{
  "schema": "compressionbenchmark-operator-byte-effect-current135-complete-key-coverage-v2",
  "status": "complete_canonical_key_coverage_partial_current_input_qualification",
  "claim_boundary": "value-column matched omissions only; byte effects only; no timing ranking",
  "coverage": {
    "scope_identity_count": 135,
    "column_complete_identity_count": 135,
    "value_column_count": 3519,
    "recipe_count": 10,
    "expected_recipe_key_count": 35190,
    "observed_recipe_key_count": 35190,
    "missing_recipe_key_count": 0,
    "incomplete_identities": [],
    "status_counts": {
      "ok": 25413,
      "unsupported": 9399,
      "N/A": 378
    }
  },
  "canonical_key_coverage_complete": true,
  "current_input_qualified": false,
  "current_input_qualification": {
    "current_manifest_bound_columns": 454,
    "current_manifest_bound_recipe_keys": 4540,
    "retained_historical_columns_not_requalified_to_current_input_sha": 3065,
    "retained_historical_recipe_keys_not_requalified_to_current_input_sha": 30650
  },
  "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
  "publish_as_full_current135": false,
  "publish_as_full_current135_key_coverage": true,
  "publish_as_full_current_input_qualified": false,
  "rows": [
    {
      "admitted_dataset_count": 63,
      "admitted_value_column_count": 2012,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 63,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "IGlocations2",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "bitcoin_price_timeseries",
        "crypto_data",
        "deep-space-probes",
        "dst-index",
        "eea_pm25_forecasting",
        "electricity_demand",
        "faang_engineered_time_series_features_2013_2025",
        "forex_factory_calendar",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "hourly-stock-data-2023",
        "indian_stock_hourly_2017_2021",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "meteoblue",
        "multi_model_trading_data",
        "nifty50_market_regime",
        "omie_blockchain_study",
        "ooni_censorship_historical",
        "orbital_chaos_nasa_ssc",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "salesforecastingwomartstore",
        "sleep_score_fitbit",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "uk_electricity_generation_mix_2019_2026",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wordle_mcm_dataset",
        "xauusd",
        "xauusd_1m"
      ],
      "diagnostic_recipe_id": "corad_tricklet_dictionary_pair_v1",
      "display_label": "Dictionary",
      "mean_baseline_to_original_ratio": 3.484793340026168,
      "mean_byte_change_percent": -13.133511056818936,
      "mean_omission_to_baseline_ratio": 0.8686648894318106,
      "mean_omission_to_original_ratio": 2.653840249254806,
      "mean_rate_multiple_after_over_before": 0.8686648894318106,
      "omitted_operator": "dictionary",
      "operator": "Dictionary",
      "row_count": 2012,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 58,
      "admitted_value_column_count": 1551,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 58,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "IGlocations2",
        "Metro-Traffic",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "bitcoin_price_timeseries",
        "crypto_data",
        "deep-space-probes",
        "dst-index",
        "eea_pm25_forecasting",
        "electricity_demand",
        "faang_engineered_time_series_features_2013_2025",
        "forex_factory_calendar",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "hourly-stock-data-2023",
        "indian_stock_hourly_2017_2021",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "meteoblue",
        "multi_model_trading_data",
        "ooni_censorship_historical",
        "orbital_chaos_nasa_ssc",
        "polymarket_crypto_5m_15m",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "salesforecastingwomartstore",
        "sleep_score_fitbit",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "uk_electricity_generation_mix_2019_2026",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wordle_mcm_dataset",
        "xauusd_1m"
      ],
      "diagnostic_recipe_id": "fpzip_range_pair_v1",
      "display_label": "Range (FPZIP)",
      "mean_baseline_to_original_ratio": 1.7567656588732088,
      "mean_byte_change_percent": 33.07125172743892,
      "mean_omission_to_baseline_ratio": 1.3307125172743892,
