jzxiao commited on
Commit
2649daa
·
verified ·
1 Parent(s): c0ffced

Update accepted BOS REGER and Sub-column results for 200 datasets

Browse files

Use the latest complete lossless-verified results for BOS, REGER, and Sub-column. Preserve all historical records and all other current measurements. Bind the result assets to immutable revision 5511b6a3a1cdb5a002795e36de0915a1588504df; keep existing metric and score definitions.

Files changed (6) hide show
  1. LATEST_THREE200_ACCEPTANCE.json +46 -0
  2. README.md +4 -2
  3. app.js +10 -10
  4. index.html +4 -4
  5. manifest.json +373 -1
  6. project200-scope.js +1 -1
LATEST_THREE200_ACCEPTANCE.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "candidate": {
3
+ "current_data_sha256": "25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5",
4
+ "sidecar_sha256": "65a04e9e7704e7a9a2847216dad4a5ab5f4f57077754790250f9711d817d5a7c",
5
+ "ui_data_sha256": "2534a59a84f8acc9c80530f017238c520ea810c9761e98ee82b4e5552fc3b6bc"
6
+ },
7
+ "failed_columns": 0,
8
+ "input_identity_equal_across_targets": true,
9
+ "metric_contract": {
10
+ "column_mean_compression_rate": "arithmetic mean of per-column complete_frame_bytes / canonical_input_bytes",
11
+ "compression_rate": "sum(complete_frame_bytes) / sum(canonical_input_bytes)",
12
+ "compression_rate_source_native": "sum(complete_frame_bytes) / sum(source_native_numeric_bytes)",
13
+ "compression_time_ns_per_point": "arithmetic mean of per-column compression_time_ns_per_valid_value",
14
+ "decompression_time_ns_per_point": "arithmetic mean of per-column decompression_time_ns_per_valid_value",
15
+ "website_manuscript_boundary": "The website primary rate uses the pooled canonical-input denominator; the manuscript's native-denominator column mean is a distinct metric and is not substituted for it."
16
+ },
17
+ "native_and_cold_bit_exact_all_columns": true,
18
+ "preservation_receipt_sha256": "7ac8cf0e91f054d070cab6f788991f2b08c62c9a89a20ef3a23c1d81f07f7b1a",
19
+ "schema": "latest-three200-site-acceptance-v1",
20
+ "scope": {
21
+ "columns_per_method": 3723,
22
+ "datasets": 200,
23
+ "methods": 86,
24
+ "operators": 97
25
+ },
26
+ "source_results_audit_sha256": "3e4434f898b5986795d9fd8beb86f6eb68391f48fc7f19510802db6ef05195e0",
27
+ "space_parent_revision": "c0ffced61ef3d4fcfb6bc6621a54caf315d32ce8",
28
+ "status": "accepted_local_candidate_not_published",
29
+ "targets": {
30
+ "BOS": {
31
+ "acceptance_sha256": "6fe2c5d7774a64d2dec1693034959b378ea958ddcaa8dce91900703bd216d621",
32
+ "binary_sha256": "22ed503e9dc8e01a7926d0756d34f5fab4341c5f584a0108e21e059939150a7d",
33
+ "column_results_sha256": "f1d077cf310c0f957694ff26941790e85315a3a482c2c86e83e53948b9817166"
34
+ },
35
+ "REGER": {
36
+ "acceptance_sha256": "2f69142e6ef1cff4a22fd230445d6397408a51bce06fa2761cf24fad932330e6",
37
+ "binary_sha256": "d250bca3cbb621c78c2a3bd7ef1fac1e2e88aab63086400004de0ce1b9e1a615",
38
+ "column_results_sha256": "29a7554534bd308e0810b34a93357064ca48034b36f7e1e8ce749b9e79896673"
39
+ },
40
+ "Sub-column": {
41
+ "acceptance_sha256": "aa8b2f53dd0e65127ce849ce3120c1a3277694b28da42ffe5e6129cbbfc8fc4c",
42
+ "binary_sha256": "2c4acc731a67abdc9bb9e49f2d0fd12a2aceaea49c30e8486c785bcd44398f03",
43
+ "column_results_sha256": "b5dcb39803bd9d1d9cf0304d80fa2c2b1d06c9c96dd09d9adc37eb1b865807bb"
44
+ }
45
+ }
46
+ }
README.md CHANGED
@@ -10,7 +10,7 @@ pinned: false
10
 
11
  # THULab Time Series Compression Benchmark
12
 
13
- The active benchmark scope contains **200 measured datasets**, **85 compression algorithms**, and **97 active operator implementations**. Every displayed algorithm result is bound to accepted bit-exact evidence. Unsupported and not-applicable outcomes remain explicit and do not participate in rankings.
14
 
15
  Compression rate is complete compressed-frame bytes divided by canonical numerical input bytes. Timestamps, identifiers, labels, and other metadata are excluded from the numerical payload. Compression and decompression timing uses each result's receipt-bound W1/R3/T1 contract. The combined C++ view selects the latest accepted authority atomically for each dataset and method; historical rows remain preserved.
16
 
@@ -24,4 +24,6 @@ Current C++ algorithm measurements and current operator measurements remove NULL
24
 
25
  ## Immutable result assets
26
 
27
- The current clean-input payloads are served from the immutable `THULab/TSCB_dataset` revision `eb44d8917c982e9a6fa283bdee1ff894a406d8ff` under `benchmark-results/clean200_20261025_v4/`. The page verifies both compressed and decompressed SHA-256 bindings before using the data. This transport-only placement preserves all scientific bytes and leaves the Space's existing historical files and Git history intact.
 
 
 
10
 
11
  # THULab Time Series Compression Benchmark
12
 
13
+ The active benchmark scope contains **200 measured datasets**, **86 compression algorithms**, and **97 active operator implementations**. Every displayed algorithm result is bound to accepted bit-exact evidence. Unsupported and not-applicable outcomes remain explicit and do not participate in rankings.
14
 
15
  Compression rate is complete compressed-frame bytes divided by canonical numerical input bytes. Timestamps, identifiers, labels, and other metadata are excluded from the numerical payload. Compression and decompression timing uses each result's receipt-bound W1/R3/T1 contract. The combined C++ view selects the latest accepted authority atomically for each dataset and method; historical rows remain preserved.
16
 
