bytes": 5279306, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 6383120, "source": "Hugging Face", "source_order": 112, "source_url": "https://huggingface.co/datasets/SURESHBEEKHANI/SalesForecastingWOMartStore", "value_cell_count": 587285, "mean_valid_values_per_numerical_sequence": 402.25 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/saugeenday-monash", "has_published_results": true, "key": "saugeenday-monash", "label": "saugeenday-monash", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 23741, "shared_metadata_bytes": 479298, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 474820, "source": "Zenodo", "source_order": 113, "source_url": "https://zenodo.org/record/4656058", "value_cell_count": 23741, "mean_valid_values_per_numerical_sequence": 23741.0 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/scaphandre_cpu_usage", "has_published_results": true, "key": "scaphandre_cpu_usage", "label": "scaphandre_cpu_usage", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 300, "shared_metadata_bytes": 8094, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3600, "source": "Hugging Face", "source_order": 114, "source_url": "https://huggingface.co/datasets/ICOS-AI/scaphandre_cpu_usage", "value_cell_count": 300, "mean_valid_values_per_numerical_sequence": 300.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/sg_carpark", "has_published_results": true, "key": "sg_carpark", "label": "sg_carpark", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 5131230, "shared_metadata_bytes": 103450460, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 61343952, "source": "Hugging Face", "source_order": 115, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/SG_Carpark/15T/item0.csv", "value_cell_count": 5131230, "mean_valid_values_per_numerical_sequence": 14332.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/sg_pm25", "has_published_results": true, "key": "sg_pm25", "label": "sg_pm25", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 193440, "shared_metadata_bytes": 3891000, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2294668, "source": "Hugging Face", "source_order": 116, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/SG_PM25/H/item0.csv", "value_cell_count": 193440, "mean_valid_values_per_numerical_sequence": 37357.4 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/sg_weather", "has_published_results": true, "key": "sg_weather", "label": "sg_weather", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 70872, "shared_metadata_bytes": 1449231, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 836272, "source": "Hugging Face", "source_order": 117, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/SG_Weather/D/S104.csv", "value_cell_count": 70872, "mean_valid_values_per_numerical_sequence": 2805.1666666666665 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/sleep_score_fitbit", "has_published_results": true, "key": "sleep_score_fitbit", "label": "sleep_score_fitbit", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 291, "shared_metadata_bytes": 8776, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 13968, "source": "Hugging Face", "source_order": 118, "source_url": "https://huggingface.co/datasets/aai530-group6/sleep-score-fitbit", "value_cell_count": 1455, "mean_valid_values_per_numerical_sequence": 291.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/solar_10_minutes", "has_published_results": true, "key": "solar_10_minutes", "label": "solar_10_minutes", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7200720, "shared_metadata_bytes": 144922970, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 144014400, "source": "Zenodo", "source_order": 119, "source_url": "https://zenodo.org/record/4656144", "value_cell_count": 7200720, "mean_valid_values_per_numerical_sequence": 52560.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/solar_4_seconds", "has_published_results": true, "key": "solar_4_seconds", "label": "solar_4_seconds", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7397222, "shared_metadata_bytes": 148718165, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 147944440, "source": "Zenodo", "source_order": 120, "source_url": "https://zenodo.org/record/4656027", "value_cell_count": 7397222, "mean_valid_values_per_numerical_sequence": 7397222.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 10, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/solusdt_enhanced_180", "has_published_results": true, "key": "solusdt_enhanced_180", "label": "solusdt_enhanced_180", "measurement_eligibility": "eligible", "numeric_column_count": 9, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 259200, "shared_metadata_bytes": 5213719, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 20736000, "source": "Hugging Face", "source_order": 122, "source_url": "https://huggingface.co/datasets/roadz/solusdt_enhanced_180", "value_cell_count": 2332800, "mean_valid_values_per_numerical_sequence": 259200.