      "mean_omission_to_original_ratio": 1.6819759812283008,
      "mean_rate_multiple_after_over_before": 1.3307125172743892,
      "omitted_operator": "entropy_range",
      "operator": "Range (FPZIP)",
      "row_count": 1551,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 63,
      "admitted_value_column_count": 2012,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 63,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "IGlocations2",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "bitcoin_price_timeseries",
        "crypto_data",
        "deep-space-probes",
        "dst-index",
        "eea_pm25_forecasting",
        "electricity_demand",
        "faang_engineered_time_series_features_2013_2025",
        "forex_factory_calendar",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "hourly-stock-data-2023",
        "indian_stock_hourly_2017_2021",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "meteoblue",
        "multi_model_trading_data",
        "nifty50_market_regime",
        "omie_blockchain_study",
        "ooni_censorship_historical",
        "orbital_chaos_nasa_ssc",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "salesforecastingwomartstore",
        "sleep_score_fitbit",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "uk_electricity_generation_mix_2019_2026",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wordle_mcm_dataset",
        "xauusd",
        "xauusd_1m"
      ],
      "diagnostic_recipe_id": "gorilla_trailing_pack_pair_v1",
      "display_label": "Trailing-zero pack",
      "mean_baseline_to_original_ratio": 1.4453034473928652,
      "mean_byte_change_percent": 147.18360100114847,
      "mean_omission_to_baseline_ratio": 2.4718360100114847,
      "mean_omission_to_original_ratio": 1.5976028338796278,
      "mean_rate_multiple_after_over_before": 2.4718360100114847,
      "omitted_operator": "trailing_zero_pack",
      "operator": "Trailing-zero pack",
      "row_count": 2012,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 135,
      "admitted_value_column_count": 3473,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 135,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "ETDataset-ett",
        "IGlocations2",
        "METR-LA",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "PEMS-BAY",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "australia_solar",
        "australian_electricity_demand",
        "auto_production_sf",
        "azure2019_u",
        "bitcoin",
        "bitcoin_price_timeseries",
        "coastal_t_s",
        "commodity_import",
        "commodity_production",
        "covid_deaths-monash",
        "cphl",
        "crypto",
        "crypto_data",
        "current_velocity",
        "deep-space-probes",
        "dst-index",
        "ecdc_covid",
        "eea_pm25_forecasting",
        "electricity_demand",
        "electricity_load_2011_2014",
        "electricity_production",
        "enedis-with-holidays",
        "epf_electricity_price",
        "eweld_load",
        "exchange_rate",
        "faang_engineered_time_series_features_2013_2025",
        "finland_traffic",
        "forex_factory_calendar",
        "fred_md",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "global_influenza",
        "global_price",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "greatplains_multisource_2000_2024",
        "hourly-stock-data-2023",
        "hourly_electricity_demand_brazil",
        "indian_stock_hourly_2017_2021",
        "job_claims",
        "jolts",
        "kdd_cup_2018",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "london_smart_meters",
        "m2oe2_timeseries",
        "meteoblue",
        "metropt_3",
        "multi_model_trading_data",
        "national_illness",
        "ne_china_wind",
        "nifty50_market_regime",
        "nn5_daily",
        "oikolab_weather",
        "oil_price",
        "omie_blockchain_study",
        "online_retail_2_uci",
        "ooni_censorship_historical",
        "openelectricity_nem",
        "orbital_chaos_nasa_ssc",
        "pedestrian_counts",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "port_activity",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "rideshare",
        "salesforecastingwomartstore",
        "saugeenday-monash",
        "scaphandre_cpu_usage",
        "sg_carpark",
        "sg_pm25",
        "sg_weather",
        "sleep_score_fitbit",