 
24
 
25
  ## Immutable result assets
26
 
27
+ The current clean-input payloads are served from the immutable `THULab/TSCB_dataset` revision `5511b6a3a1cdb5a002795e36de0915a1588504df` under `benchmark-results/clean200_latest_three_20261029_v1/`. The page verifies both compressed and decompressed SHA-256 bindings before using the data. This transport-only placement preserves all scientific bytes and leaves the Space's existing historical files and Git history intact.
28
+
29
+ The latest accepted Clean200 BOS, REGER, and Sub-column results are integrated from complete 3,723-column W1/R3/T1 campaigns with native and independent cold-process bit-exact recovery. The website primary compression rate is pooled complete-frame bytes divided by pooled canonical-input bytes; the per-column canonical mean and pooled source-native-denominator rate remain separate fields. Compression and decompression times are equal-column means in ns per valid value. This website rate is distinct from the manuscript's native-denominator column mean and is not substituted for it.
app.js CHANGED
@@ -1,15 +1,15 @@
1
- import {PROJECT200_SCOPE,PROJECT200_INPUT_STATUS,applyProject200Scope,filterProject200Catalog,project200CoverageForFamily} from './project200-scope.js?v=20261025-clean200-v1';
2
  import {WEIGHT_TENTHS,parseWeights,addRankingMetrics} from './ranking.js?v=20261021-bos-reger-rank85-v1';
3
  import {DEFAULT_PROFILE,profileLabel,defaultColumnVisible,metricAvailability,summarizeAvailability,visibleColumns,profileScopeText,aggregateTimedSubset,strictTimingMode} from './availability.js?v=20261023-clean150-v1-ui-scope2';
4
- const UI_DATA_SHA256='160e49e5afcb8a27e0e48e311fe1838d70930782d659dc5c444b9b0f4faebf59';
5
- const UI_DATA_GZIP_SHA256='c2f0f46fc5c715af4da8f43101cada390c32e10e04f9fdbfb5e8896723daab65';
6
- const CPP_LATEST_VIEW_SHA256='f6ba04065b400361ba6e7da93b4e336d02cd03687448f1f337738d533505edb2';
7
- const CPP_LATEST_VIEW_GZIP_SHA256='1a36afc4f34ef09d4e71f76a95c3ae4b42026a1cc31a4006d457143c582a4762';
8
  const OPERATOR97_SHA256='370a01786db4d034d49117ee76c5f8999a9514192ee61ebca7151bed481739e0';
9
  const OPERATOR97_GZIP_SHA256='0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00';
10
  const DATASET_CATALOG_SHA256='e25642fe1d87ab0bb595a391f4582c43ab94b9d6ae5ebd2be9903ccf261c1fd2';
11
  const DATASET_CATALOG_GZIP_SHA256='b6d261c84e236efba34618975db37fb481f60e50e5682074fd103d784c1bb9f4';
12
- const CLEAN200_ASSET_BASE='https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4';
13
  const clean200AssetUrl=(name)=>`${CLEAN200_ASSET_BASE}/${name}`;
14
  const $ = (id) => document.getElementById(id);
15
  const escape = (value) => String(value ?? '').replace(/[&<>"']/g, (c) => ({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c]));
@@ -424,7 +424,7 @@ async function loadDatasetCatalog() {
424
  }
425
  function renderAbout() {
426
  const b=snapshot.benchmark||{},s=snapshot.source||{},c=snapshot.coverage||{};
427
- const notes=['The active benchmark scope contains 200 datasets with accepted numerical measurements for 85 compression algorithms and 97 active operator implementations. Unsupported and N/A outcomes are explicit and never participate in rankings.',b.aggregation_note,b.selection_note,...(b.notes||[]),...(b.measurement_boundaries||[])].filter(Boolean);
428
  $('methodology').innerHTML=notes.map(n=>`<p class="notice">${escape(n)}</p>`).join('');
429
  const definitions=b.metric_definitions||{};if(Object.keys(definitions).length)$('methodology').innerHTML+=`<dl class="definitions">${Object.entries(definitions).map(([k,v])=>`<div><dt>${escape(k.replaceAll('_',' '))}</dt><dd>${escape(typeof v==='string'?v:JSON.stringify(v))}</dd></div>`).join('')}</dl>`;
430
  const exclusions=c.exclusions||c.excluded_datasets||snapshot.exclusions||[];
@@ -438,10 +438,10 @@ function decodeCompactRecord(row,index) {
438
  return {_compact_index:index,dataset:t.datasets[row[0]],scope:t.scopes[row[1]],runtime:t.runtimes[row[2]],comparison_profile:t.comparison_profiles[row[3]],family:t.families[row[4]],method:t.configurations[row[5]],algorithm_variant:t.configurations[row[5]],compression_rate:row[6],compression_time_ns_per_point:row[7],decompression_time_ns_per_point:row[8],original_size_bytes:row[9],compressed_size_bytes:row[10],timing_column_count:row[11],timing_aggregation:t.timing_aggregations[row[12]],eligible_column_set_sha256:t.support_sets[row[13]],measurement_status:t.measurement_statuses[row[14]],timing_profile_status:t.timing_statuses[row[15]],binary_sha256:t.binary_hashes[row[16]]};
439
  }
440
  function applyCppLatestView() {
441
- if(!cppLatestView||cppLatestView.schema!=='compressionbenchmark-cpp-latest-view-v1'||cppLatestView.status!=='built_from_accepted_clean200_results_v1')throw new Error('The combined C++ selection sidecar has an invalid schema or status.');
442
  const compact=snapshot.compact_records;if(!Array.isArray(compact))throw new Error('The SHA-bound compact record table is missing.');
443
- if(cppLatestView.baseline?.compact_record_count!==153219||compact.length!==191299)throw new Error('The Clean200 compact-record prefix or final count is invalid.');
444
- if(snapshot.source_data_sha256!=='18a96a681dbddfe1aef51108f1399f836b970391891ed1d051bc6cdce81bf7fe'||cppLatestView.cpp?.counts?.clean200_accepted_dataset_family_pair_count!==17000)throw new Error('The Clean200 selection sidecar binding is invalid.');
445
  const selectors=cppLatestView.selectors;if(!Array.isArray(selectors)||selectors.join('\0')!=='cpp\0java\0python')throw new Error('The combined view must expose exactly C++, Java, and Python.');
446
  const selected=cppLatestView.cpp?.selected_rows;if(!Array.isArray(selected))throw new Error('The combined C++ selected-row index is missing.');
447
  const seen=new Set(),cpp=[];
 
1
+ import {PROJECT200_SCOPE,PROJECT200_INPUT_STATUS,applyProject200Scope,filterProject200Catalog,project200CoverageForFamily} from './project200-scope.js?v=20261029-latest-three200-v1';
2
  import {WEIGHT_TENTHS,parseWeights,addRankingMetrics} from './ranking.js?v=20261021-bos-reger-rank85-v1';
3
  import {DEFAULT_PROFILE,profileLabel,defaultColumnVisible,metricAvailability,summarizeAvailability,visibleColumns,profileScopeText,aggregateTimedSubset,strictTimingMode} from './availability.js?v=20261023-clean150-v1-ui-scope2';
4
+ const UI_DATA_SHA256='2534a59a84f8acc9c80530f017238c520ea810c9761e98ee82b4e5552fc3b6bc';
5
+ const UI_DATA_GZIP_SHA256='5bc9f4640232f238463d88d643b267625af06f75382294570ae20471e24ace09';
6
+ const CPP_LATEST_VIEW_SHA256='65a04e9e7704e7a9a2847216dad4a5ab5f4f57077754790250f9711d817d5a7c';
7
+ const CPP_LATEST_VIEW_GZIP_SHA256='99bf6329af9745899349eca91d161cf867d03d0ebe28d46a9482c0de8b4db560';
8
  const OPERATOR97_SHA256='370a01786db4d034d49117ee76c5f8999a9514192ee61ebca7151bed481739e0';
9
  const OPERATOR97_GZIP_SHA256='0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00';
10
  const DATASET_CATALOG_SHA256='e25642fe1d87ab0bb595a391f4582c43ab94b9d6ae5ebd2be9903ccf261c1fd2';
11
  const DATASET_CATALOG_GZIP_SHA256='b6d261c84e236efba34618975db37fb481f60e50e5682074fd103d784c1bb9f4';
12
+ const CLEAN200_ASSET_BASE='https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1';
13
  const clean200AssetUrl=(name)=>`${CLEAN200_ASSET_BASE}/${name}`;
14
  const $ = (id) => document.getElementById(id);
15
  const escape = (value) => String(value ?? '').replace(/[&<>"']/g, (c) => ({'&':'&amp;','<':'&lt;','>':'&gt;','"':'&quot;',"'":'&#39;'}[c]));
 
424
  }
425
  function renderAbout() {
426
  const b=snapshot.benchmark||{},s=snapshot.source||{},c=snapshot.coverage||{};
427
+ const notes=['The active benchmark scope contains 200 datasets with accepted numerical measurements for 86 compression algorithms and 97 active operator implementations. Unsupported and N/A outcomes are explicit and never participate in rankings.',b.aggregation_note,b.selection_note,...(b.notes||[]),...(b.measurement_boundaries||[])].filter(Boolean);
428
  $('methodology').innerHTML=notes.map(n=>`<p class="notice">${escape(n)}</p>`).join('');
429
  const definitions=b.metric_definitions||{};if(Object.keys(definitions).length)$('methodology').innerHTML+=`<dl class="definitions">${Object.entries(definitions).map(([k,v])=>`<div><dt>${escape(k.replaceAll('_',' '))}</dt><dd>${escape(typeof v==='string'?v:JSON.stringify(v))}</dd></div>`).join('')}</dl>`;
430
  const exclusions=c.exclusions||c.excluded_datasets||snapshot.exclusions||[];
 
438
  return {_compact_index:index,dataset:t.datasets[row[0]],scope:t.scopes[row[1]],runtime:t.runtimes[row[2]],comparison_profile:t.comparison_profiles[row[3]],family:t.families[row[4]],method:t.configurations[row[5]],algorithm_variant:t.configurations[row[5]],compression_rate:row[6],compression_time_ns_per_point:row[7],decompression_time_ns_per_point:row[8],original_size_bytes:row[9],compressed_size_bytes:row[10],timing_column_count:row[11],timing_aggregation:t.timing_aggregations[row[12]],eligible_column_set_sha256:t.support_sets[row[13]],measurement_status:t.measurement_statuses[row[14]],timing_profile_status:t.timing_statuses[row[15]],binary_sha256:t.binary_hashes[row[16]]};
439
  }
440
  function applyCppLatestView() {
441
+ if(!cppLatestView||cppLatestView.schema!=='compressionbenchmark-cpp-latest-view-v1'||cppLatestView.status!=='built_from_latest_three_accepted_clean200_results_v1')throw new Error('The combined C++ selection sidecar has an invalid schema or status.');
442
  const compact=snapshot.compact_records;if(!Array.isArray(compact))throw new Error('The SHA-bound compact record table is missing.');
443
+ if(cppLatestView.baseline?.compact_record_count!==153219||compact.length!==192643)throw new Error('The Clean200 compact-record prefix or final count is invalid.');
444
+ if(snapshot.source_data_sha256!=='25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5'||cppLatestView.cpp?.counts?.clean200_accepted_dataset_family_pair_count!==17200)throw new Error('The Clean200 selection sidecar binding is invalid.');
445
  const selectors=cppLatestView.selectors;if(!Array.isArray(selectors)||selectors.join('\0')!=='cpp\0java\0python')throw new Error('The combined view must expose exactly C++, Java, and Python.');
446
  const selected=cppLatestView.cpp?.selected_rows;if(!Array.isArray(selected))throw new Error('The combined C++ selected-row index is missing.');
447
  const seen=new Set(),cpp=[];
index.html CHANGED
@@ -7,7 +7,7 @@
7
  <meta name="color-scheme" content="light dark">
8
  <title>THULab | Time Series Compression Benchmark</title>
9
  <link rel="stylesheet" href="style.css?v=20261019-operator97-v1">
10
- <script src="app.js?v=20261025-clean200-v1" type="module"></script>
11
  </head>
12
  <body>
13
  <a class="skip-link" href="#content">Skip to results</a>
@@ -16,7 +16,7 @@
16
  <div class="header-links"><a href="https://github.com/xjz17/web_compression" target="_blank" rel="noopener">Project code ↗</a><button id="theme" class="quiet-button" type="button" aria-label="Switch color theme">Theme</button></div>
17
  </header>
18
  <main id="content">
19
- <section class="snapshot-notice" aria-label="Current benchmark scope"><strong>Test scope: 200 measured datasets</strong><p>Current C++ clean-input results use per-column NULL and NaN removal for 85 compression algorithms; current operator results cover 97 implementations. Historical Java and Python views retain their original input contracts. Unsupported and N/A outcomes are explicit and never rank.</p><a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/dataset-catalog.json.gz?download=true" download>Dataset catalog</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/algorithm200-current-dataset-results.jsonl.gz?download=true" download>Current measurements</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/current-clean200-data.json.gz?download=true" download>Current complete data (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/clean200-dataset-statistics.json.gz?download=true" download>Clean-input dataset statistics (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/ASSET_MANIFEST.json?download=true" download>Immutable asset manifest</a> · <a href="manifest.json" download>Release manifest</a></section>
20
 
