diff --git "a/sequence-length-audit.json" "b/sequence-length-audit.json" new file mode 100644--- /dev/null +++ "b/sequence-length-audit.json" @@ -0,0 +1,5919 @@ +{ + "dataset_count": 160, + "datasets": [ + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 9357 is at least 128", + "dataset_id": "Air-Quality", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 1, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 9357.0, + "nonempty_numeric_sequence_count": 13, + "numeric_catalog_record_count": 13, + "numeric_sequence_count_including_empty": 13, + "role_record_counts": { + "value": 13 + }, + "role_valid_counts": { + "value": 121641 + }, + "source_bindings": { + "block_catalog_bytes": 35840, + "block_catalog_path": "/data/root/web_compression/datasets164/Air-Quality/typed/full/blocks.jsonl", + "block_catalog_sha256": "a183f8edf62b8e0e3882b86b58646e57faf2ffe1bcee49756d9262b76d14a1b1", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Air-Quality/typed/dataset_manifest.json", + "typed_manifest_sha256": "812a7fe4878912c353e6b71e08f01d9af9cacc2996fdd82c6e5f22037e21f608" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 121641 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 14057567 is at least 128", + "dataset_id": "Bar-Crawl", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 1406, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 14057567.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 4218, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 4218 + }, + "role_valid_counts": { + "value": 42172701 + }, + "source_bindings": { + "block_catalog_bytes": 14336508, + "block_catalog_path": "/data/root/web_compression/datasets164/Bar-Crawl/typed/full/blocks.jsonl", + "block_catalog_sha256": "0a5d798a728b5615cf6ab26c59ce89052f21f6341aa0512953462dc20fd1b6bc", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Bar-Crawl/typed/dataset_manifest.json", + "typed_manifest_sha256": "7e54cf34c831e859a382d84d14d999b3e349b4efe0eb38b81b50d72f575b225e" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 42172701 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 89867 is at least 128", + "dataset_id": "Bird-migration", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 9, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 89867.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 54, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 54 + }, + "role_valid_counts": { + "value": 539202 + }, + "source_bindings": { + "block_catalog_bytes": 168278, + "block_catalog_path": "/data/root/web_compression/datasets164/Bird-migration/typed/full/blocks.jsonl", + "block_catalog_sha256": "70463bbc617f1d729d079554179ce50f74ddaf64b8d359980385adabd76ff101", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Bird-migration/typed/dataset_manifest.json", + "typed_manifest_sha256": "ee88a5f58418513d41208aeb7a52a933a979552a01e7893f8c4292014e07c30b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 539202 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 9411727 is at least 128", + "dataset_id": "Comments", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 942, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 9411727.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 2826, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 2826 + }, + "role_valid_counts": { + "value": 28235181 + }, + "source_bindings": { + "block_catalog_bytes": 9605438, + "block_catalog_path": "/data/root/web_compression/datasets164/Comments/typed/full/blocks.jsonl", + "block_catalog_sha256": "568d62f7e5f77b1bc54124096d463761d91f46e92f24a97d21cfd4151d133a45", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Comments/typed/dataset_manifest.json", + "typed_manifest_sha256": "1f749942cadc63f3e7f30649ee8fd3da23b7fe0b74d2b592bd3d6930a88b7865" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 28235181 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 43550 is at least 128", + "dataset_id": "ETDataset-ett", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 43550.0, + "nonempty_numeric_sequence_count": 28, + "numeric_catalog_record_count": 126, + "numeric_sequence_count_including_empty": 28, + "role_record_counts": { + "value": 126 + }, + "role_valid_counts": { + "value": 1219400 + }, + "source_bindings": { + "block_catalog_bytes": 272991, + "block_catalog_path": "/data/root/web_compression/datasets164/ETDataset-ett/typed/full/blocks.jsonl", + "block_catalog_sha256": "65ead5c4b3411d59d1b2f05e2375e01cd78e06c6a590e0dbe359f00f94539d05", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ETDataset-ett/typed/dataset_manifest.json", + "typed_manifest_sha256": "f4c7d88db6161ce8a98f8af615e90d33bff4d5fc9009c808777cedf3cbd5bd5a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1219400 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 4323468.14286 is at least 128", + "dataset_id": "IGlocations2", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 433, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 4323468.142857143, + "nonempty_numeric_sequence_count": 7, + "numeric_catalog_record_count": 3031, + "numeric_sequence_count_including_empty": 7, + "role_record_counts": { + "value": 3031 + }, + "role_valid_counts": { + "value": 30264277 + }, + "source_bindings": { + "block_catalog_bytes": 9010504, + "block_catalog_path": "/data/root/web_compression/datasets164/IGlocations2/typed/full/blocks.jsonl", + "block_catalog_sha256": "395fbb91de76ce1e523554f585cbb38050c57073dfe3aff007f41ebbe0ca1ae1", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/IGlocations2/typed/dataset_manifest.json", + "typed_manifest_sha256": "7e62a734d89ab13b774b9dfa102c7b849886d21933f3eacf952c8d7a685c59d5" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 30264277 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 6850 is at least 128", + "dataset_id": "METR-LA", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 6850.0, + "nonempty_numeric_sequence_count": 6831, + "numeric_catalog_record_count": 6831, + "numeric_sequence_count_including_empty": 6831, + "role_record_counts": { + "value": 6831 + }, + "role_valid_counts": { + "value": 46792350 + }, + "source_bindings": { + "block_catalog_bytes": 14691777, + "block_catalog_path": "/data/root/web_compression/datasets164/METR-LA/typed/full/blocks.jsonl", + "block_catalog_sha256": "d60529b7a023d63d8ef47745827567fe8509c0cdc056b27a3df8d83d31e152ea", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/METR-LA/typed/dataset_manifest.json", + "typed_manifest_sha256": "a4a68d552b1dc3e4f850cae39e9fa927a946afb5954b7d5b4794a6669e6db9b3" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 46792350 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 48204 is at least 128", + "dataset_id": "Metro-Traffic", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 5, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 48204.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 25, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 25 + }, + "role_valid_counts": { + "value": 241020 + }, + "source_bindings": { + "block_catalog_bytes": 77840, + "block_catalog_path": "/data/root/web_compression/datasets164/Metro-Traffic/typed/full/blocks.jsonl", + "block_catalog_sha256": "25d5a0f1ecf4c29c7657cfedb616f581d4d8e3dd40a49386960632a083c496fa", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Metro-Traffic/typed/dataset_manifest.json", + "typed_manifest_sha256": "9dbf08bd2fca30de907c3695facf99cadb245cb86db21b3b621469790936dc91" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 241020 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 47248845 is at least 128", + "dataset_id": "NYC_Yellow_Taxi_Trip", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 4725, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 47248845.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 4725, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 4725 + }, + "role_valid_counts": { + "value": 47248845 + }, + "source_bindings": { + "block_catalog_bytes": 25664658, + "block_catalog_path": "/data/root/web_compression/datasets164/NYC_Yellow_Taxi_Trip/typed/full/blocks.jsonl", + "block_catalog_sha256": "3f72333dd1862a813f58b2f881f3fe4d2114ba0690c778dce996dd231ea014f8", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/NYC_Yellow_Taxi_Trip/typed/dataset_manifest.json", + "typed_manifest_sha256": "43649f09bd551b9c94b2af8aabbdfea23364a6eebfc9523ca3b2da095f0d11f3" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 47248845 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 10419 is at least 128", + "dataset_id": "PEMS-BAY", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 10419.0, + "nonempty_numeric_sequence_count": 2925, + "numeric_catalog_record_count": 5850, + "numeric_sequence_count_including_empty": 2925, + "role_record_counts": { + "value": 5850 + }, + "role_valid_counts": { + "value": 30475575 + }, + "source_bindings": { + "block_catalog_bytes": 12633605, + "block_catalog_path": "/data/root/web_compression/datasets164/PEMS-BAY/typed/full/blocks.jsonl", + "block_catalog_sha256": "517f459db93b6464b0a714fb87097758232ef25551fa24afa575a10af105a965", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/PEMS-BAY/typed/dataset_manifest.json", + "typed_manifest_sha256": "b5f87bea78259a1e62813af2a0d81abed4f09756c917460da0738ecb8a05199a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 30475575 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 19531359 is at least 128", + "dataset_id": "RealEstate1", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 1954, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 19531359.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 9770, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 9770 + }, + "role_valid_counts": { + "value": 97656795 + }, + "source_bindings": { + "block_catalog_bytes": 30456190, + "block_catalog_path": "/data/root/web_compression/datasets164/RealEstate1/typed/full/blocks.jsonl", + "block_catalog_sha256": "3b8fab4ef0632f40a0a8b158787b4d4f2c1303a26538b98f3ff3160cbad72b1f", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/RealEstate1/typed/dataset_manifest.json", + "typed_manifest_sha256": "35aae65d10a65602319a56ec78c2fcfb6f8355b6ce310c89de624481591d9896" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 97656795 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 9459564.5 is at least 128", + "dataset_id": "RealEstate2", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 949, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 9459564.5, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 3796, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 3796 + }, + "role_valid_counts": { + "value": 37838258 + }, + "source_bindings": { + "block_catalog_bytes": 12312534, + "block_catalog_path": "/data/root/web_compression/datasets164/RealEstate2/typed/full/blocks.jsonl", + "block_catalog_sha256": "fdbd987833615df579f43814d2dfe28825c0802d1aa62bcd2c2f66eb1d8e904b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/RealEstate2/typed/dataset_manifest.json", + "typed_manifest_sha256": "7ff257d1b471722e624e0b81842c1249b7f03286154ebd9fd535b4c20eb8c332" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 37838258 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2208926.4 is at least 128", + "dataset_id": "Romance", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 318, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2208926.4, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 1590, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 1590 + }, + "role_valid_counts": { + "value": 11044632 + }, + "source_bindings": { + "block_catalog_bytes": 4868780, + "block_catalog_path": "/data/root/web_compression/datasets164/Romance/typed/full/blocks.jsonl", + "block_catalog_sha256": "a4f37aafb6bb7c7f9700d980f83b758dfad47f993b73b81419769838120c0bfa", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Romance/typed/dataset_manifest.json", + "typed_manifest_sha256": "116aec2976f649923a3f44ede27be08cbdd4f8932120237302db1f7a37192e7b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11044632 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 934.288981289 is at least 128", + "dataset_id": "SpatialEpiBench", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 934.2889812889813, + "nonempty_numeric_sequence_count": 481, + "numeric_catalog_record_count": 481, + "numeric_sequence_count_including_empty": 481, + "role_record_counts": { + "value": 481 + }, + "role_valid_counts": { + "value": 449393 + }, + "source_bindings": { + "block_catalog_bytes": 1043963, + "block_catalog_path": "/data/root/web_compression/datasets164/SpatialEpiBench/typed/full/blocks.jsonl", + "block_catalog_sha256": "8686843b3189cdb7ec29924eb3bb9b3fc1859a2021e6d6d50a155c9425efb13d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/SpatialEpiBench/typed/dataset_manifest.json", + "typed_manifest_sha256": "4d072159f7a4fdddf077ee68262bc8af9c457babdf4cb53aa1b5dd1c0d1f9417" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 449393 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2907282.44444 is at least 128", + "dataset_id": "Telco", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 292, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2907282.4444444445, + "nonempty_numeric_sequence_count": 45, + "numeric_catalog_record_count": 13140, + "numeric_sequence_count_including_empty": 45, + "role_record_counts": { + "value": 13140 + }, + "role_valid_counts": { + "value": 130827710 + }, + "source_bindings": { + "block_catalog_bytes": 34106536, + "block_catalog_path": "/data/root/web_compression/datasets164/Telco/typed/full/blocks.jsonl", + "block_catalog_sha256": "624a4508cdb0d1e2049288c52a1a2f5309bc9e6c88625a1911ac2956e7d84afe", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Telco/typed/dataset_manifest.json", + "typed_manifest_sha256": "94342ed42aabff9fc19b02071f0a3e2ca78f856a0cc4c1ac42ab4ecbd6305b0c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 130827710 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 30979075 is at least 128", + "dataset_id": "TrainsUK2", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 6226, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 30979075.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 6226, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "value": 6226 + }, + "role_valid_counts": { + "value": 61958150 + }, + "source_bindings": { + "block_catalog_bytes": 32145816, + "block_catalog_path": "/data/root/web_compression/datasets164/TrainsUK2/typed/full/blocks.jsonl", + "block_catalog_sha256": "3d2839d8a3d48755ca64e59050da8b8e4b59b9d26d83ceb0fe17beb69f689770", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/TrainsUK2/typed/dataset_manifest.json", + "typed_manifest_sha256": "8893639a6741f96f4a94c3d2db889afedeb5b8bd23d0a75e045938880b9558c2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 61958150 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7465713.57143 is at least 128", + "dataset_id": "Uberlandia", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 3024, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7465713.571428572, + "nonempty_numeric_sequence_count": 14, + "numeric_catalog_record_count": 10584, + "numeric_sequence_count_including_empty": 14, + "role_record_counts": { + "value": 10584 + }, + "role_valid_counts": { + "value": 104519990 + }, + "source_bindings": { + "block_catalog_bytes": 35194556, + "block_catalog_path": "/data/root/web_compression/datasets164/Uberlandia/typed/full/blocks.jsonl", + "block_catalog_sha256": "12dca05fb8c78582b1e4cf24aa74c9813c45a6ed539b3dae9ebf6212ec063894", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Uberlandia/typed/dataset_manifest.json", + "typed_manifest_sha256": "749535fa1e165821f7d7683dd70b2e595a93e9db14e502a9df26b314d7082b67" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 104519990 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 555789.893617 is at least 128", + "dataset_id": "Wins", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 168, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 555789.8936170213, + "nonempty_numeric_sequence_count": 235, + "numeric_catalog_record_count": 13160, + "numeric_sequence_count_including_empty": 235, + "role_record_counts": { + "value": 13160 + }, + "role_valid_counts": { + "value": 130610625 + }, + "source_bindings": { + "block_catalog_bytes": 33688243, + "block_catalog_path": "/data/root/web_compression/datasets164/Wins/typed/full/blocks.jsonl", + "block_catalog_sha256": "63740242376ba889d091ff04466ce3680b263ef5839cc9ca2b1c66bb46e71ce8", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/Wins/typed/dataset_manifest.json", + "typed_manifest_sha256": "5185a42b96be5af56f2030a453e8ac23ae011012b887ea4fb98bfb1ce25c51fa" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 130610625 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 5669512.875 is at least 128", + "dataset_id": "YaleLanguages", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 577, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 5669512.875, + "nonempty_numeric_sequence_count": 8, + "numeric_catalog_record_count": 4616, + "numeric_sequence_count_including_empty": 8, + "role_record_counts": { + "value": 4616 + }, + "role_valid_counts": { + "value": 45356103 + }, + "source_bindings": { + "block_catalog_bytes": 13565544, + "block_catalog_path": "/data/root/web_compression/datasets164/YaleLanguages/typed/full/blocks.jsonl", + "block_catalog_sha256": "c542adf7729af1cf5eea2c34fd252a533888b534b90ecb09650b5d6e2bbc6dd5", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/YaleLanguages/typed/dataset_manifest.json", + "typed_manifest_sha256": "78044819f2855d63273d25658b540a1845fb33110781435f1641ee1bf9e69b2c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 45356103 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 30.8716052531 is below 128", + "dataset_id": "africa_senegal_mauritania_crops_spi", + "empty_numeric_sequence_count": 99, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 30.87160525309193, + "nonempty_numeric_sequence_count": 7843, + "numeric_catalog_record_count": 7942, + "numeric_sequence_count_including_empty": 7942, + "role_record_counts": { + "value": 7942 + }, + "role_valid_counts": { + "value": 242126 + }, + "source_bindings": { + "block_catalog_bytes": 18563392, + "block_catalog_path": "/data/root/web_compression/datasets164/africa_senegal_mauritania_crops_spi/typed/full/blocks.jsonl", + "block_catalog_sha256": "69e195e6a31c16e86bd8fb450ca8b82c7142b41c274534b6571e561b7a98163f", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/africa_senegal_mauritania_crops_spi/typed/dataset_manifest.json", + "typed_manifest_sha256": "7d13ad8ef221f1996ee5f7ccc75d7c33e9dffd763021c546a25d18905e72c728" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 242126 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2977.75 is at least 128", + "dataset_id": "ahr999-dataset", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2977.75, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 4, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 4 + }, + "role_valid_counts": { + "value": 11911 + }, + "source_bindings": { + "block_catalog_bytes": 8668, + "block_catalog_path": "/data/root/web_compression/datasets164/ahr999-dataset/typed/full/blocks.jsonl", + "block_catalog_sha256": "fb7388bb402347bf8097db7bd35c3eb79fee544d30acfc0311de3bc1f01a82ee", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ahr999-dataset/typed/dataset_manifest.json", + "typed_manifest_sha256": "77fc665aea1863870eb53712cf8a1ed7ac5de0492ba679e5445a06c65e59af40" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11911 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 147 is at least 128", + "dataset_id": "ast_spacemobile_fleet_data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 147.