Spaces:

THULab
/

CompressionBenchmark

Running

App Files Files Community

jzxiao commited on 3 days ago

Commit

a0cf6c3

verified ·

1 Parent(s): f4921dc

Add current-scope operator supplement and explicit remaining column coverage

Browse files

Files changed (5) hide show

app.js +7 -7
index.html +5 -5
manifest.json +33 -0
operator-byte-effect-current135-summary.json +1163 -0
operator_byte_effect_current135_new540.public.csv.gz +3 -0

app.js CHANGED Viewed

@@ -277,16 +277,16 @@ function renderMethodDocumentation() {
 }
 function renderOperatorEffect() {
   const status=$('operator-effect-status'),body=$('operator-effect-table')?.querySelector('tbody');if(!status||!body)return;
-  if(operatorEffectError){status.textContent='Verified byte-effect results could not be loaded.';body.innerHTML=`<tr><td colspan="7" class="empty-cell">${escape(operatorEffectError.message)}</td></tr>`;return;}
-  if(!operatorEffect){status.textContent='Loading verified byte effects…';return;}
-  const rows=operatorEffect.rows||[],audit=operatorEffect.audit||{};
-  status.textContent=`Historical input-version diagnostic. Current-scope, corrected-input operator replacement is pending. ${rows.length} omitted operators · ${countFmt(audit.admitted_ok_row_count||0)} admitted rows from the exact ${countFmt(audit.input_row_count||0)}-row union · timing unavailable`;
-  body.innerHTML=rows.length?rows.map(row=>`<tr><td>${escape(row.operator)}</td><td class="numeric">${fmt(row.mean_omission_to_baseline_ratio,3)}×</td><td class="numeric ${number(row.mean_byte_change_percent)>0?'operator-effect-cost':'operator-effect-saving'}">${number(row.mean_byte_change_percent)>0?'+':''}${fmt(row.mean_byte_change_percent,1)}%</td><td class="numeric">${fmt(row.mean_baseline_to_original_ratio,3)}</td><td class="numeric">${fmt(row.mean_omission_to_original_ratio,3)}</td><td class="numeric"><span class="coverage">${countFmt(row.dataset_count)}</span></td><td class="numeric">${countFmt(row.row_count)}</td></tr>`).join(''):'<tr><td colspan="7" class="empty-cell">No admitted matched-omission rows.</td></tr>';
 }
 async function loadOperatorEffect() {
   try {
-    const response=await fetch('./operator-byte-effect-summary.json?v=20261011-byte-effect-v1',{cache:'no-cache'});if(!response.ok)throw new Error(`Operator byte-effect request returned ${response.status}.`);
-    const value=await response.json();if(value?.schema!=='compressionbenchmark-operator-byte-effect-summary-v1'||value?.status!=='accepted'||value?.timing?.status!=='unavailable'||!Array.isArray(value.rows))throw new Error('Operator byte-effect summary has an invalid schema.');operatorEffect=value;
   } catch(error) { operatorEffectError=error instanceof Error?error:new Error('Operator byte-effect summary is unavailable.'); }
   renderOperatorEffect();
 }

 }
 function renderOperatorEffect() {
   const status=$('operator-effect-status'),body=$('operator-effect-table')?.querySelector('tbody');if(!status||!body)return;
+  if(operatorEffectError){status.textContent='Operator byte-effect results could not be loaded.';body.innerHTML=`<tr><td colspan="7" class="empty-cell">${escape(operatorEffectError.message)}</td></tr>`;return;}
+  if(!operatorEffect){status.textContent='Loading byte effects…';return;}
+  const rows=operatorEffect.rows||[],coverage=operatorEffect.coverage||{};
+  status.textContent=`${countFmt(coverage.scope_identity_count)} dataset scope · ${countFmt(coverage.column_complete_identity_count)} identities have complete column-key coverage · ${countFmt(coverage.observed_recipe_key_count)} / ${countFmt(coverage.expected_recipe_key_count)} recipe keys · ${countFmt(coverage.missing_recipe_key_count)} pending · timing unavailable`;
+  body.innerHTML=rows.map(row=>`<tr><td>${escape(row.display_label)}</td><td class="numeric">${fmt(row.mean_rate_multiple_after_over_before,3)}×</td><td class="numeric">${fmt(100*(row.mean_rate_multiple_after_over_before-1),1)}%</td><td class="numeric">${fmt(row.mean_baseline_to_original_ratio,3)}</td><td class="numeric">${fmt(row.mean_omission_to_original_ratio,3)}</td><td class="numeric">${countFmt(row.admitted_dataset_count)}</td><td class="numeric">${countFmt(row.admitted_value_column_count)}</td></tr>`).join('');
 }
 async function loadOperatorEffect() {
   try {
+    const response=await fetch('./operator-byte-effect-current135-summary.json?v=20261016-current135-v1',{cache:'no-cache'});if(!response.ok)throw new Error(`Operator byte-effect request returned ${response.status}.`);
+    const value=await response.json();if(value?.schema!=='compressionbenchmark-operator-byte-effect-current135-patch-v1'||value?.timing_fields_all_null!==true||!Array.isArray(value.rows)||value?.publish_as_full_current135!==false)throw new Error('Operator byte-effect summary has an invalid schema.');operatorEffect=value;
   } catch(error) { operatorEffectError=error instanceof Error?error:new Error('Operator byte-effect summary is unavailable.'); }
   renderOperatorEffect();
 }