21
  <section class="intro" aria-labelledby="title">
22
  <p class="eyebrow">Time-series systems research</p>
@@ -101,7 +101,7 @@
101
  <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>
102
  </div>
103
  <section id="operator97-results" class="operator-effect-results" aria-labelledby="operator97-title">
104
- <div class="operator-effect-head"><div><h3 id="operator97-title">H0 entropy, third-order Markov entropy, and paired ablation · 200 datasets</h3><p class="muted">The same full-data pass produced all three measurements for 97 implementations. H0 and Markov values are operator-present minus operator-input bits per valid value. The paired ablation is operator-present minus operator-omitted Zstd level 3 bits per valid value. Overall dataset-equal means are populated only for the exact full-200 support cohort. Domain-limited implementations keep per-dataset values but have no overall score or rank.</p></div><div class="operator97-downloads"><button class="quiet-button" id="operator97-download-csv" type="button">Download CSV</button><a class="quiet-button" href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/operator97-project200-summary.json.gz?download=true" download="operator97-project200-results.json.gz">Download JSON</a></div></div>
105
  <div class="operator97-controls"><label>Dataset<select id="operator97-dataset"><option value="all">All 200 datasets · dataset-equal means</option></select></label><label>Find implementation<input id="operator97-search" type="search" placeholder="A-ID, implementation, or family" autocomplete="off"></label></div>
106
  <p id="operator97-status" class="documentation-status" aria-live="polite">Loading Operator97 results…</p>
107
  <div class="table-wrap operator-effect-table-wrap"><table id="operator97-table"><thead><tr><th>Implementation</th><th>H0 Δ bits/value</th><th>Markov-3 Δ bits/value</th><th>Zstd-3 ablation Δ bits/value</th><th>Present / omitted bytes</th><th>Executable support</th><th>Status</th><th>Support cohort</th></tr></thead><tbody><tr><td colspan="8" class="loading-cell">Loading Operator97 results…</td></tr></tbody></table></div>
@@ -137,7 +137,7 @@
137
  <p>By default, each family selects the lowest-rate exact variant independently for each dataset only when all candidates for that dataset/family have one exact support set. This view can choose different binaries across datasets. Ambiguous support sets are omitted. Switch Method rows to Exact configuration to inspect fixed variants, source profiles, binaries, and support hashes.</p>
138
  <p>These are published measurements, not experiments executed inside this Space. A reported ratio alone does not establish lossless reconstruction; round-trip checks and hardware details are shown only when their evidence exists in the source snapshot. Timings without an exact admitted source/build/binary/boundary chain are unavailable to timing and composite rankings.</p>
139
  <h3>Download and provenance</h3>
140
- <p><a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/ui-data-project200.json.gz?download=true" download>Current 200-dataset compact result snapshot (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/cpp-latest-view-project200.json.gz?download=true" download>Current C++ selection evidence (JSON.GZ)</a> · <a href="valid48-lzg-current135-dataset-method.csv.gz" download>Historical 48-codec timing and LZG base (CSV.GZ)</a> · <a href="lzg-bavaria-current135-completion-supplement.csv" download>Historical Bavaria LZG completion record (CSV)</a> · <a href="bos-reger-current135-scope-results.csv" download>Historical BOS/REGER 135-dataset results (CSV)</a> · <a href="bos-reger-current135-columns.json" download>Historical BOS/REGER column evidence (JSON)</a> · <a href="bos-reger-current135-ui-patch.json" download>Historical BOS/REGER compact result overlay (JSON)</a> · <a href="bos-reger-current135-selection-patch.json" download>Historical BOS/REGER selection overlay (JSON)</a><br><span class="muted">The interactive page verifies the frozen 200-dataset compact result snapshot and its receipt-bound selection evidence. Use Download CSV above for the currently displayed merged rows.</span> · <a href="remaining6-completed5-dataset-method-overlay.jsonl.gz" download>Historical C++ timing overlay (JSONL.GZ)</a> · <a href="manifest.json" download>Source manifest (JSON)</a> · <a href="native86-coverage.json" download>Native86 coverage summary (JSON)</a> · <a href="native86-terminal-matrix.jsonl.gz" download>Historical 164-dataset terminal matrix (JSONL.GZ)</a> · <a href="native86-v9-current154-thin.jsonl.gz" download>Historical 154-pair V9 evidence (JSONL.GZ)</a> · <a href="native86-recovery-reconciliation.json" download>Recovery reconciliation (JSON)</a></p>
141
  <div id="provenance"></div>
142
  <h3>Contribute a result</h3>
143
  <p>Run the project benchmark and provide the codec/configuration, input identity, compression and decompression measurements, execution environment, and round-trip validation evidence. Results can be updated from the source project using the snapshot exporter included in the Space repository.</p>
 
7
  <meta name="color-scheme" content="light dark">
8
  <title>THULab | Time Series Compression Benchmark</title>
9
  <link rel="stylesheet" href="style.css?v=20261019-operator97-v1">
10
+ <script src="app.js?v=20261029-latest-three200-v1" type="module"></script>
11
  </head>
12
  <body>
13
  <a class="skip-link" href="#content">Skip to results</a>
 
16
  <div class="header-links"><a href="https://github.com/xjz17/web_compression" target="_blank" rel="noopener">Project code ↗</a><button id="theme" class="quiet-button" type="button" aria-label="Switch color theme">Theme</button></div>
17
  </header>
18
  <main id="content">
19
+ <section class="snapshot-notice" aria-label="Current benchmark scope"><strong>Test scope: 200 measured datasets</strong><p>Current C++ clean-input results use per-column NULL and NaN removal for 86 compression algorithms; current operator results cover 97 implementations. Historical Java and Python views retain their original input contracts. Unsupported and N/A outcomes are explicit and never rank.</p><a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/dataset-catalog.json.gz?download=true" download>Dataset catalog</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/algorithm200-current-dataset-results.jsonl.gz?download=true" download>Current measurements</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/current-clean200-data.json.gz?download=true" download>Current complete data (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/clean200-dataset-statistics.json.gz?download=true" download>Clean-input dataset statistics (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/ASSET_MANIFEST.json?download=true" download>Immutable asset manifest</a> · <a href="manifest.json" download>Release manifest</a></section>
20
 
21
  <section class="intro" aria-labelledby="title">
22
  <p class="eyebrow">Time-series systems research</p>
 
101
  <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>
102
  </div>
103
  <section id="operator97-results" class="operator-effect-results" aria-labelledby="operator97-title">
104
+ <div class="operator-effect-head"><div><h3 id="operator97-title">H0 entropy, third-order Markov entropy, and paired ablation · 200 datasets</h3><p class="muted">The same full-data pass produced all three measurements for 97 implementations. H0 and Markov values are operator-present minus operator-input bits per valid value. The paired ablation is operator-present minus operator-omitted Zstd level 3 bits per valid value. Overall dataset-equal means are populated only for the exact full-200 support cohort. Domain-limited implementations keep per-dataset values but have no overall score or rank.</p></div><div class="operator97-downloads"><button class="quiet-button" id="operator97-download-csv" type="button">Download CSV</button><a class="quiet-button" href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/operator97-project200-summary.json.gz?download=true" download="operator97-project200-results.json.gz">Download JSON</a></div></div>
105
  <div class="operator97-controls"><label>Dataset<select id="operator97-dataset"><option value="all">All 200 datasets · dataset-equal means</option></select></label><label>Find implementation<input id="operator97-search" type="search" placeholder="A-ID, implementation, or family" autocomplete="off"></label></div>
106
  <p id="operator97-status" class="documentation-status" aria-live="polite">Loading Operator97 results…</p>
107
  <div class="table-wrap operator-effect-table-wrap"><table id="operator97-table"><thead><tr><th>Implementation</th><th>H0 Δ bits/value</th><th>Markov-3 Δ bits/value</th><th>Zstd-3 ablation Δ bits/value</th><th>Present / omitted bytes</th><th>Executable support</th><th>Status</th><th>Support cohort</th></tr></thead><tbody><tr><td colspan="8" class="loading-cell">Loading Operator97 results…</td></tr></tbody></table></div>
 