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 6, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 6 + }, + "role_valid_counts": { + "value": 882 + }, + "source_bindings": { + "block_catalog_bytes": 13553, + "block_catalog_path": "/data/root/web_compression/datasets164/ast_spacemobile_fleet_data/typed/full/blocks.jsonl", + "block_catalog_sha256": "9b337cecfa2e2c258e1b2670ba1d4b74d98c843e1bbd70f914d3eb0fe7a9107c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ast_spacemobile_fleet_data/typed/dataset_manifest.json", + "typed_manifest_sha256": "e84ccd99c24f9494018d5c87ac20f99b6fedb72c4e8c0ff9bd799662b9c730b3" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 882 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 28660.6666667 is at least 128", + "dataset_id": "australia_solar", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 28660.666666666668, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 12, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 12 + }, + "role_valid_counts": { + "value": 85982 + }, + "source_bindings": { + "block_catalog_bytes": 26333, + "block_catalog_path": "/data/root/web_compression/datasets164/australia_solar/typed/full/blocks.jsonl", + "block_catalog_sha256": "b2dc93e5cfb8423a3d8728cb8dff5227e91ee9942d7690a9082fb8aaf4ec82f6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/australia_solar/typed/dataset_manifest.json", + "typed_manifest_sha256": "af63863500eb02b150d512b43779e4684b5d68b1e2a4aab87cb96e7f6c90d5e3" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 85982 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 231052.8 is at least 128", + "dataset_id": "australian_electricity_demand", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 231052.8, + "nonempty_numeric_sequence_count": 10, + "numeric_catalog_record_count": 240, + "numeric_sequence_count_including_empty": 10, + "role_record_counts": { + "additional_temporal_coordinate": 120, + "value": 120 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 1155264, + "value": 1155264 + }, + "source_bindings": { + "block_catalog_bytes": 561103, + "block_catalog_path": "/data/root/web_compression/datasets164/australian_electricity_demand/typed/full/blocks.jsonl", + "block_catalog_sha256": "391b2e345a46200538564a670f7f6efb0e67397e9b35f0847d1e72eead44115d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/australian_electricity_demand/typed/dataset_manifest.json", + "typed_manifest_sha256": "b71635914cebf0b549a254a832ea5de00131fdd20ce1bf703439d0ce5444a8fe" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2310528 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 367 is at least 128", + "dataset_id": "auto_production_sf", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 367.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 1, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 1 + }, + "role_valid_counts": { + "value": 367 + }, + "source_bindings": { + "block_catalog_bytes": 2189, + "block_catalog_path": "/data/root/web_compression/datasets164/auto_production_sf/typed/full/blocks.jsonl", + "block_catalog_sha256": "1ed512ccc24f563ae75a63b2bf64664d7abfb1027f7c96d960c7e262849ae27e", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/auto_production_sf/typed/dataset_manifest.json", + "typed_manifest_sha256": "826f3ee8ec3b3315e4fe9f7c356ca2e214810120b60b992b3fd4aea6c2a33eca" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 367 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1406.06410256 is at least 128", + "dataset_id": "azure2019_u", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1406.0641025641025, + "nonempty_numeric_sequence_count": 234, + "numeric_catalog_record_count": 234, + "numeric_sequence_count_including_empty": 234, + "role_record_counts": { + "value": 234 + }, + "role_valid_counts": { + "value": 329019 + }, + "source_bindings": { + "block_catalog_bytes": 505587, + "block_catalog_path": "/data/root/web_compression/datasets164/azure2019_u/typed/full/blocks.jsonl", + "block_catalog_sha256": "85b4c3888699074aa7f60ef604d1f62ef94190a2c83797d59190cf3dd331a4cc", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/azure2019_u/typed/dataset_manifest.json", + "typed_manifest_sha256": "4b35feb998503f368fb201a1f8a201993d090325d3a316fc06ade78d150eee23" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 329019 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 4580.16666667 is at least 128", + "dataset_id": "bitcoin", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 4580.166666666667, + "nonempty_numeric_sequence_count": 36, + "numeric_catalog_record_count": 36, + "numeric_sequence_count_including_empty": 36, + "role_record_counts": { + "additional_temporal_coordinate": 18, + "value": 18 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 82443, + "value": 82443 + }, + "source_bindings": { + "block_catalog_bytes": 77350, + "block_catalog_path": "/data/root/web_compression/datasets164/bitcoin/typed/full/blocks.jsonl", + "block_catalog_sha256": "83b96b60a6ce750149ff7d95313809ad20f9b1ce7e39dcde5ac1eac2f8f3c9df", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/bitcoin/typed/dataset_manifest.json", + "typed_manifest_sha256": "f6e81ee307509fa04833b93859868b856e3a5141f34873f5ef444ce04591cb85" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 164886 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1048575 is at least 128", + "dataset_id": "bitcoin_price_timeseries", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1048575.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 525, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 525 + }, + "role_valid_counts": { + "value": 5242875 + }, + "source_bindings": { + "block_catalog_bytes": 1191391, + "block_catalog_path": "/data/root/web_compression/datasets164/bitcoin_price_timeseries/typed/full/blocks.jsonl", + "block_catalog_sha256": "fb400b2d06b922475deab62c1457936e0cf4023b1a2a33905ee6a3f2cd9d847b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/bitcoin_price_timeseries/typed/dataset_manifest.json", + "typed_manifest_sha256": "bb5f7308c0b19d08d9a6d5ed66831e60d23f2497c9f87854319b3baf40936fa2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5242875 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 50.7651458489 is below 128", + "dataset_id": "car_parts", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 50.76514584891548, + "nonempty_numeric_sequence_count": 5348, + "numeric_catalog_record_count": 5348, + "numeric_sequence_count_including_empty": 5348, + "role_record_counts": { + "additional_temporal_coordinate": 2674, + "value": 2674 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 135746, + "value": 135746 + }, + "source_bindings": { + "block_catalog_bytes": 11551132, + "block_catalog_path": "/data/root/web_compression/datasets164/car_parts/typed/full/blocks.jsonl", + "block_catalog_sha256": "df9670d9af90f132228ca048bf46889c53eae59fcf4561cb727f78112f30dd33", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/car_parts/typed/dataset_manifest.json", + "typed_manifest_sha256": "3deda1e663dfc0f1255b0ddac83b7859d6c6e44ab1790f64b4d311147c6842fe" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 271492 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 30815.5416667 is at least 128", + "dataset_id": "coastal_t_s", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 30815.541666666668, + "nonempty_numeric_sequence_count": 144, + "numeric_catalog_record_count": 510, + "numeric_sequence_count_including_empty": 144, + "role_record_counts": { + "value": 510 + }, + "role_valid_counts": { + "value": 4437438 + }, + "source_bindings": { + "block_catalog_bytes": 1108708, + "block_catalog_path": "/data/root/web_compression/datasets164/coastal_t_s/typed/full/blocks.jsonl", + "block_catalog_sha256": "2d50a083dabd17d64a2b529e8956720bb418cbe816bd75d67f596344bfd1e629", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/coastal_t_s/typed/dataset_manifest.json", + "typed_manifest_sha256": "b2af8587b70fca1b3d92f20e5779292af95154d7f3899a390b85bbc5126185b8" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4437438 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 697.25 is at least 128", + "dataset_id": "commodity_import", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 697.25, + "nonempty_numeric_sequence_count": 8, + "numeric_catalog_record_count": 8, + "numeric_sequence_count_including_empty": 8, + "role_record_counts": { + "value": 8 + }, + "role_valid_counts": { + "value": 5578 + }, + "source_bindings": { + "block_catalog_bytes": 17472, + "block_catalog_path": "/data/root/web_compression/datasets164/commodity_import/typed/full/blocks.jsonl", + "block_catalog_sha256": "4523f31ebee40271b295d566f65482060dfcb9e77de573b97069fc3e1d8e6fe6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/commodity_import/typed/dataset_manifest.json", + "typed_manifest_sha256": "aa4773cea4f52bcea10118cd08a3abcff08e47842977599a951fa48927c8c54f" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5578 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 325.09375 is at least 128", + "dataset_id": "commodity_production", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 325.09375, + "nonempty_numeric_sequence_count": 32, + "numeric_catalog_record_count": 32, + "numeric_sequence_count_including_empty": 32, + "role_record_counts": { + "value": 32 + }, + "role_valid_counts": { + "value": 10403 + }, + "source_bindings": { + "block_catalog_bytes": 71025, + "block_catalog_path": "/data/root/web_compression/datasets164/commodity_production/typed/full/blocks.jsonl", + "block_catalog_sha256": "ea18ee9a3dd58f5c8e0aaf81d628d28025e1396431e6e276bdff2e4b393c16db", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/commodity_production/typed/dataset_manifest.json", + "typed_manifest_sha256": "63bbd8e4b788c365f911542ae99144c660b94ffe8b3ceec1bb4065ab1fa96fdb" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 10403 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 212 is at least 128", + "dataset_id": "covid_deaths-monash", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 212.0, + "nonempty_numeric_sequence_count": 532, + "numeric_catalog_record_count": 532, + "numeric_sequence_count_including_empty": 532, + "role_record_counts": { + "additional_temporal_coordinate": 266, + "value": 266 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 56392, + "value": 56392 + }, + "source_bindings": { + "block_catalog_bytes": 1187783, + "block_catalog_path": "/data/root/web_compression/datasets164/covid_deaths-monash/typed/full/blocks.jsonl", + "block_catalog_sha256": "be1b68fcfbd29de25cabec0057a4a383d465e01950f0dab480f6f9efd61e832d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/covid_deaths-monash/typed/dataset_manifest.json", + "typed_manifest_sha256": "219ea4a90a988a4fb686b07fdb4adc36271b3b111ad2c485bde077d59b08121a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 112784 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8343.125 is at least 128", + "dataset_id": "cphl", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8343.125, + "nonempty_numeric_sequence_count": 8, + "numeric_catalog_record_count": 11, + "numeric_sequence_count_including_empty": 8, + "role_record_counts": { + "value": 11 + }, + "role_valid_counts": { + "value": 66745 + }, + "source_bindings": { + "block_catalog_bytes": 23131, + "block_catalog_path": "/data/root/web_compression/datasets164/cphl/typed/full/blocks.jsonl", + "block_catalog_sha256": "24852c6f4f12e6b7381c66e6a679e129e9bb20de0a2c86d90212b6767b45fe69", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/cphl/typed/dataset_manifest.json", + "typed_manifest_sha256": "39b05c9f511d33aeb8aad7a881aba3024e3a2062f0941cacbecdb606eda35329" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 66745 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2842 is at least 128", + "dataset_id": "crypto", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2842.0, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 4, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 4 + }, + "role_valid_counts": { + "value": 11368 + }, + "source_bindings": { + "block_catalog_bytes": 8443, + "block_catalog_path": "/data/root/web_compression/datasets164/crypto/typed/full/blocks.jsonl", + "block_catalog_sha256": "ebc40bc5f0b4211e46b2de705a09f666aecceebca8da370fdb9dc379e93835b4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/crypto/typed/dataset_manifest.json", + "typed_manifest_sha256": "05b502323ee37895a1225844482bfff81a1244ef79489ca47c66b8d3a337226f" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11368 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 735.462585034 is at least 128", + "dataset_id": "crypto_data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 735.4625850340136, + "nonempty_numeric_sequence_count": 1470, + "numeric_catalog_record_count": 1470, + "numeric_sequence_count_including_empty": 1470, + "role_record_counts": { + "value": 1470 + }, + "role_valid_counts": { + "value": 1081130 + }, + "source_bindings": { + "block_catalog_bytes": 3166517, + "block_catalog_path": "/data/root/web_compression/datasets164/crypto_data/typed/full/blocks.jsonl", + "block_catalog_sha256": "df528320bed5b61129b95e6dcaa96497a9bc847973634e32cb5ead5a68432371", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/crypto_data/typed/dataset_manifest.json", + "typed_manifest_sha256": "f11ef9f52b1b34e34b19b0cfd629c496e3f53daa331c6e124aaa55c837dd7f50" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1081130 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8097.6 is at least 128", + "dataset_id": "current_velocity", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8097.6, + "nonempty_numeric_sequence_count": 390, + "numeric_catalog_record_count": 528, + "numeric_sequence_count_including_empty": 390, + "role_record_counts": { + "value": 528 + }, + "role_valid_counts": { + "value": 3158064 + }, + "source_bindings": { + "block_catalog_bytes": 1168307, + "block_catalog_path": "/data/root/web_compression/datasets164/current_velocity/typed/full/blocks.jsonl", + "block_catalog_sha256": "2ad692e84f2d3a1c621fc1135080a42775943a305bf0a3d261bee2e72243c561", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/current_velocity/typed/dataset_manifest.json", + "typed_manifest_sha256": "15dbc4cadf5cee619d589eb078c5d01c8d5b93210d2126937be53efed9673e37" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 3158064 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 51818.4 is at least 128", + "dataset_id": "deep-space-probes", + "empty_numeric_sequence_count": 93, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 51818.4, + "nonempty_numeric_sequence_count": 95, + "numeric_catalog_record_count": 4747, + "numeric_sequence_count_including_empty": 188, + "role_record_counts": { + "value": 4747 + }, + "role_valid_counts": { + "value": 4922748 + }, + "source_bindings": { + "block_catalog_bytes": 10556811, + "block_catalog_path": "/data/root/web_compression/datasets164/deep-space-probes/typed/full/blocks.jsonl", + "block_catalog_sha256": "4a6bc6c8f12823a83ad7fc2a89abb55e599e58253978c3d71671d2328ab08d4c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/deep-space-probes/typed/dataset_manifest.json", + "typed_manifest_sha256": "cab1dde5aca2e736bbb99f9096cf171af207c2fbb029b2fc4a80c5d54437f972" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4922748 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 48.0614420063 is below 128", + "dataset_id": "dmi-aarhus-weather-data", + "empty_numeric_sequence_count": 4010, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 48.061442006269594, + "nonempty_numeric_sequence_count": 60610, + "numeric_catalog_record_count": 64620, + "numeric_sequence_count_including_empty": 64620, + "role_record_counts": { + "additional_temporal_coordinate": 874, + "value": 63746 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 43910, + "value": 2869094 + }, + "source_bindings": { + "block_catalog_bytes": 145991876, + "block_catalog_path": "/data/root/web_compression/datasets164/dmi-aarhus-weather-data/typed/full/blocks.jsonl", + "block_catalog_sha256": "76999b090861b54c87599295d59ea84275a1657159b2fc10f3c10fcc7f5f0276", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/dmi-aarhus-weather-data/typed/dataset_manifest.json", + "typed_manifest_sha256": "07816de98eda4e4567d96cfd1f0f0017b9476aad776dfb338c4dac9e0fb496d4" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2913004 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 391519 is at least 128", + "dataset_id": "dst-index", + "empty_numeric_sequence_count": 2, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 391519.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 160, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 160 + }, + "role_valid_counts": { + "value": 783038 + }, + "source_bindings": { + "block_catalog_bytes": 343620, + "block_catalog_path": "/data/root/web_compression/datasets164/dst-index/typed/full/blocks.jsonl", + "block_catalog_sha256": "df9de70944f7e233b67b3cd621fa9a5d189dd1e67df804a13d412ed685da5fc8", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/dst-index/typed/dataset_manifest.json", + "typed_manifest_sha256": "09d8c756f4683ca1e9b044cc4312d6c42a7dc5d4eb61a3ce17226e6c429a5094" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 783038 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 491.6 is at least 128", + "dataset_id": "ecdc_covid", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 491.6, + "nonempty_numeric_sequence_count": 25, + "numeric_catalog_record_count": 25, + "numeric_sequence_count_including_empty": 25, + "role_record_counts": { + "value": 25 + }, + "role_valid_counts": { + "value": 12290 + }, + "source_bindings": { + "block_catalog_bytes": 53517, + "block_catalog_path": "/data/root/web_compression/datasets164/ecdc_covid/typed/full/blocks.jsonl", + "block_catalog_sha256": "39395af50827129ffec74a612cfa8051ce37518cefd7f3986ebc5067ce3abe4a", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ecdc_covid/typed/dataset_manifest.json", + "typed_manifest_sha256": "b3c3f67c0d8976c8ace32792ea9f3546e95c0a037fbe8a58d527a4ed6332efc0" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 12290 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 51188.2368421 is at least 128", + "dataset_id": "eea_pm25_forecasting", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 51188.23684210526, + "nonempty_numeric_sequence_count": 1710, + "numeric_catalog_record_count": 9675, + "numeric_sequence_count_including_empty": 1710, + "role_record_counts": { + "value": 9675 + }, + "role_valid_counts": { + "value": 87531885 + }, + "source_bindings": { + "block_catalog_bytes": 21824702, + "block_catalog_path": "/data/root/web_compression/datasets164/eea_pm25_forecasting/typed/full/blocks.jsonl", + "block_catalog_sha256": "0695d5d097d7288caa0cb2b00525b99c3244a63c33dc58266ca298f392deb458", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/eea_pm25_forecasting/typed/dataset_manifest.json", + "typed_manifest_sha256": "e59fec36013f68d8943f3f5c7899b1f10d323207a11b6175fd69787513836a14" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 87531885 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1344 is at least 128", + "dataset_id": "electricity_demand", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1344.