        "solar_10_minutes",
        "solar_4_seconds",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "sunspot",
        "telangana_weather",
        "temperature_rain",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "traffic",
        "traffic_hourly",
        "trxusdt_spot_1m_05_2021_to_03_2026",
        "uk_electricity_generation_mix_2019_2026",
        "uncertainty_1m",
        "us_births-monash",
        "us_labor",
        "us_term_structure",
        "vehicle_sales",
        "vehicle_supply",
        "vehicle_trips",
        "water_quality_darwin",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wind_4_seconds",
        "wind_farms_minutely",
        "wordle_mcm_dataset",
        "wui_global",
        "xauusd",
        "xauusd_1m",
        "xinyi_public_gym",
        "xrpusdt_spot_1m_05_2021_to_03_2026",
        "yongchun_public_gym"
      ],
      "diagnostic_recipe_id": "project_arithmetic_bytes_v1",
      "display_label": "Arithmetic",
      "mean_baseline_to_original_ratio": 7.056445303633313,
      "mean_byte_change_percent": 17.84897134410577,
      "mean_omission_to_baseline_ratio": 1.1784897134410577,
      "mean_omission_to_original_ratio": 1.9208154369383852,
      "mean_rate_multiple_after_over_before": 1.1784897134410577,
      "omitted_operator": "entropy_range",
      "operator": "Arithmetic",
      "row_count": 3473,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 135,
      "admitted_value_column_count": 3473,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 135,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "ETDataset-ett",
        "IGlocations2",
        "METR-LA",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "PEMS-BAY",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "australia_solar",
        "australian_electricity_demand",
        "auto_production_sf",
        "azure2019_u",
        "bitcoin",
        "bitcoin_price_timeseries",
        "coastal_t_s",
        "commodity_import",
        "commodity_production",
        "covid_deaths-monash",
        "cphl",
        "crypto",
        "crypto_data",
        "current_velocity",
        "deep-space-probes",
        "dst-index",
        "ecdc_covid",
        "eea_pm25_forecasting",
        "electricity_demand",
        "electricity_load_2011_2014",
        "electricity_production",
        "enedis-with-holidays",
        "epf_electricity_price",
        "eweld_load",
        "exchange_rate",
        "faang_engineered_time_series_features_2013_2025",
        "finland_traffic",
        "forex_factory_calendar",
        "fred_md",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "global_influenza",
        "global_price",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "greatplains_multisource_2000_2024",
        "hourly-stock-data-2023",
        "hourly_electricity_demand_brazil",
        "indian_stock_hourly_2017_2021",
        "job_claims",
        "jolts",
        "kdd_cup_2018",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "london_smart_meters",
        "m2oe2_timeseries",
        "meteoblue",
        "metropt_3",
        "multi_model_trading_data",
        "national_illness",
        "ne_china_wind",
        "nifty50_market_regime",
        "nn5_daily",
        "oikolab_weather",
        "oil_price",
        "omie_blockchain_study",
        "online_retail_2_uci",
        "ooni_censorship_historical",
        "openelectricity_nem",
        "orbital_chaos_nasa_ssc",
        "pedestrian_counts",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "port_activity",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "rideshare",
        "salesforecastingwomartstore",
        "saugeenday-monash",
        "scaphandre_cpu_usage",
        "sg_carpark",
        "sg_pm25",
        "sg_weather",
        "sleep_score_fitbit",
        "solar_10_minutes",
        "solar_4_seconds",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "sunspot",
        "telangana_weather",
        "temperature_rain",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "traffic",
        "traffic_hourly",
        "trxusdt_spot_1m_05_2021_to_03_2026",
        "uk_electricity_generation_mix_2019_2026",
        "uncertainty_1m",
        "us_births-monash",
        "us_labor",
        "us_term_structure",
        "vehicle_sales",
        "vehicle_supply",
        "vehicle_trips",
        "water_quality_darwin",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wind_4_seconds",
