jzxiao commited on
Commit
d84ab71
·
verified ·
1 Parent(s): a21e6ea

Publish accepted corrected datasets and gzip operator evidence

Browse files

Add 858 independently accepted corrected-five dataset rows and the full 41090-row operator byte-effect union with 970 recovered rows. Operator CSV evidence is losslessly gzip encoded and verifies byte-for-byte after decompression. Preserve existing results and history. Fresh114 remains pending and excluded; unqualified timings stay unavailable.

CORRECTED_FIVE425_INDEPENDENT_ACCEPTANCE.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Fresh_excluded": true,
3
+ "actual_original_partial_census": {
4
+ "bytes": 2264,
5
+ "sha256": "48ce3bc099a19d6af0dcf00e5b73d67282561b1d713519c4840fda1344e54b35"
6
+ },
7
+ "aggregate_status_counts": {
8
+ "ok": 4498,
9
+ "unsupported": 687
10
+ },
11
+ "all_na_pair_count": 0,
12
+ "all_source_partial_count_observed": 4,
13
+ "all_unsupported_pair_count": 39,
14
+ "bzip_original_failure_exclusion": {
15
+ "dataset_id": "us_stock_financial_ratios",
16
+ "frame_files": [
17
+ {
18
+ "bytes": 162634,
19
+ "relative": "09/09e6689a6d9a4daf51af8cf960aea90423d30348414dbd29f183e8286fd3567f.ngb1",
20
+ "sha256": "09e6689a6d9a4daf51af8cf960aea90423d30348414dbd29f183e8286fd3567f"
21
+ },
22
+ {
23
+ "bytes": 161325,
24
+ "relative": "0e/0e23b9275b4d5925a61a4543fdbbde3c69373d42d97f3cb60cc4b9c4f1dbaf6f.ngb1",
25
+ "sha256": "0e23b9275b4d5925a61a4543fdbbde3c69373d42d97f3cb60cc4b9c4f1dbaf6f"
26
+ },
27
+ {
28
+ "bytes": 162602,
29
+ "relative": "1e/1ede9580cdd2d585d6844f5f5adf6a37006608632c3081a2fc42fb5a28a7801e.ngb1",
30
+ "sha256": "1ede9580cdd2d585d6844f5f5adf6a37006608632c3081a2fc42fb5a28a7801e"
31
+ },
32
+ {
33
+ "bytes": 162778,
34
+ "relative": "2f/2fd54c3a854590ffdcf36ab793a10b93ed045c343aeff9b8e9b77694a5d6f25e.ngb1",
35
+ "sha256": "2fd54c3a854590ffdcf36ab793a10b93ed045c343aeff9b8e9b77694a5d6f25e"
36
+ },
37
+ {
38
+ "bytes": 162722,
39
+ "relative": "39/39484d3d9df502bb100fad087243126119c285507b452e2bc4404802f46a2499.ngb1",
40
+ "sha256": "39484d3d9df502bb100fad087243126119c285507b452e2bc4404802f46a2499"
41
+ },
42
+ {
43
+ "bytes": 162257,
44
+ "relative": "3e/3e265cd4cd832639c04ccbf0f5aa752501f8fac121d928208059fc6f7dc35890.ngb1",
45
+ "sha256": "3e265cd4cd832639c04ccbf0f5aa752501f8fac121d928208059fc6f7dc35890"
46
+ },
47
+ {
48
+ "bytes": 162690,
49
+ "relative": "48/489aa8e4bb0a438c0aa135947475afc6b420f4b275938961894292a86a27ff42.ngb1",
50
+ "sha256": "489aa8e4bb0a438c0aa135947475afc6b420f4b275938961894292a86a27ff42"
51
+ },
52
+ {
53
+ "bytes": 162681,
54
+ "relative": "49/492395a40c812a42e479a0cd5b66279596b8edc99a670740aee2056d43d4cbe1.ngb1",
55