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 2, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "value": 2 + }, + "role_valid_counts": { + "value": 2688 + }, + "source_bindings": { + "block_catalog_bytes": 4397, + "block_catalog_path": "/data/root/web_compression/datasets164/electricity_demand/typed/full/blocks.jsonl", + "block_catalog_sha256": "a672a9415634222165310c1a6b39487a9d9da2f6f6ee09708bedd7b318b3174b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/electricity_demand/typed/dataset_manifest.json", + "typed_manifest_sha256": "39d5e0577b74ae3e0443c5c8f63f958c80ac95741d02e9a6d8e6a8f7f80e118d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2688 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 140256 is at least 128", + "dataset_id": "electricity_load_2011_2014", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 140256.0, + "nonempty_numeric_sequence_count": 370, + "numeric_catalog_record_count": 5550, + "numeric_sequence_count_including_empty": 370, + "role_record_counts": { + "value": 5550 + }, + "role_valid_counts": { + "value": 51894720 + }, + "source_bindings": { + "block_catalog_bytes": 12620118, + "block_catalog_path": "/data/root/web_compression/datasets164/electricity_load_2011_2014/typed/full/blocks.jsonl", + "block_catalog_sha256": "697d25d5235ddf71d32a12b9eadfa42d51c967007e4c41050efd18b55704d6ec", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/electricity_load_2011_2014/typed/dataset_manifest.json", + "typed_manifest_sha256": "96528fe8394a3c5965080b4fb11014144c4defa3cd41eae5a5ad3187121483fa" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 51894720 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 397 is at least 128", + "dataset_id": "electricity_production", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 397.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 1, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 1 + }, + "role_valid_counts": { + "value": 397 + }, + "source_bindings": { + "block_catalog_bytes": 2220, + "block_catalog_path": "/data/root/web_compression/datasets164/electricity_production/typed/full/blocks.jsonl", + "block_catalog_sha256": "47b61576c78bded59965a68615c2e545815b85b5c3acab59cd835d38a66c398d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/electricity_production/typed/dataset_manifest.json", + "typed_manifest_sha256": "a98f876267f9ab3dc0010d212ecd9155576943e9343bd470bb9ba5782c4a303b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 397 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 32260 is at least 128", + "dataset_id": "enedis-with-holidays", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 32260.0, + "nonempty_numeric_sequence_count": 12, + "numeric_catalog_record_count": 44, + "numeric_sequence_count_including_empty": 12, + "role_record_counts": { + "value": 44 + }, + "role_valid_counts": { + "value": 387120 + }, + "source_bindings": { + "block_catalog_bytes": 98763, + "block_catalog_path": "/data/root/web_compression/datasets164/enedis-with-holidays/typed/full/blocks.jsonl", + "block_catalog_sha256": "4df83f355079d44cbabf2b2b869133d967e48df6bb7601fefe9b6f78618ef9c3", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/enedis-with-holidays/typed/dataset_manifest.json", + "typed_manifest_sha256": "946f9b3f235bf4a131ca482913cdab89226c4e3cd65b15f0ea31434e5bd47b33" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 387120 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 52416 is at least 128", + "dataset_id": "epf_electricity_price", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 52416.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 30, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 30 + }, + "role_valid_counts": { + "value": 262080 + }, + "source_bindings": { + "block_catalog_bytes": 67333, + "block_catalog_path": "/data/root/web_compression/datasets164/epf_electricity_price/typed/full/blocks.jsonl", + "block_catalog_sha256": "d9dae4a21712f4cd00996fe6d6b2cab69f1163b2f63edaab46b7127ba29e98bb", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/epf_electricity_price/typed/dataset_manifest.json", + "typed_manifest_sha256": "5ae9ebb15f44c974eaef30d031d0c161372a042af93b3e143ac47c05d12ab7de" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 262080 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 20544 is at least 128", + "dataset_id": "eweld_load", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 20544.0, + "nonempty_numeric_sequence_count": 10, + "numeric_catalog_record_count": 30, + "numeric_sequence_count_including_empty": 10, + "role_record_counts": { + "value": 30 + }, + "role_valid_counts": { + "value": 205440 + }, + "source_bindings": { + "block_catalog_bytes": 64575, + "block_catalog_path": "/data/root/web_compression/datasets164/eweld_load/typed/full/blocks.jsonl", + "block_catalog_sha256": "d3bf5669cf674c21872f6eb6f99780411f91337231ee759c41c28e88c15d824a", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/eweld_load/typed/dataset_manifest.json", + "typed_manifest_sha256": "0bcd5c6be8ef21cc5511a012e8ee2369aee1c236e8bfe4d2842f83d1006ee98b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 205440 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7588 is at least 128", + "dataset_id": "exchange_rate", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7588.0, + "nonempty_numeric_sequence_count": 8, + "numeric_catalog_record_count": 8, + "numeric_sequence_count_including_empty": 8, + "role_record_counts": { + "value": 8 + }, + "role_valid_counts": { + "value": 60704 + }, + "source_bindings": { + "block_catalog_bytes": 17244, + "block_catalog_path": "/data/root/web_compression/datasets164/exchange_rate/typed/full/blocks.jsonl", + "block_catalog_sha256": "7dd75730c59c244e22dc982f2f52d2f3bd6f36be3e32196bce911694e10e90ce", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/exchange_rate/typed/dataset_manifest.json", + "typed_manifest_sha256": "7155b4abd6bc5fdc0ff7c5ea2794dd62b2efb3101cb318c274755ae4b4f51a59" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 60704 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 3256.11111111 is at least 128", + "dataset_id": "faang_engineered_time_series_features_2013_2025", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 3256.1111111111113, + "nonempty_numeric_sequence_count": 45, + "numeric_catalog_record_count": 45, + "numeric_sequence_count_including_empty": 45, + "role_record_counts": { + "value": 45 + }, + "role_valid_counts": { + "value": 146525 + }, + "source_bindings": { + "block_catalog_bytes": 110077, + "block_catalog_path": "/data/root/web_compression/datasets164/faang_engineered_time_series_features_2013_2025/typed/full/blocks.jsonl", + "block_catalog_sha256": "5e78183c7efa6213b6ba5ae1cd5d6ed5e1f9d2b797a9ca0df6eb0b8b99d8256e", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/faang_engineered_time_series_features_2013_2025/typed/dataset_manifest.json", + "typed_manifest_sha256": "77358b6cf4f274b464afcd5079fe0c0991203439e2eae5c5a1973b47314ed46a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 146525 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 35136 is at least 128", + "dataset_id": "finland_traffic", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 35136.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 4, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 4 + }, + "role_valid_counts": { + "value": 35136 + }, + "source_bindings": { + "block_catalog_bytes": 8758, + "block_catalog_path": "/data/root/web_compression/datasets164/finland_traffic/typed/full/blocks.jsonl", + "block_catalog_sha256": "9ebba442c59efc6d35640381e52b2b977db8c9612a9b6e9ea0998762f7c63415", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/finland_traffic/typed/dataset_manifest.json", + "typed_manifest_sha256": "1c3c5a20be2b85666675210ab52bf6e00a19603519d2251e3a89716ec78ed839" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 35136 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 177.491525424 is at least 128", + "dataset_id": "forex_factory_calendar", + "empty_numeric_sequence_count": 1879, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 177.4915254237288, + "nonempty_numeric_sequence_count": 236, + "numeric_catalog_record_count": 2115, + "numeric_sequence_count_including_empty": 2115, + "role_record_counts": { + "value": 2115 + }, + "role_valid_counts": { + "value": 41888 + }, + "source_bindings": { + "block_catalog_bytes": 4717810, + "block_catalog_path": "/data/root/web_compression/datasets164/forex_factory_calendar/typed/full/blocks.jsonl", + "block_catalog_sha256": "f89146c9b058adabce7a3977948496b0bf10dfcf4005aef9dc4640f373927174", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/forex_factory_calendar/typed/dataset_manifest.json", + "typed_manifest_sha256": "567b0348c0eba7ff3d55665d2615dff67654636d51a7387da065f8892e32217d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 41888 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 728 is at least 128", + "dataset_id": "fred_md", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 728.0, + "nonempty_numeric_sequence_count": 214, + "numeric_catalog_record_count": 214, + "numeric_sequence_count_including_empty": 214, + "role_record_counts": { + "additional_temporal_coordinate": 107, + "value": 107 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 77896, + "value": 77896 + }, + "source_bindings": { + "block_catalog_bytes": 458676, + "block_catalog_path": "/data/root/web_compression/datasets164/fred_md/typed/full/blocks.jsonl", + "block_catalog_sha256": "5bc9e297232d3cacfa0959ab610742875db1968505da9c49e20323841207b473", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/fred_md/typed/dataset_manifest.json", + "typed_manifest_sha256": "632fba7f01d6bf111a113a346ece221a5581033dc34be8261ce9e5c655263898" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 155792 + }, + { + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 48.5 is below 128", + "dataset_id": "freshretailnet_50k", + "details": { + "entities": 100000, + "rows": 4850000, + "structural_inactive_columns_per_row": 57, + "table_applicable_value_columns_per_entity": 57, + "total_table_qualified_columns": 114 + }, + "empty_numeric_sequence_count": 0, + "input_version": "corrected_full114_typed_frozen_ready", + "mean_valid_values_per_sequence": 48.5, + "nonempty_numeric_sequence_count": 5700000, + "numeric_sequence_count_including_empty": 5700000, + "source_bindings": { + "block_catalog": { + "bytes": 13015265091, + "path": "/data/user/new_ai_compress/operator_sweep/six_dataset_numeric_repair_20261012_v1/typed_attempt_v2/datasets/freshretailnet_50k/full/blocks.jsonl", + "sha256": "fe0b800aed22cde1e823dd8f0861246acd71746023f0ddb095a9e2510fa7fe8c" + }, + "frozen_ready": { + "bytes": 8026, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/fresh50k/typed_ready_v2/FROZEN_READY.json", + "sha256": "1b71521fbd61e9d9ffe737d57b6ac73077b7e8e1f77661eacac45e8a4abb1dcd" + }, + "source_data_sha256": "6f7e162d476c2025cd1493da71939f5c20f0e7cbdb5724b4d1e3bc0b11a4ff3c", + "typed_manifest": { + "bytes": 82351, + "path": "/data/user/new_ai_compress/operator_sweep/six_dataset_numeric_repair_20261012_v1/typed_attempt_v2/datasets/freshretailnet_50k/dataset_manifest.json", + "sha256": "17b2a278f4eeacc1f27a64e1cbb348e1946e6ed173a658eca59c15d94d4ece76" + } + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 276450000 + }, + { + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 241.037948936 is at least 128", + "dataset_id": "freshretailnet_lt", + "details": { + "entities": 32939, + "null_nan_inf": { + "nan": 0, + "negative_inf": 0, + "null": 0, + "positive_inf": 0 + }, + "readiness_boundary": "exact source-derived scope statistic; typed production remains gated", + "rows": 7939549, + "structural_inactive_columns_per_row": 57, + "table_applicable_value_columns_per_entity": 57, + "total_table_qualified_columns": 114 + }, + "empty_numeric_sequence_count": 0, + "input_version": "corrected_full114_source_contract_pending_typed_ready", + "mean_valid_values_per_sequence": 241.03794893591183, + "nonempty_numeric_sequence_count": 1877523, + "numeric_sequence_count_including_empty": 1877523, + "source_bindings": { + "contract_status": "frozen_preparation_contract", + "input_contract": { + "bytes": 1744, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/final160_dataset_format_audit_20261013_v1/remote_input_build/INPUT_CONTRACT.json", + "sha256": "c88f506e22066773e93eb2e764ace34c6df3cdc00654293724be7dde4f60f2a3" + } + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 452554293 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1933.875 is at least 128", + "dataset_id": "fulus_lyd_rates_2025", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1933.875, + "nonempty_numeric_sequence_count": 24, + "numeric_catalog_record_count": 24, + "numeric_sequence_count_including_empty": 24, + "role_record_counts": { + "additional_temporal_coordinate": 8, + "value": 16 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 15471, + "value": 30942 + }, + "source_bindings": { + "block_catalog_bytes": 53678, + "block_catalog_path": "/data/root/web_compression/datasets164/fulus_lyd_rates_2025/typed/full/blocks.jsonl", + "block_catalog_sha256": "624b8e02b05f0d6d13cafc9167620b6689d3561a4b44f229a8262354278bf1f7", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/fulus_lyd_rates_2025/typed/dataset_manifest.json", + "typed_manifest_sha256": "cff98d8ee6295e1edc02c8ca2051bdefb8c9f2f9b94acdc82b5904bd080a730d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 46413 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 686 is at least 128", + "dataset_id": "geomagnetic_kp_index", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 686.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 3, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 3 + }, + "role_valid_counts": { + "value": 2058 + }, + "source_bindings": { + "block_catalog_bytes": 6618, + "block_catalog_path": "/data/root/web_compression/datasets164/geomagnetic_kp_index/typed/full/blocks.jsonl", + "block_catalog_sha256": "fc6624fb3efc6626af2898a4637b840ab1a7f2ca492d7aa6a82dc936a0a254d0", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/geomagnetic_kp_index/typed/dataset_manifest.json", + "typed_manifest_sha256": "54b97f0693f8635c268b299783042bebd9088997ad6eb76eda97fa955b373222" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2058 + }, + { + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 6.24678294161 is below 128", + "dataset_id": "github_top_projects", + "empty_numeric_sequence_count": 5888, + "input_version": "corrected_accepted_input", + "mean_valid_values_per_sequence": 6.246782941614378, + "nonempty_numeric_sequence_count": 37612, + "numeric_sequence_count_including_empty": 43500, + "row_count": 85173, + "source_bindings": { + "columns_csv": { + "bytes": 443, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/github_top_projects/columns.csv", + "sha256": "f1ee36477b22012eab7b9567b138be0a01265377df6541bef82b6519ed087be1" + }, + "data_csv": { + "bytes": 2855950, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/github_top_projects/data.csv", + "sha256": "faa5bdd56961f095da5d6f885055ad3d05a5711814547d9be9d8449a81f43201" + }, + "dataset_manifest": { + "bytes": 1316, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/github_top_projects/dataset_manifest.json", + "sha256": "c472deb1f54446d0a7d83cb239424ece7da8e73b73737ae234ac2b68fd276d5c" + }, + "method": "local_exact_corrected_wide_csv_scan", + "series_map_csv": { + "bytes": 2136531, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/github_top_projects/series_map.csv", + "sha256": "a15818feb0a413c06652f6e68ef88dd97edd19e603b726bc2ba7f102ac3232d9" + } + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 234954 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 201.75 is at least 128", + "dataset_id": "global_influenza", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 201.75, + "nonempty_numeric_sequence_count": 60, + "numeric_catalog_record_count": 60, + "numeric_sequence_count_including_empty": 60, + "role_record_counts": { + "value": 60 + }, + "role_valid_counts": { + "value": 12105 + }, + "source_bindings": { + "block_catalog_bytes": 131163, + "block_catalog_path": "/data/root/web_compression/datasets164/global_influenza/typed/full/blocks.jsonl", + "block_catalog_sha256": "8c03598b7a443906ff28992df8c3510179ac7983aab80fc8cc02a2ad8116377d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/global_influenza/typed/dataset_manifest.json", + "typed_manifest_sha256": "abad355b9650bb55d3ee0f1751ee96b8f319aebae1fa44401901f4d8cb02d35d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 12105 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 141.066666667 is at least 128", + "dataset_id": "global_price", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 141.06666666666666, + "nonempty_numeric_sequence_count": 60, + "numeric_catalog_record_count": 60, + "numeric_sequence_count_including_empty": 60, + "role_record_counts": { + "value": 60 + }, + "role_valid_counts": { + "value": 8464 + }, + "source_bindings": { + "block_catalog_bytes": 129129, + "block_catalog_path": "/data/root/web_compression/datasets164/global_price/typed/full/blocks.jsonl", + "block_catalog_sha256": "3201382d4cba50c558f882487453e95ca30e4123121cb0feaee5998796cad177", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/global_price/typed/dataset_manifest.json", + "typed_manifest_sha256": "b92c5c6df2e35f2ee1410c1ffc20433f3f3c1bbbc423e61b735f32c5310c28ee" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 8464 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 109.25 is below 128", + "dataset_id": "globalstar_fleet_data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 109.25, + "nonempty_numeric_sequence_count": 20, + "numeric_catalog_record_count": 20, + "numeric_sequence_count_including_empty": 20, + "role_record_counts": { + "value": 20 + }, + "role_valid_counts": { + "value": 2185 + }, + "source_bindings": { + "block_catalog_bytes": 44300, + "block_catalog_path": "/data/root/web_compression/datasets164/globalstar_fleet_data/typed/full/blocks.jsonl", + "block_catalog_sha256": "c8378f97eaaafb2678dc119ed5fc922077f6e96324059dcc25515c01137ebafd", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/globalstar_fleet_data/typed/dataset_manifest.json", + "typed_manifest_sha256": "e13103d004e8503a68292af02b6b14704065d33318e8dbef15a623567fc616b0" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2185 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2716.09357278 is at least 128", + "dataset_id": "gluco_tsfm_benchmark", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2716.093572778828, + "nonempty_numeric_sequence_count": 1058, + "numeric_catalog_record_count": 1219, + "numeric_sequence_count_including_empty": 1058, + "role_record_counts": { + "value": 1219 + }, + "role_valid_counts": { + "value": 2873627 + }, + "source_bindings": { + "block_catalog_bytes": 2732352, + "block_catalog_path": "/data/root/web_compression/datasets164/gluco_tsfm_benchmark/typed/full/blocks.jsonl", + "block_catalog_sha256": "b4f56be75e72c91e46bf3a81d643ec023f573aa3bc828258dc00e2a6979e8201", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/gluco_tsfm_benchmark/typed/dataset_manifest.json", + "typed_manifest_sha256": "7dc58193b769c0fb01c649903f4fb24876c48a22f5ec44c5b27022015694832b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2873627 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 362652.432836 is at least 128", + "dataset_id": "goes_omni_electron_flux_forecasting", + "empty_numeric_sequence_count": 16, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 362652.4328358209, + "nonempty_numeric_sequence_count": 134, + "numeric_catalog_record_count": 6172, + "numeric_sequence_count_including_empty": 150, + "role_record_counts": { + "value": 6172 + }, + "role_valid_counts": { + "value": 48595426 + }, + "source_bindings": { + "block_catalog_bytes": 14561214, + "block_catalog_path": "/data/root/web_compression/datasets164/goes_omni_electron_flux_forecasting/typed/full/blocks.jsonl", + "block_catalog_sha256": "c84f5487ca84ecc292d1537ebc19cd1189c6decddf8e57c2d4423ce64a8692d6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/goes_omni_electron_flux_forecasting/typed/dataset_manifest.json", + "typed_manifest_sha256": "5086b8b7db0b4e8154e70f61bbe4c599ffe2bb4f8cfa32d9e1abaf51229829dc" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 48595426 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1143 is at least 128", + "dataset_id": "greatplains_multisource_2000_2024", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1143.