        "wind_farms_minutely",
        "wordle_mcm_dataset",
        "wui_global",
        "xauusd",
        "xauusd_1m",
        "xinyi_public_gym",
        "xrpusdt_spot_1m_05_2021_to_03_2026",
        "yongchun_public_gym"
      ],
      "diagnostic_recipe_id": "project_huffman_bytes_v1",
      "display_label": "Huffman",
      "mean_baseline_to_original_ratio": 7.043703924984161,
      "mean_byte_change_percent": 12.537077495632087,
      "mean_omission_to_baseline_ratio": 1.1253707749563209,
      "mean_omission_to_original_ratio": 1.9208154369383852,
      "mean_rate_multiple_after_over_before": 1.1253707749563209,
      "omitted_operator": "entropy_huffman",
      "operator": "Huffman",
      "row_count": 3473,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 135,
      "admitted_value_column_count": 3473,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 135,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "ETDataset-ett",
        "IGlocations2",
        "METR-LA",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "PEMS-BAY",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "australia_solar",
        "australian_electricity_demand",
        "auto_production_sf",
        "azure2019_u",
        "bitcoin",
        "bitcoin_price_timeseries",
        "coastal_t_s",
        "commodity_import",
        "commodity_production",
        "covid_deaths-monash",
        "cphl",
        "crypto",
        "crypto_data",
        "current_velocity",
        "deep-space-probes",
        "dst-index",
        "ecdc_covid",
        "eea_pm25_forecasting",
        "electricity_demand",
        "electricity_load_2011_2014",
        "electricity_production",
        "enedis-with-holidays",
        "epf_electricity_price",
        "eweld_load",
        "exchange_rate",
        "faang_engineered_time_series_features_2013_2025",
        "finland_traffic",
        "forex_factory_calendar",
        "fred_md",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "global_influenza",
        "global_price",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "greatplains_multisource_2000_2024",
        "hourly-stock-data-2023",
        "hourly_electricity_demand_brazil",
        "indian_stock_hourly_2017_2021",
        "job_claims",
        "jolts",
        "kdd_cup_2018",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "london_smart_meters",
        "m2oe2_timeseries",
        "meteoblue",
        "metropt_3",
        "multi_model_trading_data",
        "national_illness",
        "ne_china_wind",
        "nifty50_market_regime",
        "nn5_daily",
        "oikolab_weather",
        "oil_price",
        "omie_blockchain_study",
        "online_retail_2_uci",
        "ooni_censorship_historical",
        "openelectricity_nem",
        "orbital_chaos_nasa_ssc",
        "pedestrian_counts",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "port_activity",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "rideshare",
        "salesforecastingwomartstore",
        "saugeenday-monash",
        "scaphandre_cpu_usage",
        "sg_carpark",
        "sg_pm25",
        "sg_weather",
        "sleep_score_fitbit",
        "solar_10_minutes",
        "solar_4_seconds",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "sunspot",
        "telangana_weather",
        "temperature_rain",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "traffic",
        "traffic_hourly",
        "trxusdt_spot_1m_05_2021_to_03_2026",
        "uk_electricity_generation_mix_2019_2026",
        "uncertainty_1m",
        "us_births-monash",
        "us_labor",
        "us_term_structure",
        "vehicle_sales",
        "vehicle_supply",
        "vehicle_trips",
        "water_quality_darwin",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wind_4_seconds",
        "wind_farms_minutely",
        "wordle_mcm_dataset",
        "wui_global",
        "xauusd",
        "xauusd_1m",
        "xinyi_public_gym",
        "xrpusdt_spot_1m_05_2021_to_03_2026",
        "yongchun_public_gym"
      ],
      "diagnostic_recipe_id": "project_rans_reference_v1",
      "display_label": "rANS",
      "mean_baseline_to_original_ratio": 5.0131495620199695,
      "mean_byte_change_percent": 29.146811586712396,
      "mean_omission_to_baseline_ratio": 1.291468115867124,
      "mean_omission_to_original_ratio": 1.9208154369383852,