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 7, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/spx", "has_published_results": true, "key": "spx", "label": "spx", "measurement_eligibility": "eligible", "numeric_column_count": 6, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 24167, "shared_metadata_bytes": 488224, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1353352, "source": "Hugging Face", "source_order": 123, "source_url": "https://huggingface.co/datasets/misikoff/SPX", "value_cell_count": 145002, "mean_valid_values_per_numerical_sequence": 24167.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 72, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/stock_dataset", "has_published_results": true, "key": "stock_dataset", "label": "stock_dataset", "measurement_eligibility": "eligible", "numeric_column_count": 71, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 620095, "shared_metadata_bytes": 13044609, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 357174720, "source": "Hugging Face", "source_order": 124, "source_url": "https://huggingface.co/datasets/Blaze2oi/stock-dataset/blob/8f71473cc1f26ea3c025a6eb157f3d07483cb776/README.md", "value_cell_count": 44026745, "mean_valid_values_per_numerical_sequence": 1232.79324055666 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/substorm_onsets", "has_published_results": true, "key": "substorm_onsets", "label": "substorm_onsets", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 256682, "shared_metadata_bytes": 5166279, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 10267280, "source": "Hugging Face", "source_order": 125, "source_url": "https://huggingface.co/datasets/juliensimon/substorm-onsets", "value_cell_count": 1026728, "mean_valid_values_per_numerical_sequence": 51336.4 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/sunspot", "has_published_results": true, "key": "sunspot", "label": "sunspot", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 73924, "shared_metadata_bytes": 1487844, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1478480, "source": "Zenodo", "source_order": 126, "source_url": "https://zenodo.org/record/4654773", "value_cell_count": 73924, "mean_valid_values_per_numerical_sequence": 73924.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 8, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/telangana_weather", "has_published_results": true, "key": "telangana_weather", "label": "telangana_weather", "measurement_eligibility": "eligible", "numeric_column_count": 7, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 445212, "shared_metadata_bytes": 9712306, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 16027632, "source": "Hugging Face", "source_order": 127, "source_url": "https://huggingface.co/datasets/ron-the-code/Telangana_time_series_2023-2025", "value_cell_count": 3116484, "mean_valid_values_per_numerical_sequence": 727.4705882352941 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/temperature_rain", "has_published_results": true, "key": "temperature_rain", "label": "temperature_rain", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 23252166, "shared_metadata_bytes": 512978913, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 279025992, "source": "Zenodo", "source_order": 128, "source_url": "https://zenodo.org/record/5129073", "value_cell_count": 23252166, "mean_valid_values_per_numerical_sequence": 724.9989398852582 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/timeseries-1m-QQQ-10y", "has_published_results": true, "key": "timeseries-1m-QQQ-10y", "label": "timeseries-1m-QQQ-10y", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 1802050, "shared_metadata_bytes": 36232729, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 86498400, "source": "Hugging Face", "source_order": 130, "source_url": "https://huggingface.co/datasets/Maxim37/timeseries-1m-QQQ-10y", "value_cell_count": 9010250, "mean_valid_values_per_numerical_sequence": 1802050.