+ "sha256": "492395a40c812a42e479a0cd5b66279596b8edc99a670740aee2056d43d4cbe1"
56
+ },
57
+ {
58
+ "bytes": 156449,
59
+ "relative": "4b/4bba4fda60b2fe4c446af9fdd2553d6e5c1213d946f728317bc73fb5e8106df5.ngb1",
60
+ "sha256": "4bba4fda60b2fe4c446af9fdd2553d6e5c1213d946f728317bc73fb5e8106df5"
61
+ },
62
+ {
63
+ "bytes": 162746,
64
+ "relative": "50/50bf67b7eeb49a5f6b3deec5c77f93dfca04d6c8cfa6f0eb1e63a989c302a3e4.ngb1",
65
+ "sha256": "50bf67b7eeb49a5f6b3deec5c77f93dfca04d6c8cfa6f0eb1e63a989c302a3e4"
66
+ },
67
+ {
68
+ "bytes": 159653,
69
+ "relative": "55/5575c523509465af87ea488e16c2fd1a19ca432b0b317e5664462d1c7a5b523a.ngb1",
70
+ "sha256": "5575c523509465af87ea488e16c2fd1a19ca432b0b317e5664462d1c7a5b523a"
71
+ },
72
+ {
73
+ "bytes": 159734,
74
+ "relative": "56/565c11c2f684a4d664a63852153d7f51693925f8d010da287631f0cbaddf8ad1.ngb1",
75
+ "sha256": "565c11c2f684a4d664a63852153d7f51693925f8d010da287631f0cbaddf8ad1"
76
+ },
77
+ {
78
+ "bytes": 162690,
79
+ "relative": "6a/6a4f2c8d2ffbabbcc6bc2254e3b29208e06d3341fb27976b980c3a0afb87d5a3.ngb1",
80
+ "sha256": "6a4f2c8d2ffbabbcc6bc2254e3b29208e06d3341fb27976b980c3a0afb87d5a3"
81
+ },
82
+ {
83
+ "bytes": 162778,
84
+ "relative": "6d/6d321ca51d3ca39fd7059a17accc8cbc4f49b9d826307dba4087ce6bced01d17.ngb1",
85
+ "sha256": "6d321ca51d3ca39fd7059a17accc8cbc4f49b9d826307dba4087ce6bced01d17"
86
+ },
87
+ {
88
+ "bytes": 162634,
89
+ "relative": "72/724aec7f17c18d4942364d57854f85783882916d6b0ddaca994bfd1b5892b05e.ngb1",
90
+ "sha256": "724aec7f17c18d4942364d57854f85783882916d6b0ddaca994bfd1b5892b05e"
91
+ },
92
+ {
93
+ "bytes": 159734,
94
+ "relative": "7f/7f253558cc1ce560dcbf0e902659ae1ea47d8f0beec7f6f77493fecf579fcdc5.ngb1",
95
+ "sha256": "7f253558cc1ce560dcbf0e902659ae1ea47d8f0beec7f6f77493fecf579fcdc5"
96
+ },
97
+ {
98
+ "bytes": 162634,
99
+ "relative": "a4/a4f0310dc8b20072cd96d864325df6a81bae14fe51a6fdf997ddbdb924ed8eb8.ngb1",
100
+ "sha256": "a4f0310dc8b20072cd96d864325df6a81bae14fe51a6fdf997ddbdb924ed8eb8"
101
+ },
102
+ {
103
+ "bytes": 162690,
104
+ "relative": "b2/b279c95b04c000f39c960b00653288a2e6a3b533b763837825683d05b223aed3.ngb1",
105
+ "sha256": "b279c95b04c000f39c960b00653288a2e6a3b533b763837825683d05b223aed3"
106
+ },
107
+ {
108
+ "bytes": 161469,
109
+ "relative": "c1/c1248b8a653ff67fd0ec4c10d4e8dc430619368b13c003150af5fc87eaebf064.ngb1",
110
+ "sha256": "c1248b8a653ff67fd0ec4c10d4e8dc430619368b13c003150af5fc87eaebf064"
111
+ },
112
+ {
113
+ "bytes": 162690,
114
+ "relative": "c9/c941ee1fda779a4898c8a63d69d8400781aa315d4702ea77c23da819406ad74f.ngb1",
115
+ "sha256": "c941ee1fda779a4898c8a63d69d8400781aa315d4702ea77c23da819406ad74f"
116
+ },
117
+ {
118
+ "bytes": 162602,
119