      "mean_rate_multiple_after_over_before": 1.291468115867124,
      "omitted_operator": "entropy_fse",
      "operator": "rANS",
      "row_count": 3473,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 135,
      "admitted_value_column_count": 3473,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 135,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "ETDataset-ett",
        "IGlocations2",
        "METR-LA",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "PEMS-BAY",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "australia_solar",
        "australian_electricity_demand",
        "auto_production_sf",
        "azure2019_u",
        "bitcoin",
        "bitcoin_price_timeseries",
        "coastal_t_s",
        "commodity_import",
        "commodity_production",
        "covid_deaths-monash",
        "cphl",
        "crypto",
        "crypto_data",
        "current_velocity",
        "deep-space-probes",
        "dst-index",
        "ecdc_covid",
        "eea_pm25_forecasting",
        "electricity_demand",
        "electricity_load_2011_2014",
        "electricity_production",
        "enedis-with-holidays",
        "epf_electricity_price",
        "eweld_load",
        "exchange_rate",
        "faang_engineered_time_series_features_2013_2025",
        "finland_traffic",
        "forex_factory_calendar",
        "fred_md",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "global_influenza",
        "global_price",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "greatplains_multisource_2000_2024",
        "hourly-stock-data-2023",
        "hourly_electricity_demand_brazil",
        "indian_stock_hourly_2017_2021",
        "job_claims",
        "jolts",
        "kdd_cup_2018",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "london_smart_meters",
        "m2oe2_timeseries",
        "meteoblue",
        "metropt_3",
        "multi_model_trading_data",
        "national_illness",
        "ne_china_wind",
        "nifty50_market_regime",
        "nn5_daily",
        "oikolab_weather",
        "oil_price",
        "omie_blockchain_study",
        "online_retail_2_uci",
        "ooni_censorship_historical",
        "openelectricity_nem",
        "orbital_chaos_nasa_ssc",
        "pedestrian_counts",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "port_activity",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "rideshare",
        "salesforecastingwomartstore",
        "saugeenday-monash",
        "scaphandre_cpu_usage",
        "sg_carpark",
        "sg_pm25",
        "sg_weather",
        "sleep_score_fitbit",
        "solar_10_minutes",
        "solar_4_seconds",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "sunspot",
        "telangana_weather",
        "temperature_rain",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "traffic",
        "traffic_hourly",
        "trxusdt_spot_1m_05_2021_to_03_2026",
        "uk_electricity_generation_mix_2019_2026",
        "uncertainty_1m",
        "us_births-monash",
        "us_labor",
        "us_term_structure",
        "vehicle_sales",
        "vehicle_supply",
        "vehicle_trips",
        "water_quality_darwin",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wind_4_seconds",
        "wind_farms_minutely",
        "wordle_mcm_dataset",
        "wui_global",
        "xauusd",
        "xauusd_1m",
        "xinyi_public_gym",
        "xrpusdt_spot_1m_05_2021_to_03_2026",
        "yongchun_public_gym"
      ],
      "diagnostic_recipe_id": "rle_run_length_direct_v1",
      "display_label": "Run length",
      "mean_baseline_to_original_ratio": 3.167913427093977,
      "mean_byte_change_percent": 55.68916736602014,
      "mean_omission_to_baseline_ratio": 1.5568916736602014,
      "mean_omission_to_original_ratio": 1.9208154369383852,
      "mean_rate_multiple_after_over_before": 1.5568916736602014,
      "omitted_operator": "run_length",
      "operator": "Run length",
      "row_count": 3473,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 135,
      "admitted_value_column_count": 3473,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 135,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "ETDataset-ett",
        "IGlocations2",
        "METR-LA",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "PEMS-BAY",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "australia_solar",
        "australian_electricity_demand",
        "auto_production_sf",