137
  <p>By default, each family selects the lowest-rate exact variant independently for each dataset only when all candidates for that dataset/family have one exact support set. This view can choose different binaries across datasets. Ambiguous support sets are omitted. Switch Method rows to Exact configuration to inspect fixed variants, source profiles, binaries, and support hashes.</p>
138
  <p>These are published measurements, not experiments executed inside this Space. A reported ratio alone does not establish lossless reconstruction; round-trip checks and hardware details are shown only when their evidence exists in the source snapshot. Timings without an exact admitted source/build/binary/boundary chain are unavailable to timing and composite rankings.</p>
139
  <h3>Download and provenance</h3>
140
+ <p><a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/ui-data-project200.json.gz?download=true" download>Current 200-dataset compact result snapshot (JSON.GZ)</a> · <a href="https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/cpp-latest-view-project200.json.gz?download=true" download>Current C++ selection evidence (JSON.GZ)</a> · <a href="valid48-lzg-current135-dataset-method.csv.gz" download>Historical 48-codec timing and LZG base (CSV.GZ)</a> · <a href="lzg-bavaria-current135-completion-supplement.csv" download>Historical Bavaria LZG completion record (CSV)</a> · <a href="bos-reger-current135-scope-results.csv" download>Historical BOS/REGER 135-dataset results (CSV)</a> · <a href="bos-reger-current135-columns.json" download>Historical BOS/REGER column evidence (JSON)</a> · <a href="bos-reger-current135-ui-patch.json" download>Historical BOS/REGER compact result overlay (JSON)</a> · <a href="bos-reger-current135-selection-patch.json" download>Historical BOS/REGER selection overlay (JSON)</a><br><span class="muted">The interactive page verifies the frozen 200-dataset compact result snapshot and its receipt-bound selection evidence. Use Download CSV above for the currently displayed merged rows.</span> · <a href="remaining6-completed5-dataset-method-overlay.jsonl.gz" download>Historical C++ timing overlay (JSONL.GZ)</a> · <a href="manifest.json" download>Source manifest (JSON)</a> · <a href="native86-coverage.json" download>Native86 coverage summary (JSON)</a> · <a href="native86-terminal-matrix.jsonl.gz" download>Historical 164-dataset terminal matrix (JSONL.GZ)</a> · <a href="native86-v9-current154-thin.jsonl.gz" download>Historical 154-pair V9 evidence (JSONL.GZ)</a> · <a href="native86-recovery-reconciliation.json" download>Recovery reconciliation (JSON)</a></p>
141
  <div id="provenance"></div>
142
  <h3>Contribute a result</h3>
143
  <p>Run the project benchmark and provide the codec/configuration, input identity, compression and decompression measurements, execution environment, and round-trip validation evidence. Results can be updated from the source project using the snapshot exporter included in the Space repository.</p>
manifest.json CHANGED
@@ -1 +1,373 @@
1
- {"algorithm_source_sha256":"853264b4a65653226b6b3b4b894613fde50329dca6c915eeae206ad6d304fa0b","all_old_raw_records_preserved":true,"baseline_revision":"4111dc15fba5e9208d5fe5e66b5a03e48cbc0ed7","clean150_external_prefix_preserved":true,"current_data_file":"https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/current-clean200-data.json.gz","current_dataset_method_pairs":17000,"current_raw_records":191299,"current_scope_rows":38080,"data_sha256":"18a96a681dbddfe1aef51108f1399f836b970391891ed1d051bc6cdce81bf7fe","dataset_revision":"eb44d8917c982e9a6fa283bdee1ff894a406d8ff","dataset_statistics_recomputed_from_unique_accepted_columns":true,"delete_operations":[],"external_assets":{"asset_manifest_sha256":"51fc6ba94da0ef43faa5051fe230cc6277ef73918948292761c4520e272717c6","asset_manifest_url":"https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/ASSET_MANIFEST.json","assets":{"algorithm200-current-dataset-results.jsonl.gz":{"bytes":1834261,"compression":"gzip","decompressed_bytes":38472294,"decompressed_name":"algorithm200-current-dataset-results.jsonl","decompressed_sha256":"04e0b28d71e851ebc7feaaf1759db3d44b0f77da862384935390de437e879d22","sha256":"a6d4a54082c02db81812871a97ebb6c96fd197b699c805d39e82a5633dfdff25"},"clean200-dataset-statistics.json.gz":{"bytes":5666,"compression":"gzip","decompressed_bytes":39209,"decompressed_name":"clean200-dataset-statistics.json","decompressed_sha256":"6c87b8a27a092cb773a56e1b943b9b725138bfcf28f07922907993150a4cf250","sha256":"abc0f4b5d6a31ca281da52b9c1ff07847162f11c03502b67873ac1dac7c29cc8"},"cpp-latest-view-project200.json.gz":{"bytes":762409,"compression":"gzip","decompressed_bytes":46397047,"decompressed_name":"cpp-latest-view-project200.json","decompressed_sha256":"f6ba04065b400361ba6e7da93b4e336d02cd03687448f1f337738d533505edb2","sha256":"1a36afc4f34ef09d4e71f76a95c3ae4b42026a1cc31a4006d457143c582a4762"},"current-clean200-data.json.gz":{"bytes":1834262,"compression":"gzip","decompressed_bytes":38472295,"decompressed_name":"current-clean200-data.json","decompressed_sha256":"18a96a681dbddfe1aef51108f1399f836b970391891ed1d051bc6cdce81bf7fe","sha256":"b009097821fb4fec651bdfcbb39c624bedc96f476694bf7ce611a0114efae847"},"dataset-catalog.json.gz":{"bytes":28363,"compression":"gzip","decompressed_bytes":475044,"decompressed_name":"dataset-catalog.json","decompressed_sha256":"e25642fe1d87ab0bb595a391f4582c43ab94b9d6ae5ebd2be9903ccf261c1fd2","sha256":"b6d261c84e236efba34618975db37fb481f60e50e5682074fd103d784c1bb9f4"},"operator97-project200-summary.json.gz":{"bytes":1635865,"compression":"gzip","decompressed_bytes":17069616,"decompressed_name":"operator97-project200-summary.json","decompressed_sha256":"370a01786db4d034d49117ee76c5f8999a9514192ee61ebca7151bed481739e0","sha256":"0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00"},"ui-data-project200.json.gz":{"bytes":4715802,"compression":"gzip","decompressed_bytes":22734661,"decompressed_name":"ui-data-project200.json","decompressed_sha256":"160e49e5afcb8a27e0e48e311fe1838d70930782d659dc5c444b9b0f4faebf59","sha256":"c2f0f46fc5c715af4da8f43101cada390c32e10e04f9fdbfb5e8896723daab65"}},"base_url":"https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4","parent_clean150_assets_preserved":true,"parent_clean150_external_assets":{"asset_manifest_sha256":"7bf5766c1ab16e577682a0d6c3e72471d99ef0018b751520cb188f9238f0ec5e","asset_manifest_url":"https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/fb42da46537a7461295587614d1573ea0f531459/benchmark-results/clean150_20261023_v1/ASSET_MANIFEST.json","assets":{"algorithm150-current-dataset-results.jsonl.gz":{"bytes":1595321,"compression":"gzip","decompressed_bytes":31302470,"decompressed_name":"algorithm150-current-dataset-results.jsonl","decompressed_sha256":"7d6a6ec9d057f2347e0e510b15d547b6835164fd16d51f64c8ab07934fc5da4c","sha256":"93b7064124c1c250336ab697648ce0c5cd7385a3264b834e6298fc330ec78c44"},"clean150-dataset-statistics.json.gz":{"bytes":4580,"compression":"gzip","decompressed_bytes":29388,"decompressed_name":"clean150-dataset-statistics.json","decompressed_sha256":"ed2d831b4c0f8724df075b5ce7bdf3c1b41f9cb4db2534f5d22c6a80b0a38905","sha256":"1f5d2564b5afdeadd14982b3fd144922a660273806e050fb39650a4e99238fa3"},"cpp-latest-view-project150.json.gz":{"bytes":804774,"compression":"gzip","copied_byte_for_byte_from_ui2":true,"decompressed_bytes":45638787,"decompressed_name":"cpp-latest-view-project150.json","decompressed_sha256":"5e280dd67b1473f03ed0f7a4ae5bd1f314d28315d5438db2c60476060686b9f0","sha256":"fc21d5459a20bf837dc2911c211cc10a30f005a7d2382e1b3c4985c81875dd01"},"current-clean150-data.json.gz":{"bytes":1551779,"compression":"gzip","decompressed_bytes":29971323,"decompressed_name":"current-clean150-data.json","decompressed_sha256":"1f75a3fadc2cbb82ff1181076dcbce760abdab6d61d2d2a9e9bb170e410c85d6","sha256":"38ba0a453415380774ab47c19a7b138fd08d93b9c4fcd97bc3310d98de28e784"},"dataset-catalog.json.gz":{"bytes":24920,"compression":"gzip","decompressed_bytes":406315,"decompressed_name":"dataset-catalog.json","decompressed_sha256":"faab81fef68cfb9395638014b610819ab