index.html CHANGED Viewed

@@ -7,7 +7,7 @@
   <meta name="color-scheme" content="light dark">
   <title>THULab | Time Series Compression Benchmark</title>
   <link rel="stylesheet" href="style.css?v=20261013-cpp-latest-v1">
-  <script src="app.js?v=20261016-score-badge-remove-v1" type="module"></script>
 </head>
 <body>
   <a class="skip-link" href="#content">Skip to results</a>
@@ -101,10 +101,10 @@
         <label class="documentation-search">Search operators<input id="operator-doc-search" type="search" placeholder="Family, A-ID, implementation, I/O, or reference" autocomplete="off"></label>
       </div>
       <section id="operator-effect-results" class="operator-effect-results" aria-labelledby="operator-effect-title">
-        <div class="operator-effect-head"><div><h3 id="operator-effect-title">Historical matched-omission byte effects</h3><p class="muted">Historical byte-only measurements from the independently accepted archived union. Its dataset identities and some inputs predate the current sequence-length filter and numeric corrections; these values are historical, not current-scope/current-input results. Every admitted row is lossless and passed fresh baseline and omission round-trip checks against the same original-byte denominator. Ratios above 1 mean omission increased reconstructable bytes. Datasets receive equal weight; timing is unavailable.</p></div><a class="quiet-button" href="operator-byte-effect-full-union.csv.gz" download>Download 41,090-row evidence</a></div>
-        <p id="operator-effect-status" class="documentation-status" aria-live="polite">Loading verified byte effects…</p>
-        <div class="table-wrap operator-effect-table-wrap"><table id="operator-effect-table"><thead><tr><th>Omitted operator</th><th>Omission / baseline</th><th>Byte change</th><th>Baseline / original</th><th>Omission / original</th><th>Dataset support</th><th>Rows</th></tr></thead><tbody><tr><td colspan="7" class="loading-cell">Loading verified byte effects…</td></tr></tbody></table></div>
-        <p class="reference-source">These matched diagnostic recipes measure byte effects only. They do not provide timing rankings or universal causal attribution for every catalog method.</p>
       </section>
       <div id="operator-summary" class="operator-summary" aria-label="Operator catalog summary"></div>
       <p class="reference-source">The family split follows the final operator registry; references include the presentation Notes and official implementation sources. STOP, Concat, and continuous Split are control or graph operations and are excluded from the 30-family count. Split (columnize) remains family 29. External links open in a new tab.</p>