        "azure2019_u",
        "bitcoin",
        "bitcoin_price_timeseries",
        "coastal_t_s",
        "commodity_import",
        "commodity_production",
        "covid_deaths-monash",
        "cphl",
        "crypto",
        "crypto_data",
        "current_velocity",
        "deep-space-probes",
        "dst-index",
        "ecdc_covid",
        "eea_pm25_forecasting",
        "electricity_demand",
        "electricity_load_2011_2014",
        "electricity_production",
        "enedis-with-holidays",
        "epf_electricity_price",
        "eweld_load",
        "exchange_rate",
        "faang_engineered_time_series_features_2013_2025",
        "finland_traffic",
        "forex_factory_calendar",
        "fred_md",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "global_influenza",
        "global_price",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "greatplains_multisource_2000_2024",
        "hourly-stock-data-2023",
        "hourly_electricity_demand_brazil",
        "indian_stock_hourly_2017_2021",
        "job_claims",
        "jolts",
        "kdd_cup_2018",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "london_smart_meters",
        "m2oe2_timeseries",
        "meteoblue",
        "metropt_3",
        "multi_model_trading_data",
        "national_illness",
        "ne_china_wind",
        "nifty50_market_regime",
        "nn5_daily",
        "oikolab_weather",
        "oil_price",
        "omie_blockchain_study",
        "online_retail_2_uci",
        "ooni_censorship_historical",
        "openelectricity_nem",
        "orbital_chaos_nasa_ssc",
        "pedestrian_counts",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "port_activity",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "rideshare",
        "salesforecastingwomartstore",
        "saugeenday-monash",
        "scaphandre_cpu_usage",
        "sg_carpark",
        "sg_pm25",
        "sg_weather",
        "sleep_score_fitbit",
        "solar_10_minutes",
        "solar_4_seconds",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "sunspot",
        "telangana_weather",
        "temperature_rain",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "traffic",
        "traffic_hourly",
        "trxusdt_spot_1m_05_2021_to_03_2026",
        "uk_electricity_generation_mix_2019_2026",
        "uncertainty_1m",
        "us_births-monash",
        "us_labor",
        "us_term_structure",
        "vehicle_sales",
        "vehicle_supply",
        "vehicle_trips",
        "water_quality_darwin",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wind_4_seconds",
        "wind_farms_minutely",
        "wordle_mcm_dataset",
        "wui_global",
        "xauusd",
        "xauusd_1m",
        "xinyi_public_gym",
        "xrpusdt_spot_1m_05_2021_to_03_2026",
        "yongchun_public_gym"
      ],
      "diagnostic_recipe_id": "snappy_token_format_pair_v1",
      "display_label": "Match tokens",
      "mean_baseline_to_original_ratio": 4.3041504311582575,
      "mean_byte_change_percent": 66.75282992940394,
      "mean_omission_to_baseline_ratio": 1.6675282992940395,
      "mean_omission_to_original_ratio": 3.4872110092581936,
      "mean_rate_multiple_after_over_before": 1.6675282992940395,
      "omitted_operator": "match_token_format",
      "operator": "Match tokens",
      "row_count": 3473,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 63,
      "admitted_value_column_count": 2012,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 63,
      "dataset_ids": [
        "Air-Quality",
        "Bar-Crawl",
        "Bird-migration",
        "Comments",
        "IGlocations2",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ahr999-dataset",
        "ast_spacemobile_fleet_data",
        "bitcoin_price_timeseries",
        "crypto_data",
        "deep-space-probes",
        "dst-index",
        "eea_pm25_forecasting",
        "electricity_demand",
        "faang_engineered_time_series_features_2013_2025",
        "forex_factory_calendar",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "gluco_tsfm_benchmark",
        "goes_omni_electron_flux_forecasting",
        "hourly-stock-data-2023",
        "indian_stock_hourly_2017_2021",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "meteoblue",
        "multi_model_trading_data",
        "nifty50_market_regime",
        "omie_blockchain_study",
        "ooni_censorship_historical",