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/timeseries_1mn_sp500", "has_published_results": true, "key": "timeseries_1mn_sp500", "label": "timeseries_1mn_sp500", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 392924, "shared_metadata_bytes": 8490099, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 17469592, "source": "Hugging Face", "source_order": 132, "source_url": "https://huggingface.co/datasets/jwigginton/timeseries-1mn-sp500", "value_cell_count": 1964620, "mean_valid_values_per_numerical_sequence": 712.0377733598409 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/timeseries_1mn_stocks", "has_published_results": true, "key": "timeseries_1mn_stocks", "label": "timeseries_1mn_stocks", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 377743, "shared_metadata_bytes": 9500852, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 18129272, "source": "Hugging Face", "source_order": 133, "source_url": "https://huggingface.co/datasets/chuyin0321/timeseries-1mn-stocks", "value_cell_count": 1888715, "mean_valid_values_per_numerical_sequence": 251.7888 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/tourism_monthly", "has_published_results": true, "key": "tourism_monthly", "label": "tourism_monthly", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 109280, "shared_metadata_bytes": 2688757, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2185600, "source": "Zenodo", "source_order": 135, "source_url": "https://zenodo.org/record/4656096", "value_cell_count": 109280, "mean_valid_values_per_numerical_sequence": 298.57923497267757 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/tourism_monthly-zaai-ai", "has_published_results": true, "key": "tourism_monthly-zaai-ai", "label": "tourism_monthly-zaai-ai", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 69114, "shared_metadata_bytes": 1815576, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3317472, "source": "Hugging Face", "source_order": 136, "source_url": "https://huggingface.co/datasets/zaai-ai/time_series_datasets", "value_cell_count": 345570, "mean_valid_values_per_numerical_sequence": 227.34868421052633 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 5, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/tourism_residuals", "has_published_results": true, "key": "tourism_residuals", "label": "tourism_residuals", "measurement_eligibility": "eligible", "numeric_column_count": 4, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 51680, "shared_metadata_bytes": 1462951, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 2067200, "source": "Hugging Face", "source_order": 138, "source_url": "https://huggingface.co/datasets/zaai-ai/time_series_dataset_residuals", "value_cell_count": 206720, "mean_valid_values_per_numerical_sequence": 170.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 863, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/traffic", "has_published_results": true, "key": "traffic", "label": "traffic", "measurement_eligibility": "eligible", "numeric_column_count": 862, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 17544, "shared_metadata_bytes": 524979, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 60632064, "source": "Hugging Face", "source_order": 140, "source_url": "https://huggingface.co/datasets/thuml/Time-Series-Library", "value_cell_count": 15122928, "mean_valid_values_per_numerical_sequence": 17544.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/traffic_hourly", "has_published_results": true, "key": "traffic_hourly", "label": "traffic_hourly", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 15122928, "shared_metadata_bytes": 304543854, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 302458560, "source": "Zenodo", "source_order": 141, "source_url": "https://zenodo.org/record/4656132", "value_cell_count": 15122928, "mean_valid_values_per_numerical_sequence": 17544.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/trxusdt_spot_1m_05_2021_to_03_2026", "has_published_results": true, "key": "trxusdt_spot_1m_05_2021_to_03_2026", "label": "trxusdt_spot_1m_05_2021_to_03_2026", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2541210, "shared_metadata_bytes": 51111337, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 71153880, "source": "Hugging Face", "source_order": 145, "source_url": "https://huggingface.co/datasets/Torch-Trade/trxusdt_spot_1m_05_2021_to_03_2026/blob/e23576e97b192e7866ea516485df57ab8ecb9c36/README.md", "value_cell_count": 12706050, "mean_valid_values_per_numerical_sequence": 2541210.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 34, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/uk_electricity_generation_mix_2019_2026", "has_published_results": true, "key": "uk_electricity_generation_mix_2019_2026", "label": "uk_electricity_generation_mix_2019_2026", "measurement_eligibility": "eligible", "numeric_column_count": 33, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 126476, "shared_metadata_bytes": 2552381, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 34401472, "source": "neso.energy", "source_order": 146, "source_url": "https://www.neso.energy/data-portal/historic-generation-mix/historic_gb_generation_mix", "value_cell_count": 4173708, "mean_valid_values_per_numerical_sequence": 126476.