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 5, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 5 + }, + "role_valid_counts": { + "value": 5715 + }, + "source_bindings": { + "block_catalog_bytes": 11595, + "block_catalog_path": "/data/root/web_compression/datasets164/greatplains_multisource_2000_2024/typed/full/blocks.jsonl", + "block_catalog_sha256": "cda0a6ce23396007a133525e4b5e2a9fe3dcbaa788d54d16f525f6d7ca097ce4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/greatplains_multisource_2000_2024/typed/dataset_manifest.json", + "typed_manifest_sha256": "7a13bf97cbaf1b64fbaf0bf856e10b844810d202757ed85380ff133d1d1b375a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5715 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 84 is below 128", + "dataset_id": "hospital-monash", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 84.0, + "nonempty_numeric_sequence_count": 1534, + "numeric_catalog_record_count": 1534, + "numeric_sequence_count_including_empty": 1534, + "role_record_counts": { + "additional_temporal_coordinate": 767, + "value": 767 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 64428, + "value": 64428 + }, + "source_bindings": { + "block_catalog_bytes": 3369626, + "block_catalog_path": "/data/root/web_compression/datasets164/hospital-monash/typed/full/blocks.jsonl", + "block_catalog_sha256": "39e9d05162ca54709299ffe7bab36e3e8d0e6ef961a04dfa1d187475f92856b7", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/hospital-monash/typed/dataset_manifest.json", + "typed_manifest_sha256": "9ccb7c12def299f710a0b5418f3fb31cea3caf22b651dccd532531e8519a1e56" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 128856 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1400.10714286 is at least 128", + "dataset_id": "hourly-stock-data-2023", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1400.107142857143, + "nonempty_numeric_sequence_count": 112, + "numeric_catalog_record_count": 112, + "numeric_sequence_count_including_empty": 112, + "role_record_counts": { + "value": 112 + }, + "role_valid_counts": { + "value": 156812 + }, + "source_bindings": { + "block_catalog_bytes": 249935, + "block_catalog_path": "/data/root/web_compression/datasets164/hourly-stock-data-2023/typed/full/blocks.jsonl", + "block_catalog_sha256": "e54fb40ec39fac5c9671c1df6b6747b893372fba622edf6bd1dcd3cb9acbf316", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/hourly-stock-data-2023/typed/dataset_manifest.json", + "typed_manifest_sha256": "c8d76ad76f4475fcdf084f85a89ade99cb1d349d979f2efa0cac80df712e02f4" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 156812 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 46320 is at least 128", + "dataset_id": "hourly_electricity_demand_brazil", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 46320.0, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 20, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 20 + }, + "role_valid_counts": { + "value": 185280 + }, + "source_bindings": { + "block_catalog_bytes": 46863, + "block_catalog_path": "/data/root/web_compression/datasets164/hourly_electricity_demand_brazil/typed/full/blocks.jsonl", + "block_catalog_sha256": "827eb0d3a44088edf6fecbd138dc694dc902bfcf1343aa1490c544d60f3789a4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/hourly_electricity_demand_brazil/typed/dataset_manifest.json", + "typed_manifest_sha256": "ac4053eaf5624e276c32f226d5b90ee9819a3d2b4d2acc24ac4e76b80963f7df" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 185280 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 114 is below 128", + "dataset_id": "housing_inventory", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 114.0, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 4, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 4 + }, + "role_valid_counts": { + "value": 456 + }, + "source_bindings": { + "block_catalog_bytes": 8721, + "block_catalog_path": "/data/root/web_compression/datasets164/housing_inventory/typed/full/blocks.jsonl", + "block_catalog_sha256": "4dface5860d4a08cc0d4d3eb928358059c871a959ac2d887c445835c7dd1487b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/housing_inventory/typed/dataset_manifest.json", + "typed_manifest_sha256": "798085150daf04292d158ce9220ec446580bf2f7bef0b9c77822f738f2964d0b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 456 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7678.23333333 is at least 128", + "dataset_id": "indian_stock_hourly_2017_2021", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7678.233333333334, + "nonempty_numeric_sequence_count": 30, + "numeric_catalog_record_count": 30, + "numeric_sequence_count_including_empty": 30, + "role_record_counts": { + "value": 30 + }, + "role_valid_counts": { + "value": 230347 + }, + "source_bindings": { + "block_catalog_bytes": 68859, + "block_catalog_path": "/data/root/web_compression/datasets164/indian_stock_hourly_2017_2021/typed/full/blocks.jsonl", + "block_catalog_sha256": "6dc7dd1c8bcb008c1a5ba615bcbe662af3b4a0af762261c7e27b4a564e534ea5", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/indian_stock_hourly_2017_2021/typed/dataset_manifest.json", + "typed_manifest_sha256": "85fae742c8197d52a602af307afe9812be3573a05a565a84c86c672d4126037b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 230347 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 196 is at least 128", + "dataset_id": "job_claims", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 196.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 2, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "value": 2 + }, + "role_valid_counts": { + "value": 392 + }, + "source_bindings": { + "block_catalog_bytes": 4250, + "block_catalog_path": "/data/root/web_compression/datasets164/job_claims/typed/full/blocks.jsonl", + "block_catalog_sha256": "af3fb5cfd68c505eb44882e26d8de93b0d4cd428aae07c0bc52f924c4999134e", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/job_claims/typed/dataset_manifest.json", + "typed_manifest_sha256": "5d58409abbe8f4e69b75b96a0f89219d1232bae4c8d1061f235467c1e93c5704" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 392 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 297 is at least 128", + "dataset_id": "jolts", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 297.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 6, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 6 + }, + "role_valid_counts": { + "value": 1782 + }, + "source_bindings": { + "block_catalog_bytes": 12553, + "block_catalog_path": "/data/root/web_compression/datasets164/jolts/typed/full/blocks.jsonl", + "block_catalog_sha256": "8fc7ebf76d03bf8f54ac44b1143918a25947b7b543030d77fbf407b185174cee", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/jolts/typed/dataset_manifest.json", + "typed_manifest_sha256": "ec04f191edfa0e449111b7d9c4740215767c1416e345526592ed91634198635c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1782 + }, + { + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 802.939957122 is at least 128", + "dataset_id": "kaggle_web_traffic", + "details": { + "canonical_nan_payload_values": 7018638, + "entities": 145063, + "finite_payload_values": 109458241, + "finite_values_per_sequence_lower_bound_using_all_entities": 754.5565788657342, + "readiness_boundary": "exact source-derived scope statistic; typed production remains gated", + "rows": 116476879, + "valid_value_semantics": "typed valid_count counts every materialized non-null numeric payload, including canonical NaN bits", + "value_columns": 1 + }, + "empty_numeric_sequence_count": 0, + "input_version": "corrected_full_row_target_only_source_contract_pending_typed_ready", + "mean_valid_values_per_sequence": 802.939957122078, + "nonempty_numeric_sequence_count": 145063, + "numeric_sequence_count_including_empty": 145063, + "source_bindings": { + "contract_status": "frozen_preparation_contract", + "input_contract": { + "bytes": 1744, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/final160_dataset_format_audit_20261013_v1/remote_input_build/INPUT_CONTRACT.json", + "sha256": "c88f506e22066773e93eb2e764ace34c6df3cdc00654293724be7dde4f60f2a3" + }, + "source_tsfile_sha256": "9745aedced9468e094b4b30fb790f185226d43bad4e93385029e05a1a46dc496" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 116476879 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 114 is below 128", + "dataset_id": "kaggle_web_traffic_weekly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 114.0, + "nonempty_numeric_sequence_count": 290126, + "numeric_catalog_record_count": 290126, + "numeric_sequence_count_including_empty": 290126, + "role_record_counts": { + "additional_temporal_coordinate": 145063, + "value": 145063 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 16537182, + "value": 16537182 + }, + "source_bindings": { + "block_catalog_bytes": 669107871, + "block_catalog_path": "/data/root/web_compression/datasets164/kaggle_web_traffic_weekly/typed/full/blocks.jsonl", + "block_catalog_sha256": "08113aae0d3d59c8a5816345c6a18f93592503590c9c7e3af03e37c687f0d38f", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/kaggle_web_traffic_weekly/typed/dataset_manifest.json", + "typed_manifest_sha256": "a3f024f36d98062db4d52b6b11e403ca998ee5c1088dc84f0fddadc2cc978b94" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 33074364 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 10812.6 is at least 128", + "dataset_id": "kdd_cup_2018", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 10812.6, + "nonempty_numeric_sequence_count": 540, + "numeric_catalog_record_count": 1028, + "numeric_sequence_count_including_empty": 540, + "role_record_counts": { + "additional_temporal_coordinate": 514, + "value": 514 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 2919402, + "value": 2919402 + }, + "source_bindings": { + "block_catalog_bytes": 2263685, + "block_catalog_path": "/data/root/web_compression/datasets164/kdd_cup_2018/typed/full/blocks.jsonl", + "block_catalog_sha256": "cdf1548422d1e9be875c1e065244d39d4389b24b2426f6ed911846420a0b13ca", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/kdd_cup_2018/typed/dataset_manifest.json", + "typed_manifest_sha256": "2f456f59076b4e89c91f1a07c94263ce312d1fcaf258d75c5ac941e5078c3e28" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5838804 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 40411.1538462 is at least 128", + "dataset_id": "knowable", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 40411.153846153844, + "nonempty_numeric_sequence_count": 117, + "numeric_catalog_record_count": 624, + "numeric_sequence_count_including_empty": 117, + "role_record_counts": { + "additional_temporal_coordinate": 220, + "value": 404 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 1862538, + "value": 2865567 + }, + "source_bindings": { + "block_catalog_bytes": 1356208, + "block_catalog_path": "/data/root/web_compression/datasets164/knowable/typed/full/blocks.jsonl", + "block_catalog_sha256": "33d2a19808787b05c05cba90a1551a3e1cddb37010b2be726b648f2988ded872", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/knowable/typed/dataset_manifest.json", + "typed_manifest_sha256": "63d5b943efadf79e33fc71d317736879fe13843c36023b088e89534414791b29" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4728105 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 14805.372428 is at least 128", + "dataset_id": "kraken-trading-data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 14805.372427983539, + "nonempty_numeric_sequence_count": 486, + "numeric_catalog_record_count": 1076, + "numeric_sequence_count_including_empty": 486, + "role_record_counts": { + "value": 1076 + }, + "role_valid_counts": { + "value": 7195411 + }, + "source_bindings": { + "block_catalog_bytes": 2399789, + "block_catalog_path": "/data/root/web_compression/datasets164/kraken-trading-data/typed/full/blocks.jsonl", + "block_catalog_sha256": "c496801c8f9e62e27bb1bc8a33d1dc907c3ddf43a98a45031a413b849fb0b391", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/kraken-trading-data/typed/dataset_manifest.json", + "typed_manifest_sha256": "b5f44d990cc4cbf996a78d4f9b6fdf538ab00103dfb93c769a3fd7dd27f80b8d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 7195411 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 144 is at least 128", + "dataset_id": "kuiper_fleet_data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 144.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 5, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 5 + }, + "role_valid_counts": { + "value": 720 + }, + "source_bindings": { + "block_catalog_bytes": 10927, + "block_catalog_path": "/data/root/web_compression/datasets164/kuiper_fleet_data/typed/full/blocks.jsonl", + "block_catalog_sha256": "4b552d1128da72df477e6b157740310d775e63f4a26d3d8697f8c3c67c7ace5f", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/kuiper_fleet_data/typed/dataset_manifest.json", + "typed_manifest_sha256": "67be868f0a21f0358dd2f7a4dac238272cd13d014983352672e8d1f3df97f60e" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 720 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 5071.5158447 is at least 128", + "dataset_id": "london_smart_meters", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 5071.515844700944, + "nonempty_numeric_sequence_count": 4765, + "numeric_catalog_record_count": 5194, + "numeric_sequence_count_including_empty": 4765, + "role_record_counts": { + "value": 5194 + }, + "role_valid_counts": { + "value": 24165773 + }, + "source_bindings": { + "block_catalog_bytes": 11627193, + "block_catalog_path": "/data/root/web_compression/datasets164/london_smart_meters/typed/full/blocks.jsonl", + "block_catalog_sha256": "e7173d32ca8de9980ded1b2a3f5620fc85428a1fa0b8c91aa5d3f1da4cc866e1", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/london_smart_meters/typed/dataset_manifest.json", + "typed_manifest_sha256": "df0f0ae549c2b17a1d236b99935f145d84752104270b88b1a5be3081bfbbb4f6" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 24165773 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8541.1064257 is at least 128", + "dataset_id": "m2oe2_timeseries", + "empty_numeric_sequence_count": 6, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8541.106425702812, + "nonempty_numeric_sequence_count": 2490, + "numeric_catalog_record_count": 2516, + "numeric_sequence_count_including_empty": 2496, + "role_record_counts": { + "value": 2516 + }, + "role_valid_counts": { + "value": 21267355 + }, + "source_bindings": { + "block_catalog_bytes": 5581510, + "block_catalog_path": "/data/root/web_compression/datasets164/m2oe2_timeseries/typed/full/blocks.jsonl", + "block_catalog_sha256": "b687324e8959af7f448d5034638514371cebab6c13ca2bdb1ad56eb899f18058", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/m2oe2_timeseries/typed/dataset_manifest.json", + "typed_manifest_sha256": "ae9123d67ec21e3814228a4896d07863e4de716d28fb31fa3fb168adb34a04e8" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 21267355 + }, + { + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 33 is below 128", + "dataset_id": "magseven_ml_ready_high_frequency_anomaly", + "empty_numeric_sequence_count": 0, + "input_version": "corrected_accepted_input", + "mean_valid_values_per_sequence": 33.0, + "nonempty_numeric_sequence_count": 6, + "numeric_sequence_count_including_empty": 6, + "row_count": 36, + "source_bindings": { + "columns_csv": { + "bytes": 1295, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/mag7_float64_v2/magseven_ml_ready_high_frequency_anomaly/columns.csv", + "sha256": "6382075fcd1109b3189b0ecb0852da6fa2d21d26bf50b4f4a22a8399b85da817" + }, + "data_csv": { + "bytes": 2122, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/mag7_float64_v2/magseven_ml_ready_high_frequency_anomaly/data.csv", + "sha256": "1bd2b20c2ad74cb89bfdec5ce4fbc8d5f99b83d423a7bc7612ebb526f1f16b32" + }, + "dataset_manifest": { + "bytes": 1632, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/mag7_float64_v2/magseven_ml_ready_high_frequency_anomaly/dataset_manifest.json", + "sha256": "4d57e891319e836e65c95cc414b37b2da1def54323562f14d35a00065753ac26" + }, + "method": "local_exact_corrected_wide_csv_scan", + "series_map_csv": { + "bytes": 322, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/mag7_float64_v2/magseven_ml_ready_high_frequency_anomaly/series_map.csv", + "sha256": "4d2b0feeed3c0ea0dfbeca93e6f5bc21fb33d99652c358e533ed1e7dfeca0426" + } + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 198 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_no_admitted_scientific_numeric_payload", + "classification_reason": "no admitted scientific numeric payload; mean is undefined and is not coerced to zero", + "dataset_id": "medium_posts", + "details": { + "boundary_receipt": { + "bytes": 7744, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/min32_scope_audit_20261013_v1/evidence/medium_posts_dataset_manifest.json", + "sha256": "9ceb1dbbcc5c8708c0f63f8d7e913b56a4fe30d2aa6f70255dc334e968c90a4e" + }, + "excluded_physical_timestamp": { + "column": "published", + "dtype": "int64", + "logical_block_count": 10, + "role": "timestamp", + "valid_count": 92191 + }, + "scientific_role_boundary": { + "excluded_roles": [ + "timestamp" + ], + "included_roles": [ + "value" + ], + "timestamp_cost": "shared_metadata_charge_once_per_dataset" + } + }, + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 10, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": null, + "nonempty_numeric_sequence_count": 0, + "numeric_catalog_record_count": 0, + "numeric_sequence_count_including_empty": 0, + "role_record_counts": {}, + "role_valid_counts": {}, + "source_bindings": { + "block_catalog_bytes": 25939, + "block_catalog_path": "/data/root/web_compression/datasets164/medium_posts/typed/full/blocks.jsonl", + "block_catalog_sha256": "a0ed3e9b2b42de7240a3f0b640f95de1179deb52f08e03fb2865c272d2cbf370", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/medium_posts/typed/dataset_manifest.json", + "typed_manifest_sha256": "9ceb1dbbcc5c8708c0f63f8d7e913b56a4fe30d2aa6f70255dc334e968c90a4e" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 0 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 143710.857143 is at least 128", + "dataset_id": "meteoblue", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 15, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 143710.85714285713, + "nonempty_numeric_sequence_count": 63, + "numeric_catalog_record_count": 945, + "numeric_sequence_count_including_empty": 63, + "role_record_counts": { + "value": 945 + }, + "role_valid_counts": { + "value": 9053784 + }, + "source_bindings": { + "block_catalog_bytes": 2548002, + "block_catalog_path": "/data/root/web_compression/datasets164/meteoblue/typed/full/blocks.jsonl", + "block_catalog_sha256": "1720eede157972d8229f1a7153074d60fddc68bc8a7dbffe8d97395a6d6cc51b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/meteoblue/typed/dataset_manifest.json", + "typed_manifest_sha256": "8f55978e460c3614d40083fa1e0449c9172f275fd15f8af3191003a9c8be09b2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 9053784 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8203 is at least 128", + "dataset_id": "metropt_3", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8203.