   <meta name="color-scheme" content="light dark">
   <title>THULab | Time Series Compression Benchmark</title>
   <link rel="stylesheet" href="style.css?v=20261013-cpp-latest-v1">
+  <script src="app.js?v=20261016-operator135-v1" type="module"></script>
 </head>
 <body>
   <a class="skip-link" href="#content">Skip to results</a>
         <label class="documentation-search">Search operators<input id="operator-doc-search" type="search" placeholder="Family, A-ID, implementation, I/O, or reference" autocomplete="off"></label>
       </div>
       <section id="operator-effect-results" class="operator-effect-results" aria-labelledby="operator-effect-title">
+        <div class="operator-effect-head"><div><h3 id="operator-effect-title">Matched-omission byte effects · 135 dataset scope</h3><p class="muted">Value columns only. The new supplement adds 540 lossless or explicitly unsupported conclusions: 270 numeric results and 270 N/A. Archived measurements are retained for matching column identities; this does not certify all archived inputs against the current input version. Complete canonical column-key coverage remains pending for 400 columns in seven datasets. Supported column bytes are summed within each dataset, then datasets receive equal weight. Ratios above 1 mean omission increased bytes. Timing is unavailable.</p></div><a class="quiet-button" href="operator_byte_effect_current135_new540.public.csv.gz" download>Download new 540-row results</a></div>
+        <p id="operator-effect-status" class="documentation-status" aria-live="polite">Loading byte effects…</p>
+        <div class="table-wrap operator-effect-table-wrap"><table id="operator-effect-table"><thead><tr><th>Omitted operator</th><th>Omission / baseline</th><th>Byte change</th><th>Baseline / original</th><th>Omission / original</th><th>Dataset support</th><th>Value columns</th></tr></thead><tbody><tr><td colspan="7" class="loading-cell">Loading byte effects…</td></tr></tbody></table></div>
+        <p class="reference-source">Missing column coverage: WiDS (243), GOES (102), Kraken (38), Polymarket (7), QuitoBench (5), Knowable (4), SalesForecasting (1). Type-inapplicable recipes remain N/A. These diagnostics do not establish timing rankings or universal causal effects. <a href="operator-byte-effect-full-union.csv.gz" download>Archived evidence</a> · <a href="operator-byte-effect-current135-summary.json" download>Scope and merge metadata</a></p>
       </section>
       <div id="operator-summary" class="operator-summary" aria-label="Operator catalog summary"></div>
       <p class="reference-source">The family split follows the final operator registry; references include the presentation Notes and official implementation sources. STOP, Concat, and continuous Split are control or graph operations and are excluded from the 30-family count. Split (columnize) remains family 29. External links open in a new tab.</p>

manifest.json CHANGED Viewed

@@ -2809,5 +2809,38 @@
       "status": "built_from_published_lossless270_plus_completed_uniform_five675",
       "uncompressed_sha256": "6ab4cc1e9e788f5baac4d79a8584ff647e3a6d7451d57a8a1fc1943502b7b2b7"
     }
   }
 }

       "status": "built_from_published_lossless270_plus_completed_uniform_five675",
       "uncompressed_sha256": "6ab4cc1e9e788f5baac4d79a8584ff647e3a6d7451d57a8a1fc1943502b7b2b7"
     }
+  },
+  "operator_current135_refresh": {
+    "schema": "compressionbenchmark-operator-byte-effect-current135-patch-v1",
+    "status": "candidate_incomplete_legacy_column_coverage",
+    "coverage": {
+      "column_complete_identity_count": 128,
+      "expected_recipe_key_count": 35190,
+      "incomplete_identities": [
+        "goes_omni_electron_flux_forecasting",
+        "knowable",
+        "kraken-trading-data",
+        "polymarket_crypto_5m_15m",
+        "quitobench",
+        "salesforecastingwomartstore",
+        "wids2023_competition_weather_forecasting"
+      ],
+      "missing_recipe_key_count": 4000,
+      "observed_recipe_key_count": 31190,
+      "scope_identity_count": 135
+    },
+    "timing_fields_all_null": true,
+    "input_version_boundary": "Archived measurements are reused where their canonical column keys match. Key coverage alone does not certify current input byte identity. The 540 new rows use current canonical inputs.",
+    "summary": {
+      "file": "operator-byte-effect-current135-summary.json",
+      "sha256": "a33ce425eaca3af0d10879fcfd76a9d83b36a47b0447d8c1eb38dd25db2c3bd5"
+    },
+    "delta": {
+      "file": "operator_byte_effect_current135_new540.public.csv.gz",
+      "sha256": "898de6be028fc1629d158f3e1d4ded766085b114dbc04961b2375ab54c2e0c08",
+      "row_count": 540
+    },
+    "historical_operator_evidence_preserved": true,
+    "native_results_unchanged": true
   }
 }