61e1b619abafcaa76ae8b265d09ee6d","sha256":"e370ed180583b6143e2293e19d4cba793b431ca02ffcb9a7ac97c93c38425cb2"},"operator97-project150-summary.json.gz":{"bytes":1219563,"compression":"gzip","decompressed_bytes":12325594,"decompressed_name":"operator97-project150-summary.json","decompressed_sha256":"79565bb3c125dca1f6f184496aa3c8d70bd28c4c4dd166ce2ac3ca04b9680eb9","sha256":"ec1ce5273c175ef82e1ae4f08f8cf73beab23327aeb6d2b5999a32c38ef4424b"},"ui-data-project150.json.gz":{"bytes":3704703,"compression":"gzip","copied_byte_for_byte_from_ui2":true,"decompressed_bytes":18417878,"decompressed_name":"ui-data-project150.json","decompressed_sha256":"aca4767f47027d96cebea3108a6e1961f6a1d494f25d3e87dc2b7797696cc47a","sha256":"9091e1dbfd826872361e4f67e8b7b4fd201a18fc987674dc6ff223891c7fc23b"}},"base_url":"https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/fb42da46537a7461295587614d1573ea0f531459/benchmark-results/clean150_20261023_v1","prefix":"benchmark-results/clean150_20261023_v1","repo":"THULab/TSCB_dataset","revision":"fb42da46537a7461295587614d1573ea0f531459"},"prefix":"benchmark-results/clean200_20261025_v4","repo":"THULab/TSCB_dataset","revision":"eb44d8917c982e9a6fa283bdee1ff894a406d8ff"},"files":{"CLEAN150_ACCEPTANCE.json":{"bytes":2855,"sha256":"720900336ea333f97df283c22a4c30c6ae6a31c87a2a63596836ef173b4aff2d"},"CLEAN150_OPERATOR_ACCEPTANCE.json":{"bytes":2619,"sha256":"b9f0315cb221d6a48252173ae4068f2f986d803d9d43f863c458cdf780485195"},"README.md":{"bytes":2474,"sha256":"40973205392f614a21c92d3edb1d4871066a769fe2e61013dd842a219026b3b6"},"app.js":{"bytes":82489,"sha256":"931adb474a0a554b1e2cad609c009e5de116f9d5f3503aac8152771fa272f272"},"availability.js":{"bytes":11334,"sha256":"bfc2597ab84517b00b5c80c868bdcd10e4342f8e0c9672fd20c86b60ea3f842e"},"index.html":{"bytes":23342,"sha256":"8cfcd54a0aab06d6690060e2c509d61883fa941817ad9706c72672b47b046583"},"project150-scope.js":{"bytes":6152,"sha256":"16e6dca24ecdfb35891d5ce665e3f0652cf1f35198d9c38d416e395e6f8e4f37"}},"filter":"remove NULL and IEEE NaN per column; preserve Inf and signed zero","historical_data_json_sha256":"3c66633b2d58b126edfad8afe173caf1f53fbcdb6f7b205c3d51b42dfc75a241","non_target_selected_preserved":5046,"old_raw_records":123639,"old_space_files_and_repository_history_preserved":true,"operator_source_sha256":"0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00","schema":"clean200-site-shell-candidate-v1","scientific_decompressed_bytes_unchanged":true,"scope":{"columns":3723,"datasets":200,"methods":85,"operator_implementations":97},"source_candidate":"/Users/xiaojinzhao/Documents/GitHub/web_compression/analysis_outputs/clean150_display_20261023_v1/site/real_candidate_v4_20261023T1720_ui2","source_manifest_sha256":"7348c3144d9c58bea10016e597a0b1eb08073346966db21bce164b49a3d13e66","space_parent_revision":"753549e74f728c131eb66d9b6eaf48375b985ae0","status":"accepted_local_candidate_not_published","transport_only":true,"ui_scope_patch":{"changed_files":["README.md","app.js","availability.js","index.html"],"cpp_precision_control":"disabled_and_reset_to_all_for_current_clean_cpp","current_cpp_scopes":["overall","integer","float"],"historical_language_input_contract_preserved":true,"historical_language_views":["java","python"],"schema":"clean150-ui-language-precision-and-source-label-patch-v2","scientific_files_unchanged":true,"script_sha256":"96703308c4502f2a5a8f6e62ac0393d71d3f8fd50e735f2c5fb7b828d5be03b3"},"ui_source_data_sha256":"18a96a681dbddfe1aef51108f1399f836b970391891ed1d051bc6cdce81bf7fe"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm_source_sha256": "853264b4a65653226b6b3b4b894613fde50329dca6c915eeae206ad6d304fa0b",
3
+ "all_old_raw_records_preserved": true,
4
+ "baseline_revision": "c0ffced61ef3d4fcfb6bc6621a54caf315d32ce8",
5
+ "clean150_external_prefix_preserved": true,
6
+ "current_data_file": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/current-clean200-data.json.gz",
7
+ "current_dataset_method_pairs": 17200,
8
+ "current_raw_records": 192643,
9
+ "current_scope_rows": 38528,
10
+ "data_sha256": "25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5",
11
+ "dataset_revision": "5511b6a3a1cdb5a002795e36de0915a1588504df",
12
+ "dataset_statistics_recomputed_from_unique_accepted_columns": true,
13
+ "delete_operations": [],
14
+ "external_assets": {
15
+ "asset_manifest_sha256": "0776625ca9593928d18e19f242cddabe9ab10489e535242d564699d674e9a525",
16
+ "asset_manifest_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1/ASSET_MANIFEST.json",
17
+ "assets": {
18
+ "ASSET_MANIFEST.json": {
19
+ "bytes": 4122,
20
+ "sha256": "0776625ca9593928d18e19f242cddabe9ab10489e535242d564699d674e9a525"
21
+ },
22
+ "LATEST_THREE200_ACCEPTANCE.json": {
23
+ "bytes": 2594,
24
+ "sha256": "82f9a89c9146e6af4a551ea6a7faae4a23315e35617f024d3607d55a1e177b05"
25
+ },
26
+ "algorithm200-current-dataset-results.jsonl.gz": {
27
+ "bytes": 2103363,
28
+ "compression": "gzip",
29
+ "decompressed_bytes": 39645280,
30
+ "decompressed_sha256": "cbd947529c67cf87fe5d564a868598fb3f1c04d33912ed4049d39660008b688b",
31
+ "sha256": "69eb3e95dc7926959bf438efe3a9e475d0a196a8276cfc1db8fb22f112cd2514"
32
+ },
33
+ "clean200-dataset-statistics.json.gz": {
34
+ "bytes": 5666,
35
+ "compression": "gzip",
36
+ "decompressed_bytes": 39209,
37
+ "decompressed_sha256": "6c87b8a27a092cb773a56e1b943b9b725138bfcf28f07922907993150a4cf250",
38
+ "sha256": "abc0f4b5d6a31ca281da52b9c1ff07847162f11c03502b67873ac1dac7c29cc8"
39
+ },
40
+ "cpp-latest-view-project200.json.gz": {
41
+ "bytes": 791240,
42
+ "compression": "gzip",
43
+ "decompressed_bytes": 47238991,
44
+ "decompressed_sha256": "65a04e9e7704e7a9a2847216dad4a5ab5f4f57077754790250f9711d817d5a7c",
45
+ "sha256": "99bf6329af9745899349eca91d161cf867d03d0ebe28d46a9482c0de8b4db560"
46
+ },
47
+ "current-clean200-data.json.gz": {
48
+ "bytes": 2103364,
49
+ "compression": "gzip",
50
+ "decompressed_bytes": 39645281,
51
+ "decompressed_sha256": "25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5",
52
+ "sha256": "78301ac206a1d2a33ae79846edf84abd616138d81013042eaca7c9f9e707e021"
53
+ },
54
+ "dataset-catalog.json.gz": {
55
+ "bytes": 28363,
56
+ "compression": "gzip",
57
+ "decompressed_bytes": 475044,
58
+ "decompressed_sha256": "e25642fe1d87ab0bb595a391f4582c43ab94b9d6ae5ebd2be9903ccf261c1fd2",
59
+ "sha256": "b6d261c84e236efba34618975db37fb481f60e50e5682074fd103d784c1bb9f4"
60
+ },
61
+ "latest-three-column-results.jsonl.gz": {
62
+ "bytes": 3527870,
63
+ "compression": "gzip",
64
+ "decompressed_bytes": 29615625,
65
+ "decompressed_sha256": "51e145628b6995aafc30e27bb0a32e78e4923b47d0b28ed37d71c797ba1690b9",
66
+ "sha256": "7839fbb3381537c478f132cb1b816d97a9bb195289d12a19d85490614ca7d586"
67
+ },
68
+ "operator97-project200-summary.json.gz": {
69
+ "bytes": 1635865,
70
+ "compression": "gzip",
71
+ "decompressed_bytes": 17069616,
72
+ "decompressed_sha256": "370a01786db4d034d49117ee76c5f8999a9514192ee61ebca7151bed481739e0",
73
+ "sha256": "0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00"
74
+ },
75
+ "ui-data-project200.json.gz": {
76
+ "bytes": 4756468,
77
+ "compression": "gzip",
78
+ "decompressed_bytes": 22884816,
79
+ "decompressed_sha256": "2534a59a84f8acc9c80530f017238c520ea810c9761e98ee82b4e5552fc3b6bc",
80
+ "sha256": "5bc9f4640232f238463d88d643b267625af06f75382294570ae20471e24ace09"
81
+ }
82
+ },
83
+ "base_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/5511b6a3a1cdb5a002795e36de0915a1588504df/benchmark-results/clean200_latest_three_20261029_v1",
84
+ "prefix": "benchmark-results/clean200_latest_three_20261029_v1",
85
+ "previous_external_assets": {
86
+ "asset_manifest_sha256": "51fc6ba94da0ef43faa5051fe230cc6277ef73918948292761c4520e272717c6",
87
+ "asset_manifest_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4/ASSET_MANIFEST.json",
88
+ "assets": {
89
+ "algorithm200-current-dataset-results.jsonl.gz": {
90
+ "bytes": 1834261,
91
+ "compression": "gzip",
92
+ "decompressed_bytes": 38472294,
93
+ "decompressed_name": "algorithm200-current-dataset-results.jsonl",
94
+ "decompressed_sha256": "04e0b28d71e851ebc7feaaf1759db3d44b0f77da862384935390de437e879d22",