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 6, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 6 + }, + "role_valid_counts": { + "value": 49218 + }, + "source_bindings": { + "block_catalog_bytes": 12849, + "block_catalog_path": "/data/root/web_compression/datasets164/metropt_3/typed/full/blocks.jsonl", + "block_catalog_sha256": "6ed8f14badb3436c235886dbd0a65bf04b56bee5c19c1f52f400cc76a01d2d79", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/metropt_3/typed/dataset_manifest.json", + "typed_manifest_sha256": "84f0903014e4f86d20cba0ceb2993887538e0bfdd17c2ba304f66e03f3755a34" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 49218 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 3614.36363636 is at least 128", + "dataset_id": "multi_model_trading_data", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 3614.3636363636365, + "nonempty_numeric_sequence_count": 22, + "numeric_catalog_record_count": 22, + "numeric_sequence_count_including_empty": 22, + "role_record_counts": { + "value": 22 + }, + "role_valid_counts": { + "value": 79516 + }, + "source_bindings": { + "block_catalog_bytes": 49679, + "block_catalog_path": "/data/root/web_compression/datasets164/multi_model_trading_data/typed/full/blocks.jsonl", + "block_catalog_sha256": "e03dab3ed7cff124a5778d71fae6126b22d32ef4bc4439ba581d55d6a503512b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/multi_model_trading_data/typed/dataset_manifest.json", + "typed_manifest_sha256": "552e4c3288f0d8fb27008ec5454c0582717cf242dd1d5c600fb028718b5f561c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 79516 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 966 is at least 128", + "dataset_id": "national_illness", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 966.0, + "nonempty_numeric_sequence_count": 7, + "numeric_catalog_record_count": 7, + "numeric_sequence_count_including_empty": 7, + "role_record_counts": { + "value": 7 + }, + "role_valid_counts": { + "value": 6762 + }, + "source_bindings": { + "block_catalog_bytes": 15242, + "block_catalog_path": "/data/root/web_compression/datasets164/national_illness/typed/full/blocks.jsonl", + "block_catalog_sha256": "4679fc55191d4ede527e75baeabb8feac900443fbff63804802ff2a7cd982389", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/national_illness/typed/dataset_manifest.json", + "typed_manifest_sha256": "0956823b7e985e1a9acf508330f03701a3758d02f46b8b82b1c41b24e7e2a9e1" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 6762 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8764 is at least 128", + "dataset_id": "ne_china_wind", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8764.0, + "nonempty_numeric_sequence_count": 4, + "numeric_catalog_record_count": 4, + "numeric_sequence_count_including_empty": 4, + "role_record_counts": { + "value": 4 + }, + "role_valid_counts": { + "value": 35056 + }, + "source_bindings": { + "block_catalog_bytes": 8677, + "block_catalog_path": "/data/root/web_compression/datasets164/ne_china_wind/typed/full/blocks.jsonl", + "block_catalog_sha256": "be5858082465a23f97fd801e6f9af9d3946ab3bb36681a6b622a54810e22c1ed", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ne_china_wind/typed/dataset_manifest.json", + "typed_manifest_sha256": "d3b8b41efc752d0dfe844bffcf42567e3700deb7b058385e1b5dab513a2b8e26" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 35056 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 60 is below 128", + "dataset_id": "niederschlag_station_4091_bavaria_germany", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 60.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 1, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 1 + }, + "role_valid_counts": { + "value": 60 + }, + "source_bindings": { + "block_catalog_bytes": 2376, + "block_catalog_path": "/data/root/web_compression/datasets164/niederschlag_station_4091_bavaria_germany/typed/full/blocks.jsonl", + "block_catalog_sha256": "616aef8f0b72a70aad8635da48e828698389db5560c446e0dd382a1da8f34be6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/niederschlag_station_4091_bavaria_germany/typed/dataset_manifest.json", + "typed_manifest_sha256": "dc85be141a65df6aceac18b72dcd960f5f81e1118a5432e00604da6e7eb27131" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 60 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2235 is at least 128", + "dataset_id": "nifty50_market_regime", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2235.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 5, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 5 + }, + "role_valid_counts": { + "value": 11175 + }, + "source_bindings": { + "block_catalog_bytes": 11096, + "block_catalog_path": "/data/root/web_compression/datasets164/nifty50_market_regime/typed/full/blocks.jsonl", + "block_catalog_sha256": "d0888e35e6c5ca99767b1b1f28cbd9b12394d2505bd515ac59fb31c9be1f6e0c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/nifty50_market_regime/typed/dataset_manifest.json", + "typed_manifest_sha256": "aa87a0231edb37d1bd2a8f42e952839fddc6daa1de355673b7be71bf54b41440" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11175 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 791 is at least 128", + "dataset_id": "nn5_daily", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 791.0, + "nonempty_numeric_sequence_count": 222, + "numeric_catalog_record_count": 222, + "numeric_sequence_count_including_empty": 222, + "role_record_counts": { + "additional_temporal_coordinate": 111, + "value": 111 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 87801, + "value": 87801 + }, + "source_bindings": { + "block_catalog_bytes": 479481, + "block_catalog_path": "/data/root/web_compression/datasets164/nn5_daily/typed/full/blocks.jsonl", + "block_catalog_sha256": "6103f917056169a467223db68654948efa3619c6881d34710b92a8f996314e31", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/nn5_daily/typed/dataset_manifest.json", + "typed_manifest_sha256": "b7464fa88c51ad498711385a393295554c1ae6113dfb2013701e120a5a2298d8" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 175602 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 113 is below 128", + "dataset_id": "nn5_weekly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 113.0, + "nonempty_numeric_sequence_count": 222, + "numeric_catalog_record_count": 222, + "numeric_sequence_count_including_empty": 222, + "role_record_counts": { + "additional_temporal_coordinate": 111, + "value": 111 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 12543, + "value": 12543 + }, + "source_bindings": { + "block_catalog_bytes": 479726, + "block_catalog_path": "/data/root/web_compression/datasets164/nn5_weekly/typed/full/blocks.jsonl", + "block_catalog_sha256": "7e80c31ba5c88bedcfc2c43695f13ce116bc2829df89d2a418c12ea2943c7b8b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/nn5_weekly/typed/dataset_manifest.json", + "typed_manifest_sha256": "7fbd87675bfd087093114168c8f972f6217790061438aa4db98cf0357a4d98ca" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 25086 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 100057 is at least 128", + "dataset_id": "oikolab_weather", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 100057.0, + "nonempty_numeric_sequence_count": 16, + "numeric_catalog_record_count": 176, + "numeric_sequence_count_including_empty": 16, + "role_record_counts": { + "additional_temporal_coordinate": 88, + "value": 88 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 800456, + "value": 800456 + }, + "source_bindings": { + "block_catalog_bytes": 391144, + "block_catalog_path": "/data/root/web_compression/datasets164/oikolab_weather/typed/full/blocks.jsonl", + "block_catalog_sha256": "a69a010a1599dc0e5d1957083feffc76d3ffb70062e8fdb42b97067944890285", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/oikolab_weather/typed/dataset_manifest.json", + "typed_manifest_sha256": "03fe0bc681ef3d695fd320249c1ec07f20723b98dfdd30fc0a0cc4bf4860c10a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1600912 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 4776 is at least 128", + "dataset_id": "oil_price", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 4776.0, + "nonempty_numeric_sequence_count": 12, + "numeric_catalog_record_count": 12, + "numeric_sequence_count_including_empty": 12, + "role_record_counts": { + "value": 12 + }, + "role_valid_counts": { + "value": 57312 + }, + "source_bindings": { + "block_catalog_bytes": 25688, + "block_catalog_path": "/data/root/web_compression/datasets164/oil_price/typed/full/blocks.jsonl", + "block_catalog_sha256": "070e6ad80bb2fa60deac9437be0c2aef6bc61b66ee86ff9b4538dcfb1a7b9bd6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/oil_price/typed/dataset_manifest.json", + "typed_manifest_sha256": "ae0211565f78a6184a66e061c241a3d21d9515827a539efc0e79323faa1fd745" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 57312 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1183.5 is at least 128", + "dataset_id": "omie_blockchain_study", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1183.5, + "nonempty_numeric_sequence_count": 10, + "numeric_catalog_record_count": 10, + "numeric_sequence_count_including_empty": 10, + "role_record_counts": { + "value": 10 + }, + "role_valid_counts": { + "value": 11835 + }, + "source_bindings": { + "block_catalog_bytes": 22221, + "block_catalog_path": "/data/root/web_compression/datasets164/omie_blockchain_study/typed/full/blocks.jsonl", + "block_catalog_sha256": "5645fe7d72db00cee62a3f738fe5f390e73420407ba5df7e4ae8b8b74e915449", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/omie_blockchain_study/typed/dataset_manifest.json", + "typed_manifest_sha256": "6fed69651f3590666147e6d6db06e2c1bde7b453e36584655a5152f4cb9932eb" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11835 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 739 is at least 128", + "dataset_id": "online_retail_2_uci", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 739.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 1, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 1 + }, + "role_valid_counts": { + "value": 739 + }, + "source_bindings": { + "block_catalog_bytes": 2197, + "block_catalog_path": "/data/root/web_compression/datasets164/online_retail_2_uci/typed/full/blocks.jsonl", + "block_catalog_sha256": "fb730409feaa09daabce6106425aa44fd61a2b0881f5e8bc071c15952c8aeca4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/online_retail_2_uci/typed/dataset_manifest.json", + "typed_manifest_sha256": "17c99514b26eb9e5016f2b9b69ace51f3628bb010dce6ac561be7bb7193a25ac" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 739 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1547.5406564 is at least 128", + "dataset_id": "ooni_censorship_historical", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1547.540656396517, + "nonempty_numeric_sequence_count": 7465, + "numeric_catalog_record_count": 7465, + "numeric_sequence_count_including_empty": 7465, + "role_record_counts": { + "value": 7465 + }, + "role_valid_counts": { + "value": 11552391 + }, + "source_bindings": { + "block_catalog_bytes": 17171702, + "block_catalog_path": "/data/root/web_compression/datasets164/ooni_censorship_historical/typed/full/blocks.jsonl", + "block_catalog_sha256": "5738d02684270c648e95004b50d2e7218f00acef41d2d8b629ba70fc690fe0f6", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/ooni_censorship_historical/typed/dataset_manifest.json", + "typed_manifest_sha256": "6b136aa890ce0f470010498637e39e2976b0cb94b4ca13e33c0718cf3a5c9648" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 11552391 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 43488 is at least 128", + "dataset_id": "openelectricity_nem", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 43488.0, + "nonempty_numeric_sequence_count": 10, + "numeric_catalog_record_count": 50, + "numeric_sequence_count_including_empty": 10, + "role_record_counts": { + "value": 50 + }, + "role_valid_counts": { + "value": 434880 + }, + "source_bindings": { + "block_catalog_bytes": 111477, + "block_catalog_path": "/data/root/web_compression/datasets164/openelectricity_nem/typed/full/blocks.jsonl", + "block_catalog_sha256": "dd184d4a6b05958bca9808992bf45aeaf840931477a3e2e80a31debd87e2c7da", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/openelectricity_nem/typed/dataset_manifest.json", + "typed_manifest_sha256": "c74b1661e386536eeadcbd7f5a7f23292254b1e2322da7f87077586da96292df" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 434880 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1004331.74419 is at least 128", + "dataset_id": "orbital_chaos_nasa_ssc", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1004331.7441860465, + "nonempty_numeric_sequence_count": 43, + "numeric_catalog_record_count": 5324, + "numeric_sequence_count_including_empty": 43, + "role_record_counts": { + "value": 5324 + }, + "role_valid_counts": { + "value": 43186265 + }, + "source_bindings": { + "block_catalog_bytes": 11943175, + "block_catalog_path": "/data/root/web_compression/datasets164/orbital_chaos_nasa_ssc/typed/full/blocks.jsonl", + "block_catalog_sha256": "eb3265def4f9272949b8681f2611f02f96ede038c0b78a7d0ec28f5905242f81", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/orbital_chaos_nasa_ssc/typed/dataset_manifest.json", + "typed_manifest_sha256": "071375b3e720fb5402ce8a1f17d81fbf2850c8e5b7c5f0902a88d26150ddb25a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 43186265 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 47459.7878788 is at least 128", + "dataset_id": "pedestrian_counts", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 47459.78787878788, + "nonempty_numeric_sequence_count": 132, + "numeric_catalog_record_count": 698, + "numeric_sequence_count_including_empty": 132, + "role_record_counts": { + "additional_temporal_coordinate": 349, + "value": 349 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 3132346, + "value": 3132346 + }, + "source_bindings": { + "block_catalog_bytes": 1567324, + "block_catalog_path": "/data/root/web_compression/datasets164/pedestrian_counts/typed/full/blocks.jsonl", + "block_catalog_sha256": "38b5164c5985129132a0fe6446169e42aa8293cf39141c93ec703a2b9b3a6eb0", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/pedestrian_counts/typed/dataset_manifest.json", + "typed_manifest_sha256": "3daba521505bd264785d54cf4e1881dd2bbb58d0751721a65cd9120e4db45a8c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 6264692 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2058.76 is at least 128", + "dataset_id": "phenology_normal_hawaii", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2058.76, + "nonempty_numeric_sequence_count": 125, + "numeric_catalog_record_count": 125, + "numeric_sequence_count_including_empty": 125, + "role_record_counts": { + "value": 125 + }, + "role_valid_counts": { + "value": 257345 + }, + "source_bindings": { + "block_catalog_bytes": 280734, + "block_catalog_path": "/data/root/web_compression/datasets164/phenology_normal_hawaii/typed/full/blocks.jsonl", + "block_catalog_sha256": "c87d08add73979fadc285b922afc2ae19557ef4351e851cb80ab0f3fc771d117", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/phenology_normal_hawaii/typed/dataset_manifest.json", + "typed_manifest_sha256": "dc0e845d85eca420d29da38ad492e04c5ce358eb41ecdce3c8dc8d7820975a4f" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 257345 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 30271.6 is at least 128", + "dataset_id": "polymarket_crypto_5m_15m", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 30271.6, + "nonempty_numeric_sequence_count": 60, + "numeric_catalog_record_count": 1448, + "numeric_sequence_count_including_empty": 60, + "role_record_counts": { + "additional_temporal_coordinate": 12, + "value": 1436 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 53232, + "value": 1763064 + }, + "source_bindings": { + "block_catalog_bytes": 3264998, + "block_catalog_path": "/data/root/web_compression/datasets164/polymarket_crypto_5m_15m/typed/full/blocks.jsonl", + "block_catalog_sha256": "0f689d9de0cef7af1ce81cb4991ad4087c15613aa9715b88ea54767013adbd07", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/polymarket_crypto_5m_15m/typed/dataset_manifest.json", + "typed_manifest_sha256": "521c8d63e2c8708ce001306af2d2f5c490a2cbd624a32e54d2905d0454e5db8b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1816296 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1215.5 is at least 128", + "dataset_id": "port_activity", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1215.5, + "nonempty_numeric_sequence_count": 396, + "numeric_catalog_record_count": 396, + "numeric_sequence_count_including_empty": 396, + "role_record_counts": { + "value": 396 + }, + "role_valid_counts": { + "value": 481338 + }, + "source_bindings": { + "block_catalog_bytes": 862030, + "block_catalog_path": "/data/root/web_compression/datasets164/port_activity/typed/full/blocks.jsonl", + "block_catalog_sha256": "e9e38e4a1e118e23100cd1ba1a1e89b99f5412b8e90ddb7a0b8783360d2b6230", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/port_activity/typed/dataset_manifest.json", + "typed_manifest_sha256": "f11c5a5304fc8f284b9fb3a2ceeae0db07873d34df5ead80492e41ddc5fc4c29" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 481338 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 9692.12713178 is at least 128", + "dataset_id": "quitobench", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 9692.127131782945, + "nonempty_numeric_sequence_count": 6450, + "numeric_catalog_record_count": 9035, + "numeric_sequence_count_including_empty": 6450, + "role_record_counts": { + "value": 9035 + }, + "role_valid_counts": { + "value": 62514220 + }, + "source_bindings": { + "block_catalog_bytes": 19602498, + "block_catalog_path": "/data/root/web_compression/datasets164/quitobench/typed/full/blocks.jsonl", + "block_catalog_sha256": "e0a121ae9e31d1612ca46b3acc47aabc2bbb18a8755e8f35e405ff539cfa1820", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/quitobench/typed/dataset_manifest.json", + "typed_manifest_sha256": "05ab75655b0fb2fa4e7eb18dd7aa21bd65a4679d30664f8db54b19c325b93d72" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 62514220 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 20000263 is at least 128", + "dataset_id": "rating", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 2001, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 20000263.