operator-byte-effect-current135-summary.json ADDED Viewed

	@@ -0,0 +1,1163 @@

+{
+  "claim_boundary": "value-column matched omissions only; byte effects only; no timing ranking",
+  "coverage": {
+    "column_complete_identity_count": 128,
+    "expected_recipe_key_count": 35190,
+    "incomplete_identities": [
+      "goes_omni_electron_flux_forecasting",
+      "knowable",
+      "kraken-trading-data",
+      "polymarket_crypto_5m_15m",
+      "quitobench",
+      "salesforecastingwomartstore",
+      "wids2023_competition_weather_forecasting"
+    ],
+    "missing_recipe_key_count": 4000,
+    "observed_recipe_key_count": 31190,
+    "scope_identity_count": 135
+  },
+  "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are frozen historical-input evidence without full current-input SHA requalification",
+  "current_input_qualified": false,
+  "publish_as_full_current135": false,
+  "rows": [
+    {
+      "admitted_dataset_count": 56,
+      "admitted_value_column_count": 1329,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 56,
+      "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",
+        "hourly-stock-data-2023",
+        "indian_stock_hourly_2017_2021",
+        "kuiper_fleet_data",
+        "meteoblue",
+        "multi_model_trading_data",
+        "nifty50_market_regime",
+        "omie_blockchain_study",
+        "ooni_censorship_historical",
+        "orbital_chaos_nasa_ssc",
+        "phenology_normal_hawaii",
+        "rating",
+        "reg_forecasting_v2",
+        "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",
+        "wordle_mcm_dataset",
+        "xauusd",
+        "xauusd_1m"
+      ],
+      "diagnostic_recipe_id": "corad_tricklet_dictionary_pair_v1",
+      "display_label": "Dictionary",
+      "mean_baseline_to_original_ratio": 3.4948208685494295,
+      "mean_byte_change_percent": -13.095640973697764,
+      "mean_omission_to_baseline_ratio": 0.8690435902630224,
+      "mean_omission_to_original_ratio": 2.659056670350407,
+      "mean_rate_multiple_after_over_before": 0.8690435902630224,
+      "omitted_operator": "dictionary",
+      "operator": "Dictionary",
+      "row_count": 1329,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 51,
+      "admitted_value_column_count": 940,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 51,
+      "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",
+        "hourly-stock-data-2023",
+        "indian_stock_hourly_2017_2021",
+        "kuiper_fleet_data",
+        "meteoblue",
+        "multi_model_trading_data",
+        "ooni_censorship_historical",
+        "orbital_chaos_nasa_ssc",
+        "rating",
+        "reg_forecasting_v2",
+        "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",
+        "wordle_mcm_dataset",
+        "xauusd_1m"
+      ],
+      "diagnostic_recipe_id": "fpzip_range_pair_v1",
+      "display_label": "Range (FPZIP)",
+      "mean_baseline_to_original_ratio": 1.764558121242927,
+      "mean_byte_change_percent": 32.39224599395219,
+      "mean_omission_to_baseline_ratio": 1.3239224599395218,
+      "mean_omission_to_original_ratio": 1.6872916494065884,
+      "mean_rate_multiple_after_over_before": 1.3239224599395218,
+      "omitted_operator": "entropy_range",
+      "operator": "Range (FPZIP)",
+      "row_count": 940,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 56,
+      "admitted_value_column_count": 1329,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 56,
+      "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",
+        "hourly-stock-data-2023",
+        "indian_stock_hourly_2017_2021",
+        "kuiper_fleet_data",
+        "meteoblue",
+        "multi_model_trading_data",
+        "nifty50_market_regime",
+        "omie_blockchain_study",
+        "ooni_censorship_historical",
+        "orbital_chaos_nasa_ssc",
+        "phenology_normal_hawaii",
+        "rating",
+        "reg_forecasting_v2",
+        "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",
+        "wordle_mcm_dataset",
+        "xauusd",
+        "xauusd_1m"
+      ],
+      "diagnostic_recipe_id": "gorilla_trailing_pack_pair_v1",
+      "display_label": "Trailing-zero pack",
+      "mean_baseline_to_original_ratio": 1.4522106782047373,
+      "mean_byte_change_percent": 156.69981630146333,
+      "mean_omission_to_baseline_ratio": 2.5669981630146332,
+      "mean_omission_to_original_ratio": 1.6024096893265105,
+      "mean_rate_multiple_after_over_before": 2.5669981630146332,
+      "omitted_operator": "trailing_zero_pack",
+      "operator": "Trailing-zero pack",
+      "row_count": 1329,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 128,
+      "admitted_value_column_count": 2786,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 128,
+      "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",
+        "greatplains_multisource_2000_2024",
+        "hourly-stock-data-2023",
+        "hourly_electricity_demand_brazil",