95
+ "sha256": "a6d4a54082c02db81812871a97ebb6c96fd197b699c805d39e82a5633dfdff25"
96
+ },
97
+ "clean200-dataset-statistics.json.gz": {
98
+ "bytes": 5666,
99
+ "compression": "gzip",
100
+ "decompressed_bytes": 39209,
101
+ "decompressed_name": "clean200-dataset-statistics.json",
102
+ "decompressed_sha256": "6c87b8a27a092cb773a56e1b943b9b725138bfcf28f07922907993150a4cf250",
103
+ "sha256": "abc0f4b5d6a31ca281da52b9c1ff07847162f11c03502b67873ac1dac7c29cc8"
104
+ },
105
+ "cpp-latest-view-project200.json.gz": {
106
+ "bytes": 762409,
107
+ "compression": "gzip",
108
+ "decompressed_bytes": 46397047,
109
+ "decompressed_name": "cpp-latest-view-project200.json",
110
+ "decompressed_sha256": "f6ba04065b400361ba6e7da93b4e336d02cd03687448f1f337738d533505edb2",
111
+ "sha256": "1a36afc4f34ef09d4e71f76a95c3ae4b42026a1cc31a4006d457143c582a4762"
112
+ },
113
+ "current-clean200-data.json.gz": {
114
+ "bytes": 1834262,
115
+ "compression": "gzip",
116
+ "decompressed_bytes": 38472295,
117
+ "decompressed_name": "current-clean200-data.json",
118
+ "decompressed_sha256": "18a96a681dbddfe1aef51108f1399f836b970391891ed1d051bc6cdce81bf7fe",
119
+ "sha256": "b009097821fb4fec651bdfcbb39c624bedc96f476694bf7ce611a0114efae847"
120
+ },
121
+ "dataset-catalog.json.gz": {
122
+ "bytes": 28363,
123
+ "compression": "gzip",
124
+ "decompressed_bytes": 475044,
125
+ "decompressed_name": "dataset-catalog.json",
126
+ "decompressed_sha256": "e25642fe1d87ab0bb595a391f4582c43ab94b9d6ae5ebd2be9903ccf261c1fd2",
127
+ "sha256": "b6d261c84e236efba34618975db37fb481f60e50e5682074fd103d784c1bb9f4"
128
+ },
129
+ "operator97-project200-summary.json.gz": {
130
+ "bytes": 1635865,
131
+ "compression": "gzip",
132
+ "decompressed_bytes": 17069616,
133
+ "decompressed_name": "operator97-project200-summary.json",
134
+ "decompressed_sha256": "370a01786db4d034d49117ee76c5f8999a9514192ee61ebca7151bed481739e0",
135
+ "sha256": "0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00"
136
+ },
137
+ "ui-data-project200.json.gz": {
138
+ "bytes": 4715802,
139
+ "compression": "gzip",
140
+ "decompressed_bytes": 22734661,
141
+ "decompressed_name": "ui-data-project200.json",
142
+ "decompressed_sha256": "160e49e5afcb8a27e0e48e311fe1838d70930782d659dc5c444b9b0f4faebf59",
143
+ "sha256": "c2f0f46fc5c715af4da8f43101cada390c32e10e04f9fdbfb5e8896723daab65"
144
+ }
145
+ },
146
+ "base_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/eb44d8917c982e9a6fa283bdee1ff894a406d8ff/benchmark-results/clean200_20261025_v4",
147
+ "parent_clean150_assets_preserved": true,
148
+ "parent_clean150_external_assets": {
149
+ "asset_manifest_sha256": "7bf5766c1ab16e577682a0d6c3e72471d99ef0018b751520cb188f9238f0ec5e",
150
+ "asset_manifest_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/fb42da46537a7461295587614d1573ea0f531459/benchmark-results/clean150_20261023_v1/ASSET_MANIFEST.json",
151
+ "assets": {
152
+ "algorithm150-current-dataset-results.jsonl.gz": {
153
+ "bytes": 1595321,
154
+ "compression": "gzip",
155
+ "decompressed_bytes": 31302470,
156
+ "decompressed_name": "algorithm150-current-dataset-results.jsonl",
157
+ "decompressed_sha256": "7d6a6ec9d057f2347e0e510b15d547b6835164fd16d51f64c8ab07934fc5da4c",
158
+ "sha256": "93b7064124c1c250336ab697648ce0c5cd7385a3264b834e6298fc330ec78c44"
159
+ },
160
+ "clean150-dataset-statistics.json.gz": {
161
+ "bytes": 4580,
162
+ "compression": "gzip",
163
+ "decompressed_bytes": 29388,
164
+ "decompressed_name": "clean150-dataset-statistics.json",
165
+ "decompressed_sha256": "ed2d831b4c0f8724df075b5ce7bdf3c1b41f9cb4db2534f5d22c6a80b0a38905",
166
+ "sha256": "1f5d2564b5afdeadd14982b3fd144922a660273806e050fb39650a4e99238fa3"
167
+ },
168
+ "cpp-latest-view-project150.json.gz": {
169
+ "bytes": 804774,
170
+ "compression": "gzip",
171
+ "copied_byte_for_byte_from_ui2": true,
172
+ "decompressed_bytes": 45638787,
173
+ "decompressed_name": "cpp-latest-view-project150.json",
174
+ "decompressed_sha256": "5e280dd67b1473f03ed0f7a4ae5bd1f314d28315d5438db2c60476060686b9f0",
175
+ "sha256": "fc21d5459a20bf837dc2911c211cc10a30f005a7d2382e1b3c4985c81875dd01"
176
+ },
177
+ "current-clean150-data.json.gz": {
178
+ "bytes": 1551779,
179
+ "compression": "gzip",
180
+ "decompressed_bytes": 29971323,
181
+ "decompressed_name": "current-clean150-data.json",
182
+ "decompressed_sha256": "1f75a3fadc2cbb82ff1181076dcbce760abdab6d61d2d2a9e9bb170e410c85d6",
183
+ "sha256": "38ba0a453415380774ab47c19a7b138fd08d93b9c4fcd97bc3310d98de28e784"
184
+ },
185
+ "dataset-catalog.json.gz": {
186
+ "bytes": 24920,
187
+ "compression": "gzip",
188
+ "decompressed_bytes": 406315,
189
+ "decompressed_name": "dataset-catalog.json",
190
+ "decompressed_sha256": "faab81fef68cfb9395638014b610819ab61e1b619abafcaa76ae8b265d09ee6d",
191
+ "sha256": "e370ed180583b6143e2293e19d4cba793b431ca02ffcb9a7ac97c93c38425cb2"
192
+ },
193
+ "operator97-project150-summary.json.gz": {
194
+ "bytes": 1219563,
195
+ "compression": "gzip",
196
+ "decompressed_bytes": 12325594,
197
+ "decompressed_name": "operator97-project150-summary.json",
198
+ "decompressed_sha256": "79565bb3c125dca1f6f184496aa3c8d70bd28c4c4dd166ce2ac3ca04b9680eb9",
199
+ "sha256": "ec1ce5273c175ef82e1ae4f08f8cf73beab23327aeb6d2b5999a32c38ef4424b"
200
+ },
201
+ "ui-data-project150.json.gz": {
202
+ "bytes": 3704703,
203
+ "compression": "gzip",
204
+ "copied_byte_for_byte_from_ui2": true,
205
+ "decompressed_bytes": 18417878,
206
+ "decompressed_name": "ui-data-project150.json",
207
+ "decompressed_sha256": "aca4767f47027d96cebea3108a6e1961f6a1d494f25d3e87dc2b7797696cc47a",
208
+ "sha256": "9091e1dbfd826872361e4f67e8b7b4fd201a18fc987674dc6ff223891c7fc23b"
209
+ }
210
+ },
211
+ "base_url": "https://huggingface.co/datasets/THULab/TSCB_dataset/resolve/fb42da46537a7461295587614d1573ea0f531459/benchmark-results/clean150_20261023_v1",
212
+ "prefix": "benchmark-results/clean150_20261023_v1",
213
+ "repo": "THULab/TSCB_dataset",
214
+ "revision": "fb42da46537a7461295587614d1573ea0f531459"
215
+ },
216
+ "prefix": "benchmark-results/clean200_20261025_v4",
217
+ "repo": "THULab/TSCB_dataset",
218
+ "revision": "eb44d8917c982e9a6fa283bdee1ff894a406d8ff"
219
+ },
220
+ "repo": "THULab/TSCB_dataset",
221
+ "revision": "5511b6a3a1cdb5a002795e36de0915a1588504df"
222
+ },
223
+ "files": {
224
+ "CLEAN150_ACCEPTANCE.json": {
225
+ "bytes": 2855,
226
+ "sha256": "720900336ea333f97df283c22a4c30c6ae6a31c87a2a63596836ef173b4aff2d"
227
+ },
228
+ "CLEAN150_OPERATOR_ACCEPTANCE.json": {
229
+ "bytes": 2619,
230
+ "sha256": "b9f0315cb221d6a48252173ae4068f2f986d803d9d43f863c458cdf780485195"
231
+ },
232
+ "CLEAN200_ACCEPTANCE.json": {
233
+ "bytes": 1720,
234
+ "sha256": "1642509cdf4291dd7ad92e0c4ae3e8b90907ebf9b2e4ef524bb0c711d3553670"
235
+ },
236
+ "CLEAN200_OPERATOR_ACCEPTANCE.json": {
237
+ "bytes": 1324,
238
+ "sha256": "7d1a14f9413a9011b83bb08f36e193893a313313a709b2183bc4d3a511f98a72"
239
+ },
240
+ "LATEST_THREE200_ACCEPTANCE.json": {
241
+ "bytes": 2594,
242
+ "sha256": "82f9a89c9146e6af4a551ea6a7faae4a23315e35617f024d3607d55a1e177b05"
243
+ },
244
+ "README.md": {
245
+ "bytes": 3075,
246
+ "sha256": "eab19229edb6e03daa3b85a3f48a8f953161e0f6b9579e79235184bdb39ac3fb"
247
+ },
248
+ "app.js": {
249
+ "bytes": 82603,
250
+ "sha256": "240b05c376efa3e17d91427bb15b512dc84a9b0b62314dfcae471adb443d5f9c"
251
+ },
252
+ "availability.js": {
253
+ "bytes": 11334,
254
+ "sha256": "bfc2597ab84517b00b5c80c868bdcd10e4342f8e0c9672fd20c86b60ea3f842e"
255
+ },
256
+ "index.html": {
257
+ "bytes": 23443,
258
+ "sha256": "4fe788c304717415c287646f72ef385316c0ed1aec3534f0bae8d16485fee618"
259
+ },
260
+ "project150-scope.js": {
261
+ "bytes": 6152,
262
+ "sha256": "16e6dca24ecdfb35891d5ce665e3f0652cf1f35198d9c38d416e395e6f8e4f37"
263
+ },
264
+ "project200-scope.js": {
265
+ "bytes": 7274,
266
+ "sha256": "2213c568cd9531afbcfe57375ae1692981284ceb02ff4a980adb1af0e1d3b7ab"
267
+ },
268
+ "ranking.js": {
269
+ "bytes": 9051,
270
+ "sha256": "279bb7b3030a6d383b5a483c629d5ba38d87a546f512d07ff66def100e3fb929"
271
+ },
272
+ "style.css": {
273
+ "bytes": 22611,
274
+ "sha256": "8788aeb1ec4e797a30188f2d7b3c207982e53dec1a21e40ade128110e6d4601f"