        "orbital_chaos_nasa_ssc",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "quitobench",
        "rating",
        "reg_forecasting_v2",
        "salesforecastingwomartstore",
        "sleep_score_fitbit",
        "solusdt_enhanced_180",
        "spx",
        "stock_dataset",
        "substorm_onsets",
        "timeseries-1m-QQQ-10y",
        "timeseries_1mn_sp500",
        "timeseries_1mn_stocks",
        "tourism_monthly-zaai-ai",
        "tourism_residuals",
        "uk_electricity_generation_mix_2019_2026",
        "weather_data_bavaria",
        "wids2023_competition_weather_forecasting",
        "wordle_mcm_dataset",
        "xauusd",
        "xauusd_1m"
      ],
      "diagnostic_recipe_id": "spdp_entropy_pair_v1",
      "display_label": "Special (SPDP)",
      "mean_baseline_to_original_ratio": 1.8928987418359482,
      "mean_byte_change_percent": 74.56963246787257,
      "mean_omission_to_baseline_ratio": 1.7456963246787256,
      "mean_omission_to_original_ratio": 1.9421803292265105,
      "mean_rate_multiple_after_over_before": 1.7456963246787256,
      "omitted_operator": "entropy_special",
      "operator": "Special (SPDP)",
      "row_count": 2012,
      "status": "ok"
    },
    {
      "admitted_dataset_count": 44,
      "admitted_value_column_count": 461,
      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
      "current_input_qualification_boundary": "Full canonical value-column key coverage is present. 454 columns are current-manifest-bound; 3,065 retained historical columns have not been requalified against the current input SHA.",
      "current_input_qualified": false,
      "dataset_count": 44,
      "dataset_ids": [
        "Air-Quality",
        "Bird-migration",
        "Comments",
        "IGlocations2",
        "Metro-Traffic",
        "NYC_Yellow_Taxi_Trip",
        "RealEstate1",
        "RealEstate2",
        "Romance",
        "SpatialEpiBench",
        "Telco",
        "TrainsUK2",
        "Uberlandia",
        "Wins",
        "YaleLanguages",
        "ast_spacemobile_fleet_data",
        "eea_pm25_forecasting",
        "faang_engineered_time_series_features_2013_2025",
        "fulus_lyd_rates_2025",
        "geomagnetic_kp_index",
        "goes_omni_electron_flux_forecasting",
        "hourly-stock-data-2023",
        "knowable",
        "kraken-trading-data",
        "kuiper_fleet_data",
        "multi_model_trading_data",
        "nifty50_market_regime",
        "omie_blockchain_study",
        "ooni_censorship_historical",
        "phenology_normal_hawaii",
        "polymarket_crypto_5m_15m",
        "rating",
        "reg_forecasting_v2",
        "salesforecastingwomartstore",
        "sleep_score_fitbit",
        "spx",
        "stock_dataset",
        "timeseries-1m-QQQ-10y",
        "tourism_monthly-zaai-ai",
        "uk_electricity_generation_mix_2019_2026",
        "wids2023_competition_weather_forecasting",
        "wordle_mcm_dataset",
        "xauusd",
        "xauusd_1m"
      ],
      "diagnostic_recipe_id": "stream_vbyte_integer_code_pair_v1",
      "display_label": "Integer code",
      "mean_baseline_to_original_ratio": 0.9521221989524588,
      "mean_byte_change_percent": 103.01479850077939,
      "mean_omission_to_baseline_ratio": 2.030147985007794,
      "mean_omission_to_original_ratio": 1.339500239698804,
      "mean_rate_multiple_after_over_before": 2.030147985007794,
      "omitted_operator": "integer_code",
      "operator": "Integer code",
      "row_count": 461,
      "status": "ok"
    }
  ],
  "source_union": {
    "local_completed_31190_file": "current135_operator_value_union.csv.gz",
    "local_completed_31190_sha256": "ff9606947ad4d328874e033203957fd01d3b226faa050a25989f26b174628849",
    "merge_rule": "append the disjoint 4000-key gap patch; duplicate dataset/column/recipe keys are rejected",
    "combined_recipe_key_count": 35190,
    "combined_keyset_sha256": "e728a9efddf61b874080efe77900261caf0986cf07c3e780a297b45317502521"
  },
  "source_deltas": [
    {
      "file": "operator_byte_effect_current135_new540.public.csv.gz",
      "row_count": 540,
      "sha256": "898de6be028fc1629d158f3e1d4ded766085b114dbc04961b2375ab54c2e0c08"
    },
    {
      "file": "operator135_gap400.current_value_columns.public.csv.gz",
      "row_count": 4000,
      "sha256": "d5cd9f92338f86ff7d38c57649c07c8dc2076415313c8c25e02d75b1ba4365de"
    }
  ],
  "timing_fields_all_null": true
}