+ "relative": "ca/cab513d76e0e524224b7c08eeaabb5df0930765643aa3e09da8432f3a474059a.ngb1",
120
+ "sha256": "cab513d76e0e524224b7c08eeaabb5df0930765643aa3e09da8432f3a474059a"
121
+ },
122
+ {
123
+ "bytes": 162494,
124
+ "relative": "dc/dcad62014ef50a04b0bac5e6f88ad1e302f2cbd346aaa98b52c3fd637288457d.ngb1",
125
+ "sha256": "dcad62014ef50a04b0bac5e6f88ad1e302f2cbd346aaa98b52c3fd637288457d"
126
+ },
127
+ {
128
+ "bytes": 161526,
129
+ "relative": "f9/f91a0cc90686fbe796642a8e2b4739aece96d8289c04e40ad4c23bc802603858.ngb1",
130
+ "sha256": "f91a0cc90686fbe796642a8e2b4739aece96d8289c04e40ad4c23bc802603858"
131
+ }
132
+ ],
133
+ "frame_inventory_sha256": "41bd03482e76ccfa4c6a3b3ffc5a25fb7e3605719e81ad1b9119156a3d7ff481",
134
+ "frame_root_present": true,
135
+ "isolated_repair_terminal": {
136
+ "bytes": 12095,
137
+ "sha256": "e87f15f684587b5e7df09808a5d95d04d77d89729824d7078a76fc6e804d94e1"
138
+ },
139
+ "method": "Bzip3",
140
+ "method_id": "25a7dc986562ff7c",
141
+ "original_failure_preserved_not_selected": true,
142
+ "terminal": {
143
+ "bytes": 12663,
144
+ "sha256": "d48ab792008c83788bd14aeb1784408c6bc59aa6693e3d3a1b5d31f8e8f28812"
145
+ },
146
+ "terminal_status": "failed_closed"
147
+ },
148
+ "created_at": "2026-10-13T07:51:43.792179+00:00",
149
+ "dataset_ids": [
150
+ "trending_stocks_yahoo_finance",
151
+ "github_top_projects",
152
+ "traqq_weekly_activity",
153
+ "us_stock_financial_ratios",
154
+ "magseven_ml_ready_high_frequency_anomaly"
155
+ ],
156
+ "excluded_fresh_historical_partial_count": 4,
157
+ "excluded_fresh_historical_partials": [
158
+ {
159
+ "bytes": 13972793,
160
+ "failed_terminal_bytes": 13666,
161
+ "failed_terminal_sha256": "6ed3e8a9690354de6e73655b71c310114a4a8ac8e004f0dbae55bb122bcb3d36",
162
+ "method": "XZ",
163
+ "method_id": "3c01374a220b9818",
164
+ "relative": "attempts/freshretailnet_50k/3c01374a220b9818/frames/partial/139cf9bb678ccb11e27a8899b657ae44c325d396cbc77231c8a3ecf2bc782b73.ngb1.partial",
165
+ "sha256": "88c90ba6f4802bde9aa5e6991af5eabc2954b626cd8abaa53d23a60f70c88168",
166
+ "terminal_status": "failed_closed"
167
+ },
168
+ {
169
+ "bytes": 20414806,
170
+ "failed_terminal_bytes": 21911,
171
+ "failed_terminal_sha256": "5de774f9bdf599fb017874e1bedd9334212452e66e58e51ce46dc6e6f8c9b0f0",
172
+ "method": "Lizard",
173
+ "method_id": "943b1f9df88791bc",
174
+ "relative": "attempts/freshretailnet_50k/943b1f9df88791bc/frames/partial/08090fa0a5b038d9a40a76d75287dd42110a59d61ba51f810b39d220f8d87224.ngb1.partial",
175
+ "sha256": "581c0064b1e654e465dcbdd70b9c354545b9aebf1e50a7781e2d22025191e29f",
176
+ "terminal_status": "failed_closed"
177
+ },
178
+ {
179
+ "bytes": 25746919,
180
+ "failed_terminal_bytes": 17970,
181