275
+ }
276
+ },
277
+ "filter": "remove NULL and IEEE NaN per column; preserve Inf and signed zero",
278
+ "historical_data_json_sha256": "3c66633b2d58b126edfad8afe173caf1f53fbcdb6f7b205c3d51b42dfc75a241",
279
+ "latest_three_integration": {
280
+ "candidate": {
281
+ "current_data_sha256": "25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5",
282
+ "sidecar_sha256": "65a04e9e7704e7a9a2847216dad4a5ab5f4f57077754790250f9711d817d5a7c",
283
+ "ui_data_sha256": "2534a59a84f8acc9c80530f017238c520ea810c9761e98ee82b4e5552fc3b6bc"
284
+ },
285
+ "failed_columns": 0,
286
+ "input_identity_equal_across_targets": true,
287
+ "metric_contract": {
288
+ "column_mean_compression_rate": "arithmetic mean of per-column complete_frame_bytes / canonical_input_bytes",
289
+ "compression_rate": "sum(complete_frame_bytes) / sum(canonical_input_bytes)",
290
+ "compression_rate_source_native": "sum(complete_frame_bytes) / sum(source_native_numeric_bytes)",
291
+ "compression_time_ns_per_point": "arithmetic mean of per-column compression_time_ns_per_valid_value",
292
+ "decompression_time_ns_per_point": "arithmetic mean of per-column decompression_time_ns_per_valid_value",
293
+ "website_manuscript_boundary": "The website primary rate uses the pooled canonical-input denominator; the manuscript's native-denominator column mean is a distinct metric and is not substituted for it."
294
+ },
295
+ "native_and_cold_bit_exact_all_columns": true,
296
+ "preservation_receipt_sha256": "7ac8cf0e91f054d070cab6f788991f2b08c62c9a89a20ef3a23c1d81f07f7b1a",
297
+ "schema": "latest-three200-site-acceptance-v1",
298
+ "scope": {
299
+ "columns_per_method": 3723,
300
+ "datasets": 200,
301
+ "methods": 86,
302
+ "operators": 97
303
+ },
304
+ "source_results_audit_sha256": "3e4434f898b5986795d9fd8beb86f6eb68391f48fc7f19510802db6ef05195e0",
305
+ "space_parent_revision": "c0ffced61ef3d4fcfb6bc6621a54caf315d32ce8",
306
+ "status": "accepted_local_candidate_not_published",
307
+ "targets": {
308
+ "BOS": {
309
+ "acceptance_sha256": "6fe2c5d7774a64d2dec1693034959b378ea958ddcaa8dce91900703bd216d621",
310
+ "binary_sha256": "22ed503e9dc8e01a7926d0756d34f5fab4341c5f584a0108e21e059939150a7d",
311
+ "column_results_sha256": "f1d077cf310c0f957694ff26941790e85315a3a482c2c86e83e53948b9817166"
312
+ },
313
+ "REGER": {
314
+ "acceptance_sha256": "2f69142e6ef1cff4a22fd230445d6397408a51bce06fa2761cf24fad932330e6",
315
+ "binary_sha256": "d250bca3cbb621c78c2a3bd7ef1fac1e2e88aab63086400004de0ce1b9e1a615",
316
+ "column_results_sha256": "29a7554534bd308e0810b34a93357064ca48034b36f7e1e8ce749b9e79896673"
317
+ },
318
+ "Sub-column": {
319
+ "acceptance_sha256": "aa8b2f53dd0e65127ce849ce3120c1a3277694b28da42ffe5e6129cbbfc8fc4c",
320
+ "binary_sha256": "2c4acc731a67abdc9bb9e49f2d0fd12a2aceaea49c30e8486c785bcd44398f03",
321
+ "column_results_sha256": "b5dcb39803bd9d1d9cf0304d80fa2c2b1d06c9c96dd09d9adc37eb1b865807bb"
322
+ }
323
+ }
324
+ },
325
+ "metric_contract": {
326
+ "column_mean_compression_rate": "arithmetic mean of per-column complete_frame_bytes / canonical_input_bytes",
327
+ "compression_rate": "sum(complete_frame_bytes) / sum(canonical_input_bytes)",
328
+ "compression_rate_source_native": "sum(complete_frame_bytes) / sum(source_native_numeric_bytes)",
329
+ "compression_time_ns_per_point": "arithmetic mean of per-column compression_time_ns_per_valid_value",
330
+ "decompression_time_ns_per_point": "arithmetic mean of per-column decompression_time_ns_per_valid_value",
331
+ "website_manuscript_boundary": "The website primary rate uses the pooled canonical-input denominator; the manuscript's native-denominator column mean is a distinct metric and is not substituted for it."
332
+ },
333
+ "non_target_selected_preserved": 5046,
334
+ "old_raw_records": 123639,
335
+ "old_space_files_and_repository_history_preserved": true,
336
+ "operator_source_sha256": "0d41c7d4f9c63d0af50f63fc39c83a2e21e5fc40512101090a0c5f5d752d7f00",
337
+ "schema": "clean200-latest-three-site-shell-v1",
338
+ "scientific_decompressed_bytes_unchanged": true,
339
+ "scope": {
340
+ "columns": 3723,
341
+ "datasets": 200,
342
+ "methods": 86,
343
+ "operator_implementations": 97
344
+ },
345
+ "source_manifest_sha256": "7348c3144d9c58bea10016e597a0b1eb08073346966db21bce164b49a3d13e66",
346
+ "source_results_audit_sha256": "3e4434f898b5986795d9fd8beb86f6eb68391f48fc7f19510802db6ef05195e0",
347
+ "space_parent_revision": "753549e74f728c131eb66d9b6eaf48375b985ae0",
348
+ "status": "accepted_local_candidate_not_published",
349
+ "transport_only": true,
350
+ "ui_scope_patch": {
351
+ "changed_files": [
352
+ "README.md",
353
+ "app.js",
354
+ "availability.js",
355
+ "index.html"
356
+ ],
357
+ "cpp_precision_control": "disabled_and_reset_to_all_for_current_clean_cpp",
358
+ "current_cpp_scopes": [
359
+ "overall",
360
+ "integer",
361
+ "float"
362
+ ],
363
+ "historical_language_input_contract_preserved": true,
364
+ "historical_language_views": [
365
+ "java",
366
+ "python"
367
+ ],
368
+ "schema": "clean150-ui-language-precision-and-source-label-patch-v2",
369
+ "scientific_files_unchanged": true,
370
+ "script_sha256": "96703308c4502f2a5a8f6e62ac0393d71d3f8fd50e735f2c5fb7b828d5be03b3"
371
+ },
372
+ "ui_source_data_sha256": "25f8e7217d3d01c93bae5db6a9043be8e41f3436a85ce727c3bc0340c3bcc3f5"
373
+ }
project200-scope.js CHANGED
@@ -1,6 +1,6 @@
1
  export const PROJECT200_SCOPE = Object.freeze({schema:'compressionbenchmark-project200-scope-v1',status:'accepted_complete',scope_id:'clean200_20261025_v1',dataset_count:200,datasets:Object.freeze(["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","hf_localnet_dynamics","hf_bike_sharing_dc_hourly","hf_refit_residential_15min","hf_lyon_velov_30min","hf_tetouan_power_10min","hf_heapo_household_hourly","hf_appliances_energy_10min","hf_seoul_bike_hourly","hf_european_nextbike_station_status","hf_m5_daily_sales","hf_har70plus_accelerometry","hf_camels_usgs_discharge_modern490","hf_serc_soil_signals","hf_lakebed_crystal_bog_temperature","hf_liander2024_grid_load","hf_lotsa_bdg_2_bear","hf_lotsa_bdg_2_fox","hf_lotsa_bdg_2_panther","hf_lotsa_bdg_2_rat","hf_lotsa_beijing_air_quality","hf_lotsa_beijing_subway_30min","hf_lotsa_borealis","hf_lotsa_bull","hf_lotsa_cdc_fluview_ilinet","hf_lotsa_cdc_fluview_who_nrevss","hf_lotsa_china_air_quality","hf_lotsa_cockatoo","hf_lotsa_covid19_energy","hf_lotsa_covid_mobility","hf_lotsa_elecdemand","hf_lotsa_elf","hf_lotsa_favorita_transactions","hf_lotsa_gfc12_load","hf_lotsa_gfc14_load","hf_lotsa_gfc17_load","hf_lotsa_hierarchical_sales","hf_lotsa_hog","hf_lotsa_hzmetro","hf_lotsa_ideal","hf_lotsa_kdd2022","hf_lotsa_loop_seattle","hf_lotsa_los_loop","hf_lotsa_m4_daily","hf_lotsa_m4_hourly","hf_lotsa_m4_monthly","hf_lotsa_m4_weekly","hf_lotsa_m_dense","hf_lotsa_pdb","hf_lotsa_pems03","hf_lotsa_pems04","hf_lotsa_pems07","hf_lotsa_pems08","hf_lotsa_project_tycho","hf_lotsa_restaurant","hf_lotsa_sceaux","hf_lotsa_shmetro","hf_lotsa_smart","hf_lotsa_spain","hf_lotsa_subseasonal_precip","hf_lotsa_sz_taxi","hf_lotsa_taxi_30min","hf_lotsa_uber_tlc_daily","hf_lotsa_uber_tlc_hourly","hf_lotsa_weather","hf_lotsa_wiki_rolling_nips"])});
2
  export const PROJECT200_INPUT_STATUS = Object.freeze({schema:'compressionbenchmark-project200-input-status-v1',status:'accepted_complete',scope_id:'clean200_20261025_v1',pending_datasets:Object.freeze([])});
3
- export const ACTIVE_CPP_FAMILIES = Object.freeze(["2DIFF","ALP","ANS","Arithmetic","BOS","BSC","BUFF","Blosc","Blosc2","BriefLZ","Brotli","Bzip2","Bzip3","CORAD","CSC","Camel","Chimp","Chimp128","Crush","DBP","Density","Dict.","Elf","Elf+","FPC","FPCmp-R","FPCmp-S","FPZIP","FSE","FastLZ","FastLZMA2","FastPFor","Gipfeli","Gorilla","Huff0","Huffman","Kanzi","LECO","LZ4","LZ4 Fast","LZ4HC","LZAV","LZF","LZFSE","LZG","LZHAM","LZJB","LZMAT","LZO1","LZO2A","LZRW","LZSSE","LZVN","Libdeflate","Lizard","Lzlib","NRV","PFPC","PPMD8","Pithy","Pongo","QuickLZ","REGER","RLBE","RLE","SLZ","SPDP","SVB","Shrinker","Simple8b","Snappy","Sprintz","TAMP","Tornado","WFLZ","XPACK","XZ","YALZ77","Yappy","ZXC","Zlib","Zlib-ng","Zling","Zstd","gzip"]);
4
 