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/uncertainty_1m", "has_published_results": true, "key": "uncertainty_1m", "label": "uncertainty_1m", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2340, "shared_metadata_bytes": 51547, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 28080, "source": "Hugging Face", "source_order": 147, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/Uncertainty_1M/M/item0.csv", "value_cell_count": 2340, "mean_valid_values_per_numerical_sequence": 780.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/us_births-monash", "has_published_results": true, "key": "us_births-monash", "label": "us_births-monash", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7305, "shared_metadata_bytes": 148496, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 146100, "source": "Zenodo", "source_order": 148, "source_url": "https://zenodo.org/record/4656049", "value_cell_count": 7305, "mean_valid_values_per_numerical_sequence": 7305.0 }, { "category": "health_society", "category_label": "Health & Society", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/us_labor", "has_published_results": true, "key": "us_labor", "label": "us_labor", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 5320, "shared_metadata_bytes": 125223, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 63840, "source": "Hugging Face", "source_order": 149, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/US_Labor/M/item0.csv", "value_cell_count": 5320, "mean_valid_values_per_numerical_sequence": 380.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/us_term_structure", "has_published_results": true, "key": "us_term_structure", "label": "us_term_structure", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 373040, "shared_metadata_bytes": 7515322, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 4412000, "source": "Hugging Face", "source_order": 151, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/US_Term_Structure/B/item0.csv", "value_cell_count": 373040, "mean_valid_values_per_numerical_sequence": 8923.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/vehicle_sales", "has_published_results": true, "key": "vehicle_sales", "label": "vehicle_sales", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 5960, "shared_metadata_bytes": 133150, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 71520, "source": "Hugging Face", "source_order": 152, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/Vehicle_Sales/M/item0.csv", "value_cell_count": 5960, "mean_valid_values_per_numerical_sequence": 596.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/vehicle_supply", "has_published_results": true, "key": "vehicle_supply", "label": "vehicle_supply", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2346, "shared_metadata_bytes": 55631, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 28152, "source": "Hugging Face", "source_order": 153, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/Vehicle_Supply/M/item0.csv", "value_cell_count": 2346, "mean_valid_values_per_numerical_sequence": 391.0 }, { "category": "transport_mobility", "category_label": "Transport & Mobility", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/vehicle_trips", "has_published_results": true, "key": "vehicle_trips", "label": "vehicle_trips", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 42382, "shared_metadata_bytes": 1338579, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 847640, "source": "Zenodo", "source_order": 154, "source_url": "https://zenodo.org/record/5122535", "value_cell_count": 42382, "mean_valid_values_per_numerical_sequence": 128.8206686930091 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/water_quality_darwin", "has_published_results": true, "key": "water_quality_darwin", "label": "water_quality_darwin", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 639636, "shared_metadata_bytes": 12888766, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 7675560, "source": "arXiv", "source_order": 155, "source_url": "https://arxiv.org/html/2602.12147v4", "value_cell_count": 639636, "mean_valid_values_per_numerical_sequence": 15229.0 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 13, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/weather_data_bavaria", "has_published_results": true, "key": "weather_data_bavaria", "label": "weather_data_bavaria", "measurement_eligibility": "eligible", "numeric_column_count": 12, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 8867345, "shared_metadata_bytes": 181076031, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 