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 6003, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 6003 + }, + "role_valid_counts": { + "value": 60000789 + }, + "source_bindings": { + "block_catalog_bytes": 20395058, + "block_catalog_path": "/data/root/web_compression/datasets164/rating/typed/full/blocks.jsonl", + "block_catalog_sha256": "e3ff616c408cfbb3b41cba8a82ce0eb398932da8f90eda7d9ec7dd27b5b4f421", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/rating/typed/dataset_manifest.json", + "typed_manifest_sha256": "92c02a47510e89f8d30db7140cd331e2d043cf0e35ae6d8cd1c3c88b1e948b5f" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 60000789 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 51539.5 is at least 128", + "dataset_id": "reg_forecasting_v2", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 51539.5, + "nonempty_numeric_sequence_count": 84, + "numeric_catalog_record_count": 504, + "numeric_sequence_count_including_empty": 84, + "role_record_counts": { + "value": 504 + }, + "role_valid_counts": { + "value": 4329318 + }, + "source_bindings": { + "block_catalog_bytes": 1120437, + "block_catalog_path": "/data/root/web_compression/datasets164/reg_forecasting_v2/typed/full/blocks.jsonl", + "block_catalog_sha256": "d53e7044eb71dacb8b89f9b6254a2c33bcd92b1f37c5222d5313717796bbd6d2", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/reg_forecasting_v2/typed/dataset_manifest.json", + "typed_manifest_sha256": "ee5e4ac0156c20225096986234328cbba7ac64a9cd00b3ca57380cd6e3d0d7fd" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4329318 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 541 is at least 128", + "dataset_id": "rideshare", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 541.0, + "nonempty_numeric_sequence_count": 4608, + "numeric_catalog_record_count": 4608, + "numeric_sequence_count_including_empty": 4608, + "role_record_counts": { + "additional_temporal_coordinate": 2304, + "value": 2304 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 1246464, + "value": 1246464 + }, + "source_bindings": { + "block_catalog_bytes": 10006189, + "block_catalog_path": "/data/root/web_compression/datasets164/rideshare/typed/full/blocks.jsonl", + "block_catalog_sha256": "c7096012f8944ab0d09a6d124bc2aef61c52c11ddc48b9ebfbefec2bb4d005e9", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/rideshare/typed/dataset_manifest.json", + "typed_manifest_sha256": "c4e0af2af0327ed197c022dc5212711e99a877a8ad1ff5ef94a9a9d91205ecb9" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2492928 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 402.25 is at least 128", + "dataset_id": "salesforecastingwomartstore", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 402.25, + "nonempty_numeric_sequence_count": 1460, + "numeric_catalog_record_count": 1460, + "numeric_sequence_count_including_empty": 1460, + "role_record_counts": { + "value": 1460 + }, + "role_valid_counts": { + "value": 587285 + }, + "source_bindings": { + "block_catalog_bytes": 3336564, + "block_catalog_path": "/data/root/web_compression/datasets164/salesforecastingwomartstore/typed/full/blocks.jsonl", + "block_catalog_sha256": "99263a17161ce1d2583e74f8dac55f41a1fdd5eeed3c2341aacdc49d88042479", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/salesforecastingwomartstore/typed/dataset_manifest.json", + "typed_manifest_sha256": "9d9f1300382e019992997965908ff2f45dd0856d2f6c9d0e9868b152e53793d5" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 587285 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 23741 is at least 128", + "dataset_id": "saugeenday-monash", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 23741.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 6, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "additional_temporal_coordinate": 3, + "value": 3 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 23741, + "value": 23741 + }, + "source_bindings": { + "block_catalog_bytes": 13332, + "block_catalog_path": "/data/root/web_compression/datasets164/saugeenday-monash/typed/full/blocks.jsonl", + "block_catalog_sha256": "428f239f3a3776f4b827e17da0b9c947d3e1bd756884a54b82278ce1bd150fa3", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/saugeenday-monash/typed/dataset_manifest.json", + "typed_manifest_sha256": "7313b76d93d3921a4502adb810fabf905534799f10c38909ed9f80837580797c" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 47482 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 300 is at least 128", + "dataset_id": "scaphandre_cpu_usage", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 300.0, + "nonempty_numeric_sequence_count": 1, + "numeric_catalog_record_count": 1, + "numeric_sequence_count_including_empty": 1, + "role_record_counts": { + "value": 1 + }, + "role_valid_counts": { + "value": 300 + }, + "source_bindings": { + "block_catalog_bytes": 2203, + "block_catalog_path": "/data/root/web_compression/datasets164/scaphandre_cpu_usage/typed/full/blocks.jsonl", + "block_catalog_sha256": "004ec8149158c6e60c25e4fb085b30505f67a55076c35bcf68fd9b6717a0db3a", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/scaphandre_cpu_usage/typed/dataset_manifest.json", + "typed_manifest_sha256": "80b2dd706ed7ca39228a321bf54a2ab0ecf1eb0d2270d9fbf009646696dced0d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 300 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 14332 is at least 128", + "dataset_id": "sg_carpark", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 14332.0, + "nonempty_numeric_sequence_count": 354, + "numeric_catalog_record_count": 708, + "numeric_sequence_count_including_empty": 354, + "role_record_counts": { + "value": 708 + }, + "role_valid_counts": { + "value": 5073528 + }, + "source_bindings": { + "block_catalog_bytes": 1533797, + "block_catalog_path": "/data/root/web_compression/datasets164/sg_carpark/typed/full/blocks.jsonl", + "block_catalog_sha256": "25cd19b5256ba02c1e54ed2af55f122c3153104a6298522dabe78788db31b2aa", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/sg_carpark/typed/dataset_manifest.json", + "typed_manifest_sha256": "fe41509fcf0b4445005673dfa892381652a14417ed9691912ae965bc5917c9dd" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5073528 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 37357.4 is at least 128", + "dataset_id": "sg_pm25", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 37357.4, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 20, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 20 + }, + "role_valid_counts": { + "value": 186787 + }, + "source_bindings": { + "block_catalog_bytes": 42643, + "block_catalog_path": "/data/root/web_compression/datasets164/sg_pm25/typed/full/blocks.jsonl", + "block_catalog_sha256": "c520b445df615f8f601f2159fbb4223fd7d6543097c02bbd34735492d41130c4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/sg_pm25/typed/dataset_manifest.json", + "typed_manifest_sha256": "5934c4b8ca9500ad93e84011bd47ff541d095c774e5be21a75e6a316c2512fb2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 186787 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2805.16666667 is at least 128", + "dataset_id": "sg_weather", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2805.1666666666665, + "nonempty_numeric_sequence_count": 24, + "numeric_catalog_record_count": 24, + "numeric_sequence_count_including_empty": 24, + "role_record_counts": { + "value": 24 + }, + "role_valid_counts": { + "value": 67324 + }, + "source_bindings": { + "block_catalog_bytes": 51609, + "block_catalog_path": "/data/root/web_compression/datasets164/sg_weather/typed/full/blocks.jsonl", + "block_catalog_sha256": "e78d23786658e533c6591ac90ac925f239fe7961b2ff92e114917ccd107b650b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/sg_weather/typed/dataset_manifest.json", + "typed_manifest_sha256": "146fd3c899f40f59c612d593a452c78f666298de4e85664f6d34af5eb2871f13" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 67324 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 291 is at least 128", + "dataset_id": "sleep_score_fitbit", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 291.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 5, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 5 + }, + "role_valid_counts": { + "value": 1455 + }, + "source_bindings": { + "block_catalog_bytes": 10979, + "block_catalog_path": "/data/root/web_compression/datasets164/sleep_score_fitbit/typed/full/blocks.jsonl", + "block_catalog_sha256": "f4baea619eba5bed39a10933fffa4d207449ff4d7bda1e5cb09b7ec6aec31a8e", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/sleep_score_fitbit/typed/dataset_manifest.json", + "typed_manifest_sha256": "c96b9f6d083d6e0027ccde078cb1ec813d8e8adf701917f9c89037edd1cac554" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1455 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 52560 is at least 128", + "dataset_id": "solar_10_minutes", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 52560.0, + "nonempty_numeric_sequence_count": 274, + "numeric_catalog_record_count": 1644, + "numeric_sequence_count_including_empty": 274, + "role_record_counts": { + "additional_temporal_coordinate": 822, + "value": 822 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 7200720, + "value": 7200720 + }, + "source_bindings": { + "block_catalog_bytes": 3681591, + "block_catalog_path": "/data/root/web_compression/datasets164/solar_10_minutes/typed/full/blocks.jsonl", + "block_catalog_sha256": "231f5da695d31f36560571e88a4f4aae2f64e7978322cef58a66d7bae196ec03", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/solar_10_minutes/typed/dataset_manifest.json", + "typed_manifest_sha256": "09e3d8b002ab22956536bcf867db9bd8adc59118e787e2b2528a9390e65704e2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 14401440 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7397222 is at least 128", + "dataset_id": "solar_4_seconds", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7397222.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 1480, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "additional_temporal_coordinate": 740, + "value": 740 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 7397222, + "value": 7397222 + }, + "source_bindings": { + "block_catalog_bytes": 3303235, + "block_catalog_path": "/data/root/web_compression/datasets164/solar_4_seconds/typed/full/blocks.jsonl", + "block_catalog_sha256": "4181b02c4b1e68cfec2f1d6f2f77843211eb8ca73a9c6f643e488a95344d2634", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/solar_4_seconds/typed/dataset_manifest.json", + "typed_manifest_sha256": "7eab90d48102d5075b3f31cf9b08050e007fc70b64f4613c4addf876b4246214" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 14794444 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 52 is below 128", + "dataset_id": "solar_weekly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 52.0, + "nonempty_numeric_sequence_count": 274, + "numeric_catalog_record_count": 274, + "numeric_sequence_count_including_empty": 274, + "role_record_counts": { + "additional_temporal_coordinate": 137, + "value": 137 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 7124, + "value": 7124 + }, + "source_bindings": { + "block_catalog_bytes": 595087, + "block_catalog_path": "/data/root/web_compression/datasets164/solar_weekly/typed/full/blocks.jsonl", + "block_catalog_sha256": "24dd43bad6668d50137e196e8e7e9749522f43b399566fab2b013b31df195e13", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/solar_weekly/typed/dataset_manifest.json", + "typed_manifest_sha256": "cac9980160d9b29b606ba108e756240a6d512ebd9d8b115e4df68240f1e9e87a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 14248 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 259200 is at least 128", + "dataset_id": "solusdt_enhanced_180", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 259200.0, + "nonempty_numeric_sequence_count": 9, + "numeric_catalog_record_count": 234, + "numeric_sequence_count_including_empty": 9, + "role_record_counts": { + "value": 234 + }, + "role_valid_counts": { + "value": 2332800 + }, + "source_bindings": { + "block_catalog_bytes": 521133, + "block_catalog_path": "/data/root/web_compression/datasets164/solusdt_enhanced_180/typed/full/blocks.jsonl", + "block_catalog_sha256": "f1c15abe1354044f805c1f2e38f34ff01cb455c1f5160762b611f30af1dfc17b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/solusdt_enhanced_180/typed/dataset_manifest.json", + "typed_manifest_sha256": "932e0b200a4eaa5a8c896cbffb8b46daaf6d379b634551165650680b06f3fec4" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2332800 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 24167 is at least 128", + "dataset_id": "spx", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 24167.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 18, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 18 + }, + "role_valid_counts": { + "value": 145002 + }, + "source_bindings": { + "block_catalog_bytes": 37597, + "block_catalog_path": "/data/root/web_compression/datasets164/spx/typed/full/blocks.jsonl", + "block_catalog_sha256": "0f09da192f6032972313f8b8489e22f41a7aed35ba97050e94af8e9c5ccdb985", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/spx/typed/dataset_manifest.json", + "typed_manifest_sha256": "ebdc787fbd54c8f547655d6bd00e56862644c724f767468ed169d6d28d9a6ef1" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 145002 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1232.79324056 is at least 128", + "dataset_id": "stock_dataset", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1232.79324055666, + "nonempty_numeric_sequence_count": 35713, + "numeric_catalog_record_count": 35713, + "numeric_sequence_count_including_empty": 35713, + "role_record_counts": { + "value": 35713 + }, + "role_valid_counts": { + "value": 44026745 + }, + "source_bindings": { + "block_catalog_bytes": 77922668, + "block_catalog_path": "/data/root/web_compression/datasets164/stock_dataset/typed/full/blocks.jsonl", + "block_catalog_sha256": "7f29026f65f8c693378041b2f3c17007f958d0191adbb336d714c47f093ec63b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/stock_dataset/typed/dataset_manifest.json", + "typed_manifest_sha256": "636935c32cea803c9073e886e97e89970e051bdf3df1b50b2d53d8bbfbf263f6" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 44026745 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 51336.4 is at least 128", + "dataset_id": "substorm_onsets", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 51336.4, + "nonempty_numeric_sequence_count": 20, + "numeric_catalog_record_count": 116, + "numeric_sequence_count_including_empty": 20, + "role_record_counts": { + "value": 116 + }, + "role_valid_counts": { + "value": 1026728 + }, + "source_bindings": { + "block_catalog_bytes": 256013, + "block_catalog_path": "/data/root/web_compression/datasets164/substorm_onsets/typed/full/blocks.jsonl", + "block_catalog_sha256": "f10c5eb8f25be6e6d2384e74683daaa6a3235cdbf85447a42060797688846989", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/substorm_onsets/typed/dataset_manifest.json", + "typed_manifest_sha256": "03a70a0baeb724c8974feddc09fe4d6346f2cdee044b2a9458e3518d81b3f695" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1026728 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 73924 is at least 128", + "dataset_id": "sunspot", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 73924.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 16, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "additional_temporal_coordinate": 8, + "value": 8 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 73924, + "value": 73924 + }, + "source_bindings": { + "block_catalog_bytes": 34445, + "block_catalog_path": "/data/root/web_compression/datasets164/sunspot/typed/full/blocks.jsonl", + "block_catalog_sha256": "525ea863945f1cc52d7f06389c1919dece5c9ca02fd66dc6a2c51e68fad8656b", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/sunspot/typed/dataset_manifest.json", + "typed_manifest_sha256": "a4781558ab847104866d9aefa2588327b50bc85c880569959b2c37286c4888e4" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 147848 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 727.470588235 is at least 128", + "dataset_id": "telangana_weather", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 727.4705882352941, + "nonempty_numeric_sequence_count": 4284, + "numeric_catalog_record_count": 4284, + "numeric_sequence_count_including_empty": 4284, + "role_record_counts": { + "value": 4284 + }, + "role_valid_counts": { + "value": 3116484 + }, + "source_bindings": { + "block_catalog_bytes": 9469052, + "block_catalog_path": "/data/root/web_compression/datasets164/telangana_weather/typed/full/blocks.jsonl", + "block_catalog_sha256": "541af17cbf6b3e57418c99cb7a9407c37c9a77cf5056911dcc5391bb711c88b3", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/telangana_weather/typed/dataset_manifest.json", + "typed_manifest_sha256": "f6860a663e086c1eb86d514d334d5f361d88b5237417f284ab555f7c4b9e15fd" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 3116484 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 724.998939885 is at least 128", + "dataset_id": "temperature_rain", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 724.9989398852582, + "nonempty_numeric_sequence_count": 32072, + "numeric_catalog_record_count": 32072, + "numeric_sequence_count_including_empty": 32072, + "role_record_counts": { + "value": 32072 + }, + "role_valid_counts": { + "value": 23252166 + }, + "source_bindings": { + "block_catalog_bytes": 70787122, + "block_catalog_path": "/data/root/web_compression/datasets164/temperature_rain/typed/full/blocks.jsonl", + "block_catalog_sha256": "35e2be01d4658f1212fac01310c715ee38ae3d5cb61d53982a341afd150ed5c4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/temperature_rain/typed/dataset_manifest.json", + "typed_manifest_sha256": "071ba47790facc2e507d46e7dfee43cd9e972ccba65ad9cd2e674857ac299482" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 23252166 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 1802050 is at least 128", + "dataset_id": "timeseries-1m-QQQ-10y", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 1802050.