5
  export function applyProject200Scope(snapshot,scope=PROJECT200_SCOPE,status=PROJECT200_INPUT_STATUS) {
6
  if(scope?.schema!=='compressionbenchmark-project200-scope-v1'||scope?.status!=='accepted_complete'||scope.scope_id!==PROJECT200_SCOPE.scope_id)throw new Error('Invalid project200 scope contract.');
 
1
  export const PROJECT200_SCOPE = Object.freeze({schema:'compressionbenchmark-project200-scope-v1',status:'accepted_complete',scope_id:'clean200_20261025_v1',dataset_count:200,datasets:Object.freeze(["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","hf_localnet_dynamics","hf_bike_sharing_dc_hourly","hf_refit_residential_15min","hf_lyon_velov_30min","hf_tetouan_power_10min","hf_heapo_household_hourly","hf_appliances_energy_10min","hf_seoul_bike_hourly","hf_european_nextbike_station_status","hf_m5_daily_sales","hf_har70plus_accelerometry","hf_camels_usgs_discharge_modern490","hf_serc_soil_signals","hf_lakebed_crystal_bog_temperature","hf_liander2024_grid_load","hf_lotsa_bdg_2_bear","hf_lotsa_bdg_2_fox","hf_lotsa_bdg_2_panther","hf_lotsa_bdg_2_rat","hf_lotsa_beijing_air_quality","hf_lotsa_beijing_subway_30min","hf_lotsa_borealis","hf_lotsa_bull","hf_lotsa_cdc_fluview_ilinet","hf_lotsa_cdc_fluview_who_nrevss","hf_lotsa_china_air_quality","hf_lotsa_cockatoo","hf_lotsa_covid19_energy","hf_lotsa_covid_mobility","hf_lotsa_elecdemand","hf_lotsa_elf","hf_lotsa_favorita_transactions","hf_lotsa_gfc12_load","hf_lotsa_gfc14_load","hf_lotsa_gfc17_load","hf_lotsa_hierarchical_sales","hf_lotsa_hog","hf_lotsa_hzmetro","hf_lotsa_ideal","hf_lotsa_kdd2022","hf_lotsa_loop_seattle","hf_lotsa_los_loop","hf_lotsa_m4_daily","hf_lotsa_m4_hourly","hf_lotsa_m4_monthly","hf_lotsa_m4_weekly","hf_lotsa_m_dense","hf_lotsa_pdb","hf_lotsa_pems03","hf_lotsa_pems04","hf_lotsa_pems07","hf_lotsa_pems08","hf_lotsa_project_tycho","hf_lotsa_restaurant","hf_lotsa_sceaux","hf_lotsa_shmetro","hf_lotsa_smart","hf_lotsa_spain","hf_lotsa_subseasonal_precip","hf_lotsa_sz_taxi","hf_lotsa_taxi_30min","hf_lotsa_uber_tlc_daily","hf_lotsa_uber_tlc_hourly","hf_lotsa_weather","hf_lotsa_wiki_rolling_nips"])});
2
  export const PROJECT200_INPUT_STATUS = Object.freeze({schema:'compressionbenchmark-project200-input-status-v1',status:'accepted_complete',scope_id:'clean200_20261025_v1',pending_datasets:Object.freeze([])});
3
+ export const ACTIVE_CPP_FAMILIES = Object.freeze(["2DIFF","ALP","ANS","Arithmetic","Blosc","Blosc2","BOS","BriefLZ","Brotli","BSC","BUFF","Bzip2","Bzip3","Camel","Chimp","Chimp128","CORAD","Crush","CSC","DBP","Density","Dict.","Elf","Elf+","FastLZ","FastLZMA2","FastPFor","FPC","FPCmp-R","FPCmp-S","FPZIP","FSE","Gipfeli","Gorilla","gzip","Huff0","Huffman","Kanzi","LECO","Libdeflate","Lizard","LZ4","LZ4 Fast","LZ4HC","LZAV","LZF","LZFSE","LZG","LZHAM","LZJB","Lzlib","LZMAT","LZO1","LZO2A","LZRW","LZSSE","LZVN","NRV","PFPC","Pithy","Pongo","PPMD8","QuickLZ","REGER","RLBE","RLE","Shrinker","Simple8b","SLZ","Snappy","SPDP","Sprintz","Sub-column","SVB","TAMP","Tornado","WFLZ","XPACK","XZ","YALZ77","Yappy","Zlib","Zlib-ng","Zling","Zstd","ZXC"]);
4
 
5
  export function applyProject200Scope(snapshot,scope=PROJECT200_SCOPE,status=PROJECT200_INPUT_STATUS) {
6
  if(scope?.schema!=='compressionbenchmark-project200-scope-v1'||scope?.status!=='accepted_complete'||scope.scope_id!==PROJECT200_SCOPE.scope_id)throw new Error('Invalid project200 scope contract.');