+        "indian_stock_hourly_2017_2021",
+        "job_claims",
+        "jolts",
+        "kdd_cup_2018",
+        "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",
+        "port_activity",
+        "rating",
+        "reg_forecasting_v2",
+        "rideshare",
+        "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",
+        "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": 7.327518427959965,
+      "mean_byte_change_percent": 15.816119420289354,
+      "mean_omission_to_baseline_ratio": 1.1581611942028935,
+      "mean_omission_to_original_ratio": 1.958199248151619,
+      "mean_rate_multiple_after_over_before": 1.1581611942028935,
+      "omitted_operator": "entropy_range",
+      "operator": "Arithmetic",
+      "row_count": 2786,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 128,
+      "admitted_value_column_count": 2786,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 128,
+      "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",
+        "greatplains_multisource_2000_2024",
+        "hourly-stock-data-2023",
+        "hourly_electricity_demand_brazil",
+        "indian_stock_hourly_2017_2021",
+        "job_claims",
+        "jolts",
+        "kdd_cup_2018",
+        "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",
+        "port_activity",
+        "rating",
+        "reg_forecasting_v2",
+        "rideshare",
+        "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",
+        "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": 7.314033028147805,
+      "mean_byte_change_percent": 10.849788409773709,
+      "mean_omission_to_baseline_ratio": 1.108497884097737,
+      "mean_omission_to_original_ratio": 1.958199248151619,
+      "mean_rate_multiple_after_over_before": 1.108497884097737,
+      "omitted_operator": "entropy_huffman",
+      "operator": "Huffman",
+      "row_count": 2786,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 128,
+      "admitted_value_column_count": 2786,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 128,
+      "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",
+        "greatplains_multisource_2000_2024",
+        "hourly-stock-data-2023",
+        "hourly_electricity_demand_brazil",
+        "indian_stock_hourly_2017_2021",
+        "job_claims",
+        "jolts",
+        "kdd_cup_2018",
+        "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",
+        "port_activity",
+        "rating",
+        "reg_forecasting_v2",
+        "rideshare",
+        "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",
+        "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": 5.200104963731671,
+      "mean_byte_change_percent": 27.216548833456102,
+      "mean_omission_to_baseline_ratio": 1.272165488334561,
+      "mean_omission_to_original_ratio": 1.958199248151619,
+      "mean_rate_multiple_after_over_before": 1.272165488334561,
+      "omitted_operator": "entropy_fse",
+      "operator": "rANS",
+      "row_count": 2786,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 128,
+      "admitted_value_column_count": 2786,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 128,
+      "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",
+        "greatplains_multisource_2000_2024",
+        "hourly-stock-data-2023",
+        "hourly_electricity_demand_brazil",
+        "indian_stock_hourly_2017_2021",
+        "job_claims",
+        "jolts",
+        "kdd_cup_2018",
+        "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",
+        "port_activity",
+        "rating",
+        "reg_forecasting_v2",
+        "rideshare",
+        "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",
+        "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": 3.278490608331889,
+      "mean_byte_change_percent": 55.78277133839909,
+      "mean_omission_to_baseline_ratio": 1.5578277133839908,
+      "mean_omission_to_original_ratio": 1.958199248151619,
+      "mean_rate_multiple_after_over_before": 1.5578277133839908,
+      "omitted_operator": "run_length",
+      "operator": "Run length",
+      "row_count": 2786,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 128,
+      "admitted_value_column_count": 2786,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 128,
+      "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",
+        "greatplains_multisource_2000_2024",
+        "hourly-stock-data-2023",
+        "hourly_electricity_demand_brazil",
+        "indian_stock_hourly_2017_2021",
+        "job_claims",
+        "jolts",
+        "kdd_cup_2018",
+        "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",
+        "port_activity",
+        "rating",
+        "reg_forecasting_v2",
+        "rideshare",
+        "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",
+        "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": 4.468813626913821,
+      "mean_byte_change_percent": 65.91895270779634,