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 905, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 905 + }, + "role_valid_counts": { + "value": 9010250 + }, + "source_bindings": { + "block_catalog_bytes": 2019096, + "block_catalog_path": "/data/root/web_compression/datasets164/timeseries-1m-QQQ-10y/typed/full/blocks.jsonl", + "block_catalog_sha256": "d04d19f90ab158efc67d56f69210fc582a5c6ac7c1659cb66ae3aa491ca5084c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/timeseries-1m-QQQ-10y/typed/dataset_manifest.json", + "typed_manifest_sha256": "f4479bdda91f79b15c5876cdbffab03c81796d6b93ab0ba5cce8e7555edb2c00" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 9010250 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 57.4972998805 is below 128", + "dataset_id": "timeseries-finance-ETF", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 57.49729988052569, + "nonempty_numeric_sequence_count": 83700, + "numeric_catalog_record_count": 83700, + "numeric_sequence_count_including_empty": 83700, + "role_record_counts": { + "value": 83700 + }, + "role_valid_counts": { + "value": 4812524 + }, + "source_bindings": { + "block_catalog_bytes": 188084769, + "block_catalog_path": "/data/root/web_compression/datasets164/timeseries-finance-ETF/typed/full/blocks.jsonl", + "block_catalog_sha256": "dd19a10edf0d6f4f5825caaf137b0f7c48453d2eb5e6f9825c87fecfaf04cd83", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/timeseries-finance-ETF/typed/dataset_manifest.json", + "typed_manifest_sha256": "e61a1c59855ddb5847b6ec292d1c9c7bec6163bc2470ea976f17bf9d3df437bc" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4812524 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 712.03777336 is at least 128", + "dataset_id": "timeseries_1mn_sp500", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 712.0377733598409, + "nonempty_numeric_sequence_count": 2515, + "numeric_catalog_record_count": 2515, + "numeric_sequence_count_including_empty": 2515, + "role_record_counts": { + "value": 2515 + }, + "role_valid_counts": { + "value": 1790775 + }, + "source_bindings": { + "block_catalog_bytes": 5569725, + "block_catalog_path": "/data/root/web_compression/datasets164/timeseries_1mn_sp500/typed/full/blocks.jsonl", + "block_catalog_sha256": "01af652814b43a1edaa4ba50a8126b769bc7b1cb79a4d704fc3b39a5a30bf33d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/timeseries_1mn_sp500/typed/dataset_manifest.json", + "typed_manifest_sha256": "dd4e86f3c4e1dbcfdf1a13fe53fdab3144b7b093289d985f5a45533817e90419" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1790775 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 251.7888 is at least 128", + "dataset_id": "timeseries_1mn_stocks", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 251.7888, + "nonempty_numeric_sequence_count": 7500, + "numeric_catalog_record_count": 7500, + "numeric_sequence_count_including_empty": 7500, + "role_record_counts": { + "value": 7500 + }, + "role_valid_counts": { + "value": 1888416 + }, + "source_bindings": { + "block_catalog_bytes": 16768387, + "block_catalog_path": "/data/root/web_compression/datasets164/timeseries_1mn_stocks/typed/full/blocks.jsonl", + "block_catalog_sha256": "34d10f318a384f066f5747c2bbf8ed127af38e97515991bdbf498939dc788ae9", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/timeseries_1mn_stocks/typed/dataset_manifest.json", + "typed_manifest_sha256": "f00b9b9cb758d5b82c226c08f8b6845f54320e4d4c4a45d7625c387a631eeaae" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1888416 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 57.4972998805 is below 128", + "dataset_id": "timeseries_finance_etf_missing", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 57.49729988052569, + "nonempty_numeric_sequence_count": 83700, + "numeric_catalog_record_count": 83700, + "numeric_sequence_count_including_empty": 83700, + "role_record_counts": { + "value": 83700 + }, + "role_valid_counts": { + "value": 4812524 + }, + "source_bindings": { + "block_catalog_bytes": 193441569, + "block_catalog_path": "/data/root/web_compression/datasets164/timeseries_finance_etf_missing/typed/full/blocks.jsonl", + "block_catalog_sha256": "bccf15a09e4a505d1a3658eac93fa5bf5e93c181c3c88dc06f63528c89c8c198", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/timeseries_finance_etf_missing/typed/dataset_manifest.json", + "typed_manifest_sha256": "02a97e0106ab3fc55ee0b384a6f5594c8097d5c61c531dc5d2258a5c74667503" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4812524 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 298.579234973 is at least 128", + "dataset_id": "tourism_monthly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 298.57923497267757, + "nonempty_numeric_sequence_count": 732, + "numeric_catalog_record_count": 732, + "numeric_sequence_count_including_empty": 732, + "role_record_counts": { + "additional_temporal_coordinate": 366, + "value": 366 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 109280, + "value": 109280 + }, + "source_bindings": { + "block_catalog_bytes": 1619050, + "block_catalog_path": "/data/root/web_compression/datasets164/tourism_monthly/typed/full/blocks.jsonl", + "block_catalog_sha256": "0152c140979727db3e74d5eed770430b9ccd98e9fd70a9c3055d53dbf4dfbcd2", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/tourism_monthly/typed/dataset_manifest.json", + "typed_manifest_sha256": "6ad1b34e864f9cac776ef348a0a56ed78a0f7ec0f50133ba365532e7de3da685" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 218560 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 227.348684211 is at least 128", + "dataset_id": "tourism_monthly-zaai-ai", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 227.34868421052633, + "nonempty_numeric_sequence_count": 1520, + "numeric_catalog_record_count": 1520, + "numeric_sequence_count_including_empty": 1520, + "role_record_counts": { + "value": 1520 + }, + "role_valid_counts": { + "value": 345570 + }, + "source_bindings": { + "block_catalog_bytes": 3402918, + "block_catalog_path": "/data/root/web_compression/datasets164/tourism_monthly-zaai-ai/typed/full/blocks.jsonl", + "block_catalog_sha256": "52600d11f3f669799ad0d3694710a4cc68504889977080bfa8ff0b32b5c7a9f7", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/tourism_monthly-zaai-ai/typed/dataset_manifest.json", + "typed_manifest_sha256": "5bcc1ec4ff71e50a772ac558d85d3d085c7cad6376063c6f9c4b3edf1bbf6ca9" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 345570 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 99.6346604215 is below 128", + "dataset_id": "tourism_quarterly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 99.63466042154566, + "nonempty_numeric_sequence_count": 854, + "numeric_catalog_record_count": 854, + "numeric_sequence_count_including_empty": 854, + "role_record_counts": { + "additional_temporal_coordinate": 427, + "value": 427 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 42544, + "value": 42544 + }, + "source_bindings": { + "block_catalog_bytes": 1896652, + "block_catalog_path": "/data/root/web_compression/datasets164/tourism_quarterly/typed/full/blocks.jsonl", + "block_catalog_sha256": "c6a22e4277933d7fc9cb19909dda84f1da108e192f011d32143fabb0f40a1495", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/tourism_quarterly/typed/dataset_manifest.json", + "typed_manifest_sha256": "7546af1d7f49ee5480d791cb942351a4a50ac6ac644dd770a1374afd6aa42cbf" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 85088 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 170 is at least 128", + "dataset_id": "tourism_residuals", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 170.0, + "nonempty_numeric_sequence_count": 1216, + "numeric_catalog_record_count": 1216, + "numeric_sequence_count_including_empty": 1216, + "role_record_counts": { + "value": 1216 + }, + "role_valid_counts": { + "value": 206720 + }, + "source_bindings": { + "block_catalog_bytes": 2673450, + "block_catalog_path": "/data/root/web_compression/datasets164/tourism_residuals/typed/full/blocks.jsonl", + "block_catalog_sha256": "e44969a3d950f776d0b33618a7bf726e8a744fa48bde2c5562d2cea76fedd1c0", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/tourism_residuals/typed/dataset_manifest.json", + "typed_manifest_sha256": "7035fed33bb3296ac58d5beee8adb22a09459b7acfc2c1fb3a5fc9ffe3302990" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 206720 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 24.6274131274 is below 128", + "dataset_id": "tourism_yearly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 24.627413127413128, + "nonempty_numeric_sequence_count": 1036, + "numeric_catalog_record_count": 1036, + "numeric_sequence_count_including_empty": 1036, + "role_record_counts": { + "additional_temporal_coordinate": 518, + "value": 518 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 12757, + "value": 12757 + }, + "source_bindings": { + "block_catalog_bytes": 2271148, + "block_catalog_path": "/data/root/web_compression/datasets164/tourism_yearly/typed/full/blocks.jsonl", + "block_catalog_sha256": "c20cdff15822ba6809d02fcfb1e0d3cffc9bb5d6eb3b05c618cf1f7f3a7a76a4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/tourism_yearly/typed/dataset_manifest.json", + "typed_manifest_sha256": "8a9f17a8b9437b4c186ddb3a8355c76f330ed2c451385cf00d4364fd9199d55d" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 25514 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 17544 is at least 128", + "dataset_id": "traffic", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 17544.0, + "nonempty_numeric_sequence_count": 862, + "numeric_catalog_record_count": 1724, + "numeric_sequence_count_including_empty": 862, + "role_record_counts": { + "value": 1724 + }, + "role_valid_counts": { + "value": 15122928 + }, + "source_bindings": { + "block_catalog_bytes": 3658421, + "block_catalog_path": "/data/root/web_compression/datasets164/traffic/typed/full/blocks.jsonl", + "block_catalog_sha256": "25ab7174598b02fb0c85eb4e1ae30e9876d09c4305221dddc0f844974099a581", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/traffic/typed/dataset_manifest.json", + "typed_manifest_sha256": "b49e01b5f88ea2626babde1c9cb6671712c7b076f7ad0a69b4d25523f7e509ec" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 15122928 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 17544 is at least 128", + "dataset_id": "traffic_hourly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 17544.0, + "nonempty_numeric_sequence_count": 1724, + "numeric_catalog_record_count": 3448, + "numeric_sequence_count_including_empty": 1724, + "role_record_counts": { + "additional_temporal_coordinate": 1724, + "value": 1724 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 15122928, + "value": 15122928 + }, + "source_bindings": { + "block_catalog_bytes": 7672006, + "block_catalog_path": "/data/root/web_compression/datasets164/traffic_hourly/typed/full/blocks.jsonl", + "block_catalog_sha256": "71372a9d3b957c308414c12351ed0e6dd1eda056d6607ae698be55b27af1f742", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/traffic_hourly/typed/dataset_manifest.json", + "typed_manifest_sha256": "90da72725c4a5763f53bcf0bcd86b743fce66ec04e5a669a9b13b43c88a6e49a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 30245856 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 104 is below 128", + "dataset_id": "traffic_weekly", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 104.0, + "nonempty_numeric_sequence_count": 1724, + "numeric_catalog_record_count": 1724, + "numeric_sequence_count_including_empty": 1724, + "role_record_counts": { + "additional_temporal_coordinate": 862, + "value": 862 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 89648, + "value": 89648 + }, + "source_bindings": { + "block_catalog_bytes": 3790280, + "block_catalog_path": "/data/root/web_compression/datasets164/traffic_weekly/typed/full/blocks.jsonl", + "block_catalog_sha256": "4aa6a797240415e2b47b9ced3ecb64d31d643c5f72bb2d97fc92500b02f63e54", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/traffic_weekly/typed/dataset_manifest.json", + "typed_manifest_sha256": "9ba985cbc9ca1ead89e8c0ee0a533bd8517c596d0a872b467b3990f73a281440" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 179296 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 4.89552238806 is below 128", + "dataset_id": "traqq_weekly_activity", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_correct_source_semantics_unchanged_typed_input", + "mean_valid_values_per_sequence": 4.895522388059701, + "nonempty_numeric_sequence_count": 335, + "numeric_catalog_record_count": 335, + "numeric_sequence_count_including_empty": 335, + "role_record_counts": { + "value": 335 + }, + "role_valid_counts": { + "value": 1640 + }, + "source_bindings": { + "block_catalog_bytes": 740698, + "block_catalog_path": "/data/root/web_compression/datasets164/traqq_weekly_activity/typed/full/blocks.jsonl", + "block_catalog_sha256": "2e35d39cbe95790c6473a49f272792e2828f623533117b12f91d9b1b5c223b61", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/traqq_weekly_activity/typed/dataset_manifest.json", + "typed_manifest_sha256": "7e9b85464124cdecd8b19b0a7c6fe59632b6856e8dd3ea340add0fb9794ba1cd" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 1640 + }, + { + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 5.7372982158 is below 128", + "dataset_id": "trending_stocks_yahoo_finance", + "empty_numeric_sequence_count": 1121, + "input_version": "corrected_accepted_input", + "mean_valid_values_per_sequence": 5.7372982158028885, + "nonempty_numeric_sequence_count": 17655, + "numeric_sequence_count_including_empty": 18776, + "row_count": 13386, + "source_bindings": { + "columns_csv": { + "bytes": 1227, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/trending_stocks_yahoo_finance/columns.csv", + "sha256": "df6236a75d3eb6f67efe9dcda7d1186b06d5d915cd7c70ea65d06750c1ca2489" + }, + "data_csv": { + "bytes": 1073819, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/trending_stocks_yahoo_finance/data.csv", + "sha256": "fd8de8b6166d6875f5bb961d423e34bb438460625c884a5c2ddc6784efea4637" + }, + "dataset_manifest": { + "bytes": 1507, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/trending_stocks_yahoo_finance/dataset_manifest.json", + "sha256": "79349da2c5a892dc988104b7ea56ee2bbc5a7128919c2caee7228107d1fc0eb6" + }, + "method": "local_exact_corrected_wide_csv_scan", + "series_map_csv": { + "bytes": 252602, + "path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/six_dataset_numeric_repair_20261012_v1/yahoo_github/output_v2/trending_stocks_yahoo_finance/series_map.csv", + "sha256": "e29ecee1ceaf947b33be5c1d143eb12e17c540f47cea39a88a2fba63423f4ee4" + } + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 101292 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2541210 is at least 128", + "dataset_id": "trxusdt_spot_1m_05_2021_to_03_2026", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2541210.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 1275, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 1275 + }, + "role_valid_counts": { + "value": 12706050 + }, + "source_bindings": { + "block_catalog_bytes": 2998902, + "block_catalog_path": "/data/root/web_compression/datasets164/trxusdt_spot_1m_05_2021_to_03_2026/typed/full/blocks.jsonl", + "block_catalog_sha256": "4f89bbcb80189f33bd23ce7badff7f537207f1cff09f9d3d2a870cf4fe7de639", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/trxusdt_spot_1m_05_2021_to_03_2026/typed/dataset_manifest.json", + "typed_manifest_sha256": "f18d93e87506874c981605fe557f9f637cabc4bdf5f14ef4431d1bfbae9308d1" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 12706050 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 126476 is at least 128", + "dataset_id": "uk_electricity_generation_mix_2019_2026", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 126476.0, + "nonempty_numeric_sequence_count": 33, + "numeric_catalog_record_count": 429, + "numeric_sequence_count_including_empty": 33, + "role_record_counts": { + "value": 429 + }, + "role_valid_counts": { + "value": 4173708 + }, + "source_bindings": { + "block_catalog_bytes": 1020785, + "block_catalog_path": "/data/root/web_compression/datasets164/uk_electricity_generation_mix_2019_2026/typed/full/blocks.jsonl", + "block_catalog_sha256": "26643bd58ef283d8e0ca6028e5b1e2b1e3453ba7dce766544c471cab3d322c7c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/uk_electricity_generation_mix_2019_2026/typed/dataset_manifest.json", + "typed_manifest_sha256": "319001514efed34609b7796d07dee9dafee754c7023296b42536f15c31353177" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4173708 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 780 is at least 128", + "dataset_id": "uncertainty_1m", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 780.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 3, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 3 + }, + "role_valid_counts": { + "value": 2340 + }, + "source_bindings": { + "block_catalog_bytes": 6490, + "block_catalog_path": "/data/root/web_compression/datasets164/uncertainty_1m/typed/full/blocks.jsonl", + "block_catalog_sha256": "d1acf5d2ddfbe193187ca95aa52b22a66c0ba1fd6ed94c9345b6eb08a40c6d5a", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/uncertainty_1m/typed/dataset_manifest.json", + "typed_manifest_sha256": "88451deda3b404f8946c888bfa0612d17d63dfd344093f5b1cb6aab7cb64c622" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2340 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7305 is at least 128", + "dataset_id": "us_births-monash", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7305.