594681400, "source": "Hugging Face", "source_order": 157, "source_url": "https://huggingface.co/datasets/Kamilatr/weather_data_bavaria", "value_cell_count": 106408140, "mean_valid_values_per_numerical_sequence": 2352.926610120759 }, { "category": "environment_space", "category_label": "Environment & Space", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 488, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/wids2023_competition_weather_forecasting", "has_published_results": true, "key": "wids2023_competition_weather_forecasting", "label": "wids2023_competition_weather_forecasting", "measurement_eligibility": "eligible", "numeric_column_count": 487, "origin_class": "derived_from_real", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 407088, "shared_metadata_bytes": 9682692, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 796827472, "source": "Hugging Face", "source_order": 158, "source_url": "https://huggingface.co/datasets/mirai-ml/wids2023_competition_weather_forecasting", "value_cell_count": 99298118, "mean_valid_values_per_numerical_sequence": 396.28131416837783 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 3, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/wind_4_seconds", "has_published_results": true, "key": "wind_4_seconds", "label": "wind_4_seconds", "measurement_eligibility": "eligible", "numeric_column_count": 2, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 7397147, "shared_metadata_bytes": 148713698, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 147942940, "source": "Zenodo", "source_order": 159, "source_url": "https://zenodo.org/record/4656032", "value_cell_count": 7397147, "mean_valid_values_per_numerical_sequence": 7397147.0 }, { "category": "energy_industry", "category_label": "Energy & Industry", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/wind_farms_minutely", "has_published_results": true, "key": "wind_farms_minutely", "label": "wind_farms_minutely", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 30724989, "shared_metadata_bytes": 617899346, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 368699868, "source": "Zenodo", "source_order": 160, "source_url": "https://zenodo.org/record/4654909", "value_cell_count": 30724989, "mean_valid_values_per_numerical_sequence": 90634.18584070797 }, { "category": "web_computing", "category_label": "Web & Computing", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 14, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/wordle_mcm_dataset", "has_published_results": true, "key": "wordle_mcm_dataset", "label": "wordle_mcm_dataset", "measurement_eligibility": "eligible", "numeric_column_count": 13, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 359, "shared_metadata_bytes": 11768, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 40208, "source": "Hugging Face", "source_order": 161, "source_url": "https://huggingface.co/datasets/qwqqwqqwq121/Wordle-MCM-Dataset", "value_cell_count": 4667, "mean_valid_values_per_numerical_sequence": 359.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 2, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/wui_global", "has_published_results": true, "key": "wui_global", "label": "wui_global", "measurement_eligibility": "eligible", "numeric_column_count": 1, "origin_class": "derived_from_real", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 4410, "shared_metadata_bytes": 108314, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 52580, "source": "Hugging Face", "source_order": 162, "source_url": "https://huggingface.co/datasets/Real-TSF/TIME-ProcessedCSV/blob/683bb21b470f5a26586e1ab2295f0a2a1529ef0f/WUI_Global/Q/item0.csv", "value_cell_count": 4410, "mean_valid_values_per_numerical_sequence": 288.3333333333333 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/xauusd", "has_published_results": true, "key": "xauusd", "label": "xauusd", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 4207608, "shared_metadata_bytes": 84577814, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 134643456, "source": "Hugging Face", "source_order": 163, "source_url": "https://huggingface.co/datasets/Pcitycrypto/xauusd", "value_cell_count": 21038040, "mean_valid_values_per_numerical_sequence": 4207608.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/xauusd_1m", "has_published_results": true, "key": "xauusd_1m", "label": "xauusd_1m", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "medium", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "incomplete", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 4207608, "shared_metadata_bytes": 84582897, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 201965184, "source": "Hugging Face", "source_order": 164, "source_url": "https://huggingface.co/datasets/ta4500/xauusd/blob/3ede3ada2a51ee5408abdcba163d8d0f3d1c2949/README.md", "value_cell_count": 21038040, "mean_valid_values_per_numerical_sequence": 4207608.