+      "mean_omission_to_baseline_ratio": 1.6591895270779633,
+      "mean_omission_to_original_ratio": 3.5963246363759165,
+      "mean_rate_multiple_after_over_before": 1.6591895270779633,
+      "omitted_operator": "match_token_format",
+      "operator": "Match tokens",
+      "row_count": 2786,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 56,
+      "admitted_value_column_count": 1329,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 56,
+      "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",
+        "hourly-stock-data-2023",
+        "indian_stock_hourly_2017_2021",
+        "kuiper_fleet_data",
+        "meteoblue",
+        "multi_model_trading_data",
+        "nifty50_market_regime",
+        "omie_blockchain_study",
+        "ooni_censorship_historical",
+        "orbital_chaos_nasa_ssc",
+        "phenology_normal_hawaii",
+        "rating",
+        "reg_forecasting_v2",
+        "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",
+        "wordle_mcm_dataset",
+        "xauusd",
+        "xauusd_1m"
+      ],
+      "diagnostic_recipe_id": "spdp_entropy_pair_v1",
+      "display_label": "Special (SPDP)",
+      "mean_baseline_to_original_ratio": 1.9050360007172102,
+      "mean_byte_change_percent": 76.40850488023496,
+      "mean_omission_to_baseline_ratio": 1.7640850488023496,
+      "mean_omission_to_original_ratio": 1.9496274411841512,
+      "mean_rate_multiple_after_over_before": 1.7640850488023496,
+      "omitted_operator": "entropy_special",
+      "operator": "Special (SPDP)",
+      "row_count": 1329,
+      "status": "ok"
+    },
+    {
+      "admitted_dataset_count": 38,
+      "admitted_value_column_count": 389,
+      "aggregation": "sum supported column bytes within dataset, then equal dataset mean",
+      "current_input_qualification_boundary": "new 540 rows are current-manifest-bound; retained legacy rows are not fully requalified against current input SHA",
+      "current_input_qualified": false,
+      "dataset_count": 38,
+      "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",
+        "hourly-stock-data-2023",
+        "kuiper_fleet_data",
+        "multi_model_trading_data",
+        "nifty50_market_regime",
+        "omie_blockchain_study",
+        "ooni_censorship_historical",
+        "phenology_normal_hawaii",
+        "rating",
+        "reg_forecasting_v2",
+        "sleep_score_fitbit",
+        "spx",
+        "stock_dataset",
+        "timeseries-1m-QQQ-10y",
+        "tourism_monthly-zaai-ai",
+        "uk_electricity_generation_mix_2019_2026",
+        "wordle_mcm_dataset",
+        "xauusd",
+        "xauusd_1m"
+      ],
+      "diagnostic_recipe_id": "stream_vbyte_integer_code_pair_v1",
+      "display_label": "Integer code",
+      "mean_baseline_to_original_ratio": 0.8751983665957126,
+      "mean_byte_change_percent": 103.0484539866046,
+      "mean_omission_to_baseline_ratio": 2.030484539866046,
+      "mean_omission_to_original_ratio": 1.2869761160123128,
+      "mean_rate_multiple_after_over_before": 2.030484539866046,
+      "omitted_operator": "integer_code",
+      "operator": "Integer code",
+      "row_count": 389,
+      "status": "ok"
+    }
+  ],
+  "schema": "compressionbenchmark-operator-byte-effect-current135-patch-v1",
+  "source_delta": {
+    "base_file": "operator-byte-effect-full-union.csv.gz",
+    "base_logical_sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2",
+    "compressed_bytes": 31987,
+    "compressed_sha256": "898de6be028fc1629d158f3e1d4ded766085b114dbc04961b2375ab54c2e0c08",
+    "field_count": 49,
+    "file": "operator_byte_effect_current135_new540.public.csv.gz",
+    "key_fields": [
+      "dataset_id",
+      "column_id",
+      "diagnostic_recipe_id"
+    ],
+    "local_full_delta_sha256": "75f70f7031bd37bc0b14ae820431c66bfef087ec8caec1c7cd58f1b92c1dee3b",
+    "merge_rule": "filter base to current135 canonical role=value keys and append delta; duplicate keys are invalid",
+    "omitted_large_fields": [
+      "baseline_frame_sha256_by_segment",
+      "omission_frame_sha256_by_segment",
+      "baseline_frame_bytes_by_segment",
+      "omission_frame_bytes_by_segment"
+    ],
+    "row_count": 540,
+    "timing_fields": {
+      "all_null": true,
+      "count": 18
+    },
+    "base_compressed_sha256": "c6962b9e57a59b50a2e4fa0dc0db9789541a763ea46f4b0cfb7cafd3b88dd22d"
+  },
+  "source_union_sha256": "ff9606947ad4d328874e033203957fd01d3b226faa050a25989f26b174628849",
+  "status": "candidate_incomplete_legacy_column_coverage",
+  "timing_fields_all_null": true,
+  "input_version_boundary": "Archived measurements are reused where their canonical column keys match. Key coverage alone does not certify current input byte identity. The 540 new rows use current canonical inputs."
+}

operator_byte_effect_current135_new540.public.csv.gz ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:898de6be028fc1629d158f3e1d4ded766085b114dbc04961b2375ab54c2e0c08
+size 31987