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 2, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "additional_temporal_coordinate": 1, + "value": 1 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 7305, + "value": 7305 + }, + "source_bindings": { + "block_catalog_bytes": 4403, + "block_catalog_path": "/data/root/web_compression/datasets164/us_births-monash/typed/full/blocks.jsonl", + "block_catalog_sha256": "0305d73ca5025b6fe59603a6597758813a36993609ff908566f18deb5c04595d", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/us_births-monash/typed/dataset_manifest.json", + "typed_manifest_sha256": "1cacc1afe26b871f010164b1dbace1b9c2a39c3e2475d89a5479f07babd3dda4" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 14610 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 380 is at least 128", + "dataset_id": "us_labor", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 380.0, + "nonempty_numeric_sequence_count": 14, + "numeric_catalog_record_count": 14, + "numeric_sequence_count_including_empty": 14, + "role_record_counts": { + "value": 14 + }, + "role_valid_counts": { + "value": 5320 + }, + "source_bindings": { + "block_catalog_bytes": 29669, + "block_catalog_path": "/data/root/web_compression/datasets164/us_labor/typed/full/blocks.jsonl", + "block_catalog_sha256": "b0b326807ad4ef0f85df5052b54cd1901173e69f75655fda165952670ec881ab", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/us_labor/typed/dataset_manifest.json", + "typed_manifest_sha256": "c6afdea55892ea1d555b5b854547cd7ef0748bed4f8fa4d551410ea013623866" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5320 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 9.89634692963 is below 128", + "dataset_id": "us_stock_financial_ratios", + "empty_numeric_sequence_count": 319, + "excluded_catalog_record_count": 0, + "input_version": "published_correct_source_semantics_unchanged_typed_input", + "mean_valid_values_per_sequence": 9.896346929627969, + "nonempty_numeric_sequence_count": 8924, + "numeric_catalog_record_count": 9243, + "numeric_sequence_count_including_empty": 9243, + "role_record_counts": { + "value": 9243 + }, + "role_valid_counts": { + "value": 88315 + }, + "source_bindings": { + "block_catalog_bytes": 20865599, + "block_catalog_path": "/data/root/web_compression/datasets164/us_stock_financial_ratios/typed/full/blocks.jsonl", + "block_catalog_sha256": "04e12b341f09d4aae337077377cd4c17e7922a8a259a5465699385f101add238", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/us_stock_financial_ratios/typed/dataset_manifest.json", + "typed_manifest_sha256": "8d2625899f1ce97ae2a1d9c4c2b82132948a31bd7803bca2818d250483812c04" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 88315 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 8923 is at least 128", + "dataset_id": "us_term_structure", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 8923.0, + "nonempty_numeric_sequence_count": 40, + "numeric_catalog_record_count": 40, + "numeric_sequence_count_including_empty": 40, + "role_record_counts": { + "value": 40 + }, + "role_valid_counts": { + "value": 356920 + }, + "source_bindings": { + "block_catalog_bytes": 88486, + "block_catalog_path": "/data/root/web_compression/datasets164/us_term_structure/typed/full/blocks.jsonl", + "block_catalog_sha256": "e0ea3a6a1bddc2e495453e271894f654fade2a51a25c7376abd2ea2abf86b1f3", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/us_term_structure/typed/dataset_manifest.json", + "typed_manifest_sha256": "1240608121648812e115e5624402113860ddbc88900b8466c0042ebdaecfbf44" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 356920 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 596 is at least 128", + "dataset_id": "vehicle_sales", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 596.0, + "nonempty_numeric_sequence_count": 10, + "numeric_catalog_record_count": 10, + "numeric_sequence_count_including_empty": 10, + "role_record_counts": { + "value": 10 + }, + "role_valid_counts": { + "value": 5960 + }, + "source_bindings": { + "block_catalog_bytes": 21582, + "block_catalog_path": "/data/root/web_compression/datasets164/vehicle_sales/typed/full/blocks.jsonl", + "block_catalog_sha256": "69b72dc99a14e36771aa7e960fa57ab9884e80e8ebc93c67b232d965b0d304d5", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/vehicle_sales/typed/dataset_manifest.json", + "typed_manifest_sha256": "ae52c9fea0c375526337e686d8b8524d4efc418638ce24aa6b4fa86ee803d97a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 5960 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 391 is at least 128", + "dataset_id": "vehicle_supply", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 391.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 6, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 6 + }, + "role_valid_counts": { + "value": 2346 + }, + "source_bindings": { + "block_catalog_bytes": 12986, + "block_catalog_path": "/data/root/web_compression/datasets164/vehicle_supply/typed/full/blocks.jsonl", + "block_catalog_sha256": "979468cc3961607780102ee38b0127ac44b67027cedaa5c5a75df2d56ffbd917", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/vehicle_supply/typed/dataset_manifest.json", + "typed_manifest_sha256": "731e325f9d09841741e48030e4de7c53c60441815093bbaa7db89a89f2af5aa6" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 2346 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 128.820668693 is at least 128", + "dataset_id": "vehicle_trips", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 128.8206686930091, + "nonempty_numeric_sequence_count": 658, + "numeric_catalog_record_count": 658, + "numeric_sequence_count_including_empty": 658, + "role_record_counts": { + "additional_temporal_coordinate": 329, + "value": 329 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 42382, + "value": 42382 + }, + "source_bindings": { + "block_catalog_bytes": 1440898, + "block_catalog_path": "/data/root/web_compression/datasets164/vehicle_trips/typed/full/blocks.jsonl", + "block_catalog_sha256": "5be6a6f1235e0caedad53d45af2622a6c2f65481e440c2dca0b2b26e10b61ee0", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/vehicle_trips/typed/dataset_manifest.json", + "typed_manifest_sha256": "b13727bcd7731d70c2b9c1c038265520903bc89d0a322860e2482e542c0978cb" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 84764 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 15229 is at least 128", + "dataset_id": "water_quality_darwin", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 15229.0, + "nonempty_numeric_sequence_count": 42, + "numeric_catalog_record_count": 78, + "numeric_sequence_count_including_empty": 42, + "role_record_counts": { + "value": 78 + }, + "role_valid_counts": { + "value": 639618 + }, + "source_bindings": { + "block_catalog_bytes": 174645, + "block_catalog_path": "/data/root/web_compression/datasets164/water_quality_darwin/typed/full/blocks.jsonl", + "block_catalog_sha256": "32700243afc590b6de43a1174f6a572cfc7dcf0b73d1bcc9d05d372cf10e7d45", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/water_quality_darwin/typed/dataset_manifest.json", + "typed_manifest_sha256": "0473fd075df08e9a4f637a4d336b9777d1ef9a192315dd0246793962b813b28e" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 639618 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2352.92661012 is at least 128", + "dataset_id": "weather_data_bavaria", + "empty_numeric_sequence_count": 5584, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2352.926610120759, + "nonempty_numeric_sequence_count": 27824, + "numeric_catalog_record_count": 33444, + "numeric_sequence_count_including_empty": 33408, + "role_record_counts": { + "value": 33444 + }, + "role_valid_counts": { + "value": 65467830 + }, + "source_bindings": { + "block_catalog_bytes": 75239497, + "block_catalog_path": "/data/root/web_compression/datasets164/weather_data_bavaria/typed/full/blocks.jsonl", + "block_catalog_sha256": "ceb5897e08fb5c7204460546c3b7027017f265f76a3952b1f70dc5eff0fbc541", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/weather_data_bavaria/typed/dataset_manifest.json", + "typed_manifest_sha256": "5822af8d0f502ca45584b94bff8ec8bf8302c3fde194334e52f6850b8ff100cd" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 65467830 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 396.281314168 is at least 128", + "dataset_id": "wids2023_competition_weather_forecasting", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 396.28131416837783, + "nonempty_numeric_sequence_count": 250318, + "numeric_catalog_record_count": 250318, + "numeric_sequence_count_including_empty": 250318, + "role_record_counts": { + "value": 250318 + }, + "role_valid_counts": { + "value": 99196346 + }, + "source_bindings": { + "block_catalog_bytes": 596035599, + "block_catalog_path": "/data/root/web_compression/datasets164/wids2023_competition_weather_forecasting/typed/full/blocks.jsonl", + "block_catalog_sha256": "12b5df6bbb51168b5a5dc127e7924abae63ea1ef270de5443f20ace03e5dd95f", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/wids2023_competition_weather_forecasting/typed/dataset_manifest.json", + "typed_manifest_sha256": "28798242c37ad0892e6663fda33f3267d74810091aa396aa73b2db91128ab0ce" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 99196346 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 7397147 is at least 128", + "dataset_id": "wind_4_seconds", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 7397147.0, + "nonempty_numeric_sequence_count": 2, + "numeric_catalog_record_count": 1480, + "numeric_sequence_count_including_empty": 2, + "role_record_counts": { + "additional_temporal_coordinate": 740, + "value": 740 + }, + "role_valid_counts": { + "additional_temporal_coordinate": 7397147, + "value": 7397147 + }, + "source_bindings": { + "block_catalog_bytes": 3291395, + "block_catalog_path": "/data/root/web_compression/datasets164/wind_4_seconds/typed/full/blocks.jsonl", + "block_catalog_sha256": "45434eca4ec142dede2d8d41ba6cd0776fc7f390d4c8ea8739bd1883a70322a4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/wind_4_seconds/typed/dataset_manifest.json", + "typed_manifest_sha256": "f36f760dfa73e7de462469c25c0a1a008db8629d0cc486b1b3338dd85980af83" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 14794294 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 90634.1858407 is at least 128", + "dataset_id": "wind_farms_minutely", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 90634.18584070797, + "nonempty_numeric_sequence_count": 339, + "numeric_catalog_record_count": 3083, + "numeric_sequence_count_including_empty": 339, + "role_record_counts": { + "value": 3083 + }, + "role_valid_counts": { + "value": 30724989 + }, + "source_bindings": { + "block_catalog_bytes": 6905957, + "block_catalog_path": "/data/root/web_compression/datasets164/wind_farms_minutely/typed/full/blocks.jsonl", + "block_catalog_sha256": "4f62df16826bfcdedce20128e7949f8b13e81520c12e80570157d399102761ed", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/wind_farms_minutely/typed/dataset_manifest.json", + "typed_manifest_sha256": "620440a86205ad6623c127d981fa69e0122f07233dbfb48be8df8fe745077f84" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 30724989 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 359 is at least 128", + "dataset_id": "wordle_mcm_dataset", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 359.0, + "nonempty_numeric_sequence_count": 13, + "numeric_catalog_record_count": 13, + "numeric_sequence_count_including_empty": 13, + "role_record_counts": { + "value": 13 + }, + "role_valid_counts": { + "value": 4667 + }, + "source_bindings": { + "block_catalog_bytes": 28450, + "block_catalog_path": "/data/root/web_compression/datasets164/wordle_mcm_dataset/typed/full/blocks.jsonl", + "block_catalog_sha256": "0655b04f7de05bb6e14dde25c37030533b9774051e835e18bd648a39c701d038", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/wordle_mcm_dataset/typed/dataset_manifest.json", + "typed_manifest_sha256": "91c83fae0b0fd02052bc30bc4cee501bfdc01a94ba6148019c5720eecd81864b" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4667 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 288.333333333 is at least 128", + "dataset_id": "wui_global", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 288.3333333333333, + "nonempty_numeric_sequence_count": 15, + "numeric_catalog_record_count": 15, + "numeric_sequence_count_including_empty": 15, + "role_record_counts": { + "value": 15 + }, + "role_valid_counts": { + "value": 4325 + }, + "source_bindings": { + "block_catalog_bytes": 32028, + "block_catalog_path": "/data/root/web_compression/datasets164/wui_global/typed/full/blocks.jsonl", + "block_catalog_sha256": "e8b36c5750f001ba5e34a282cf2f6fe2fc2268c0b50688f60b303af5ed0085a4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/wui_global/typed/dataset_manifest.json", + "typed_manifest_sha256": "4adb6ae4dd0204a3a9037e2e422d020b4c06040954753063b05e3c78c33a6c31" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 4325 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 4207608 is at least 128", + "dataset_id": "xauusd", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 4207608.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 2105, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 2105 + }, + "role_valid_counts": { + "value": 21038040 + }, + "source_bindings": { + "block_catalog_bytes": 4481368, + "block_catalog_path": "/data/root/web_compression/datasets164/xauusd/typed/full/blocks.jsonl", + "block_catalog_sha256": "fe62dab857183cad9d11087abf0fb5f4bfa656c281d747f380c42466b4228a0e", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/xauusd/typed/dataset_manifest.json", + "typed_manifest_sha256": "254a219151a83daef4516838c857a415f1b2de20e366d9e1cceeb285930900fb" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 21038040 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 4207608 is at least 128", + "dataset_id": "xauusd_1m", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 4207608.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 2105, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 2105 + }, + "role_valid_counts": { + "value": 21038040 + }, + "source_bindings": { + "block_catalog_bytes": 4533666, + "block_catalog_path": "/data/root/web_compression/datasets164/xauusd_1m/typed/full/blocks.jsonl", + "block_catalog_sha256": "e170ca930df38208ea288496df03bdc6fd21d0b3bd778bd5333ba8e79422dfcc", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/xauusd_1m/typed/dataset_manifest.json", + "typed_manifest_sha256": "d70689940c86bdba15122eed6abdf03065c5fcf2f15a5388d7b12d006fc455bc" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 21038040 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 91608 is at least 128", + "dataset_id": "xinyi_public_gym", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 91608.0, + "nonempty_numeric_sequence_count": 6, + "numeric_catalog_record_count": 60, + "numeric_sequence_count_including_empty": 6, + "role_record_counts": { + "value": 60 + }, + "role_valid_counts": { + "value": 549648 + }, + "source_bindings": { + "block_catalog_bytes": 131895, + "block_catalog_path": "/data/root/web_compression/datasets164/xinyi_public_gym/typed/full/blocks.jsonl", + "block_catalog_sha256": "10b7264c9db7c80bb5df7b800e17439b4ef801b9c7ad561625c21689ad5ed27c", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/xinyi_public_gym/typed/dataset_manifest.json", + "typed_manifest_sha256": "c02083866f656667736201f38ab992aa9a1de86aefe7580843313644b361f2d6" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 549648 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 2541600 is at least 128", + "dataset_id": "xrpusdt_spot_1m_05_2021_to_03_2026", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 2541600.0, + "nonempty_numeric_sequence_count": 5, + "numeric_catalog_record_count": 1275, + "numeric_sequence_count_including_empty": 5, + "role_record_counts": { + "value": 1275 + }, + "role_valid_counts": { + "value": 12708000 + }, + "source_bindings": { + "block_catalog_bytes": 2998912, + "block_catalog_path": "/data/root/web_compression/datasets164/xrpusdt_spot_1m_05_2021_to_03_2026/typed/full/blocks.jsonl", + "block_catalog_sha256": "0ca4da7522dcae883e58d5d040af74bf62cacaf2099802c8c3cb05a6bc663d7a", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/xrpusdt_spot_1m_05_2021_to_03_2026/typed/dataset_manifest.json", + "typed_manifest_sha256": "34f4493512d8adafac070c6628562cd1449722f49be59cc7a1cb68d7f8687f7a" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 12708000 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "retain_mean_valid_values_per_sequence_at_least_128", + "classification_reason": "mean 70313 is at least 128", + "dataset_id": "yongchun_public_gym", + "empty_numeric_sequence_count": 0, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 70313.0, + "nonempty_numeric_sequence_count": 3, + "numeric_catalog_record_count": 24, + "numeric_sequence_count_including_empty": 3, + "role_record_counts": { + "value": 24 + }, + "role_valid_counts": { + "value": 210939 + }, + "source_bindings": { + "block_catalog_bytes": 53215, + "block_catalog_path": "/data/root/web_compression/datasets164/yongchun_public_gym/typed/full/blocks.jsonl", + "block_catalog_sha256": "904832aeb17d00e961cfdfc8fd919007912688ef7976bd3db76d9c2975366e60", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/yongchun_public_gym/typed/dataset_manifest.json", + "typed_manifest_sha256": "0883269e63a6c3bb234d97980081332373c4db21b76f01d49bcfc5c675b6b0d2" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 210939 + }, + { + "catalog_schemas": [ + "thulab153-offset-block-catalog-v1" + ], + "classification": "exclude_mean_valid_values_per_sequence_below_128", + "classification_reason": "mean 32.2835181544 is below 128", + "dataset_id": "zillow_viewer", + "empty_numeric_sequence_count": 47287, + "excluded_catalog_record_count": 0, + "input_version": "published_baseline_typed_input", + "mean_valid_values_per_sequence": 32.28351815443223, + "nonempty_numeric_sequence_count": 244651, + "numeric_catalog_record_count": 291938, + "numeric_sequence_count_including_empty": 291938, + "role_record_counts": { + "value": 291938 + }, + "role_valid_counts": { + "value": 7898195 + }, + "source_bindings": { + "block_catalog_bytes": 640656958, + "block_catalog_path": "/data/root/web_compression/datasets164/zillow_viewer/typed/full/blocks.jsonl", + "block_catalog_sha256": "0e78b5cb919cbf544e49d916fe8d72ccc1b6b61ab93c635f115d149111ea33c4", + "host": "192", + "mirror_acceptance": "dataset164-final-acceptance-v2", + "typed_manifest_path": "/data/root/web_compression/datasets164/zillow_viewer/typed/dataset_manifest.json", + "typed_manifest_sha256": "1f60337db1ce69b7562ce2d20908e7158455f36481d4bb8cc3ffc130be997494" + }, + "threshold": { + "equal_128_retained": true, + "minimum_mean": 128, + "operator": ">=" + }, + "valid_value_count": 7898195 + } + ], + "definition": { + "admitted_numeric_roles": [ + "value", + "additional_temporal_coordinate" + ], + "equal_128_retained": true, + "excluded_metadata_roles": [ + "timestamp", + "series_id", + "entity_id", + "label" + ], + "no_payload_rule": "exclude separately; undefined mean is never coerced to zero", + "scientific_sequence": "complete (table_name, admitted numeric role, numeric column, entity_id) after merging catalog chunks", + "selection_rule": "retain admitted numeric payload datasets with mean valid values per complete scientific sequence >=128", + "structural_inactive_blanks": "excluded from numerator and denominator", + "threshold": 128 + }, + "derivation": { + "counts_reused_without_numeric_mutation": true, + "method": "deterministic_threshold_reclassification_without_payload_rescan", + "source_min32_sequence_length_audit_path": "/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/min32_scope_audit_20261013_v1/SEQUENCE_LENGTH_AUDIT.json", + "source_min32_sequence_length_audit_sha256": "cdce9b3f988f48639164e850ac16a345bbb23066cbd60f2c8989c21adfcd9365" + }, + "excluded_dataset_count": 23, + "excluded_dataset_ids": [ + "africa_senegal_mauritania_crops_spi", + "car_parts", + "dmi-aarhus-weather-data", + "freshretailnet_50k", + "github_top_projects", + "globalstar_fleet_data", + "hospital-monash", + "housing_inventory", + "kaggle_web_traffic_weekly", + "magseven_ml_ready_high_frequency_anomaly", + "medium_posts", + "niederschlag_station_4091_bavaria_germany", + "nn5_weekly", + "solar_weekly", + "timeseries-finance-ETF", + "timeseries_finance_etf_missing", + "tourism_quarterly", + "tourism_yearly", + "traffic_weekly", + "traqq_weekly_activity", + "trending_stocks_yahoo_finance", + "us_stock_financial_ratios", + "zillow_viewer" + ], + "generated_at": "2026-10-13T20:23:43.365976+08:00", + "no_admitted_numeric_payload_dataset_count": 1, + "retained_dataset_count": 137, + "schema": "compressionbenchmark-min128-sequence-length-audit-v1", + "sequence_length_evaluable_dataset_count": 159, + "source_final160_scope_sha256": "92a995e4278971077fe60dabd913e26e1afdccaeca1ec6181ae1de3f50929889", + "status": "verified_full160_current_input_sequence_lengths" +}