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/xinyi_public_gym", "has_published_results": true, "key": "xinyi_public_gym", "label": "xinyi_public_gym", "measurement_eligibility": "eligible", "numeric_column_count": 3, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 185311, "shared_metadata_bytes": 3728781, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 3681080, "source": "Hugging Face", "source_order": 165, "source_url": "https://huggingface.co/datasets/czl/xinyi_public_gym", "value_cell_count": 555933, "mean_valid_values_per_numerical_sequence": 91608.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 6, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/xrpusdt_spot_1m_05_2021_to_03_2026", "has_published_results": true, "key": "xrpusdt_spot_1m_05_2021_to_03_2026", "label": "xrpusdt_spot_1m_05_2021_to_03_2026", "measurement_eligibility": "eligible", "numeric_column_count": 5, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 2541600, "shared_metadata_bytes": 51119139, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 71164800, "source": "Hugging Face", "source_order": 166, "source_url": "https://huggingface.co/datasets/Torch-Trade/xrpusdt_spot_1m_05_2021_to_03_2026/blob/f6e36ee337c0c61f1b454ebe6baba4ee6900c242/README.md", "value_cell_count": 12708000, "mean_valid_values_per_numerical_sequence": 2541600.0 }, { "category": "finance_commerce", "category_label": "Finance & Commerce", "cohort": "thulab", "cohort_label": "THULab dataset collection", "column_count": 4, "controlled_test_data": false, "dataset_url": "https://huggingface.co/datasets/THULab/yongchun_public_gym", "has_published_results": true, "key": "yongchun_public_gym", "label": "yongchun_public_gym", "measurement_eligibility": "eligible", "numeric_column_count": 3, "origin_class": "real_measured", "origin_confidence": "high", "preparation_status": "ready", "production_context": "unspecified_or_production_observational", "provenance_status": "source_supported", "published_result_row_count": null, "published_result_row_count_matches_catalog": null, "published_result_scope": "published_measurements", "row_count": 70710, "shared_metadata_bytes": 1424084, "size_basis": "native_numeric_bytes_excluding_validity_and_metadata", "size_bytes": 1409436, "source": "Hugging Face", "source_order": 167, "source_url": "https://huggingface.co/datasets/czl/yongchun_public_gym", "value_cell_count": 212130, "mean_valid_values_per_numerical_sequence": 70313.0 } ], "excluded": [ { "cohort": "legacy", "decision": "exclude_unresolved_category", "key": "Arade", "origin_class": "real_measured", "reason": "The upstream benchmark identifies a real Tableau workbook, but its fixed schema exposes only F1-F9 and WNET; no domain can be assigned without guessing.", "source_url": "https://raw.githubusercontent.com/cwida/public_bi_benchmark/cf9909083bf9ed185cd7f5121a2881e1fea0e7a9/benchmark/Arade/tables/Arade_1.table.sql" }, { "cohort": "thulab", "decision": "exclude_synthetic", "key": "supply_chain_customer", "origin_class": "simulated_synthetic", "reason": "TIME v4 explicitly describes five years of simulated delivery records; both customer and location tables are aggregations of that simulated transaction source.", "source_url": "https://arxiv.org/html/2602.12147v4" }, { "cohort": "thulab", "decision": "exclude_synthetic", "key": "supply_chain_location", "origin_class": "simulated_synthetic", "reason": "TIME v4 explicitly describes five years of simulated delivery records; both customer and location tables are aggregations of that simulated transaction source.", "source_url": "https://arxiv.org/html/2602.12147v4" }, { "key": "jovian_lightning", "reason": "Outside user-authorized final160 scope; historical data preserved." }, { "key": "macroecon", "reason": "Outside user-authorized final160 scope; historical data preserved." }, { "key": "nasa_maven_kp_insitu", "reason": "Outside user-authorized final160 scope; historical data preserved." }, { "key": "weather_data_NC", "reason": "Outside user-authorized final160 scope; historical data preserved." }, { "key": "medium_posts", "reason": "No admitted scientific numeric payload; timestamp coordinates are excluded by the source role contract." }, { "key": "africa_senegal_mauritania_crops_spi", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "car_parts", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "dmi-aarhus-weather-data", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "freshretailnet_50k", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "github_top_projects", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "globalstar_fleet_data", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "hospital-monash", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "housing_inventory", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "kaggle_web_traffic_weekly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "magseven_ml_ready_high_frequency_anomaly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "niederschlag_station_4091_bavaria_germany", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "nn5_weekly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "solar_weekly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "timeseries-finance-ETF", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "timeseries_finance_etf_missing", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "tourism_quarterly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "tourism_yearly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "traffic_weekly", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "traqq_weekly_activity", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "trending_stocks_yahoo_finance", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "us_stock_financial_ratios", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." }, { "key": "zillow_viewer", "reason": "User-selected uniform rule: mean valid values per numerical sequence <128. Historical evidence preserved." } ], "schema_version": 1, "scope_id": "min128_20261013_v1", "source": { "field_boundaries": { "column_count": "Prepared-scope source_inventory_column_count.", "numeric_column_count": "Prepared-scope measured_column_count, including the numeric time axis when measured.", "published_results": "Existing Space snapshot keyed by dataset identity; it is not the pending 169-dataset Native86 run.", "row_count": "Prepared-scope source_row_count.", "size_bytes": "Native numeric bytes only; validity buffers and metadata are excluded." }, "files": [ { "path": "analysis_outputs/realdata_scope_revision_20261008/DATASET_CLASSIFICATION.csv", "sha256": "df80ef61ed6d71034dd50af5de5d06876be4e06c86499b5aae660b24404525dd" }, { "path": "analysis_outputs/realdata_scope_revision_20261008/feeds/dataset_inventory.csv", "sha256": "f4bfcfaab2ef19ec143008fdd5b1a277245b23a1038132af048a0183c03a6efa" }, { "path": "analysis_outputs/realdata_scope_revision_20261008/feeds/source_column_inventory.csv", "sha256": "f94ed9a9dfd95a74f5c48986d650f30a8f867a21e1a18ef02be6610206a21453" }, { "path": "analysis_outputs/realdata_scope_revision_20261008/scenario_provenance.json", "sha256": "c79e7a03623ac41b1e117440c10858f8590869577e6b7684babb455c86c019ec" }, { "path": "analysis_outputs/realdata_scope_revision_20261008/SCOPE_PREPARATION_RECEIPT.json", "sha256": "316e831c88f9e2236aca2f7a2c762e8b7e5f20935242d8935612d16983b33f58" }, { "path": "analysis_outputs/realdata_scope_revision_20261008/EXCLUDED_DATASETS.json", "sha256": "643537984febf5d841e177bbe2cf29113cb6645091011954b605043a5aaf7238" }, { "path": "deploy/huggingface-compressionbenchmark/data.json", "sha256": "47ddcf459b1eedd8b1dcf89d07ee544e10b527e6da24c64f81de18628b324454" } ], "paper_scope_sha256": "0fabc01f25d62ddb49585b3208103543b16c6e50340195360a0516411fa148b4", "scope_formula": "18+151=169", "source_scope_sha256": "7ec5714939750c0551371d52e593685e3c4226681a4283af0a4d5b8abea64cfd", "final_scope_sha256": "b56f9bd610e0bf63ab50d719ce70cf92ddc1b79e6b30fd2c6e2f707944b2ba72", "sequence_length_audit_sha256": "9c340b8f314984881230f0bf3122f45fde64b885ce3e26baf1ec3df1f2540df4" }, "summary": { "catalog_only_dataset_count": 2, "categories": [ { "count": 29, "key": "environment_space", "label": "Environment & Space" }, { "count": 13, "key": "health_society", "label": "Health & Society" }, { "count": 11, "key": "web_computing", "label": "Web & Computing" }, { "count": 14, "key": "transport_mobility", "label": "Transport & Mobility" }, { "count": 47, "key": "finance_commerce", "label": "Finance & Commerce" }, { "count": 23, "key": "energy_industry", "label": "Energy & Industry" } ], "dataset_count": 137, "empty_dataset_count": 0, "legacy_count": 17, "measurement_note": "Test scope: 137 dataset identities after the uniform mean numerical-sequence length >=128 filter. 2 incomplete historical input versions are excluded pending corrected-input results; 135 currently contribute numeric Overall results.", "origin_classes": { "real_measured": 76, "derived_from_real": 61 }, "provenance_statuses": { "source_supported": 125, "incomplete": 12 }, "published_measurement_dataset_count": 135, "published_result_dataset_count": 135, "thulab_count": 120 } }