+ "failed_terminal_sha256": "100b718d0a256c5d519f9f649e18607184846bcbb110a0066e4680974cc8d702",
182
+ "method": "LZHAM",
183
+ "method_id": "aee3568a55b5976b",
184
+ "relative": "attempts/freshretailnet_50k/aee3568a55b5976b/frames/partial/3e77b8fc0aec1534f29207fb52092e7bf00bff4e331291c7ad1d108256c84573.ngb1.partial",
185
+ "sha256": "915dffa8c258bcc54d81fc728ffab52b731e3dd2ce81e0d241439e388ebb0aa7",
186
+ "terminal_status": "failed_closed"
187
+ },
188
+ {
189
+ "bytes": 27598134,
190
+ "failed_terminal_bytes": 10629,
191
+ "failed_terminal_sha256": "c9dffe515d03e8972091c0e0d93db23b5efc6b68f919863ff346f5e9e28f8ad4",
192
+ "method": "Crush",
193
+ "method_id": "fd4982bc31020a05",
194
+ "relative": "attempts/freshretailnet_50k/fd4982bc31020a05/frames/partial/f90965abfe62d3d75d353a7e1a08e8dd03a0a4da03d789011ce216bc3758da22.ngb1.partial",
195
+ "sha256": "e6e6841c882d659be2fc2eb60ebd39cccb78f3253a448bc942c6b7392cb68b08",
196
+ "terminal_status": "failed_closed"
197
+ }
198
+ ],
199
+ "full_510_partial_clean_claimed": false,
200
+ "method_count": 85,
201
+ "no_numeric_mixed_terminal_pair_count": 0,
202
+ "numeric_mixed_terminal_pair_count": 40,
203
+ "numeric_pair_count": 386,
204
+ "original_campaign_counts": {
205
+ "accepted": 495,
206
+ "failed_closed": 15
207
+ },
208
+ "original_campaign_start": {
209
+ "bytes": 6833,
210
+ "sha256": "10c890cb06210d081ee1a0a646fe95bbff3d713acda488e9aca8936531b0d9a3"
211
+ },
212
+ "original_campaign_terminal": {
213
+ "bytes": 369,
214
+ "sha256": "e2613fbd9206f65e7423ea57314a470643dae092d8a9c9c37d99c52415955d27"
215
+ },
216
+ "original_worker_returncodes": [
217
+ 1,
218
+ 1,
219
+ 1,
220
+ 1,
221
+ 1,
222
+ 1,
223
+ 1,
224
+ 1
225
+ ],
226
+ "original_worker_states": [
227
+ {
228
+ "bytes": 127,
229
+ "sha256": "b35ce998ac8e32a6ed4bf32a93668605962e906c42cc8dba3e5f6537aff1b597"
230
+ },
231
+ {
232
+ "bytes": 127,
233
+ "sha256": "513795128f8247832f6685fe75b6dc368430775aa27ec04c020a198675cc4dcb"
234
+ },
235
+ {
236
+ "bytes": 127,
237
+ "sha256": "e7c7e82e6cb1cfb5ce625dfa7ca2e31a899bde30d987f0c1bf448b79bd6d5268"
238
+ },
239
+ {
240
+ "bytes": 127,
241
+ "sha256": "f746d375d4735bcb27e2b1b50f7b52a60d50ae39016b0f597a362c40705b175d"
242
+ },
243
+ {
244
+ "bytes": 127,
245
+ "sha256": "bb735f944b6b0ecca752ba09fbd457c866a2054a3e05d50a1da30598fb7947ba"
246
+ },
247
+ {
248
+ "bytes": 127,
249
+ "sha256": "b8ed085bfc3e621f479343945077ecdcb895a028041a674bf1f8de015c6f2fb5"
250
+ },
251
+ {
252
+ "bytes": 127,
253
+ "sha256": "0eeccfd66715af1cc891e74f83a22083e450eefdfa51e98e2ac7e349825ce5c3"
254
+ },
255
+ {
256
+ "bytes": 127,
257
+ "sha256": "53d37e06cad843a3641f825ccb28bfc9ea47f612877d08b4955634f0c7fac0f3"
258
+ }
259
+ ],
260
+ "pair_count": 425,
261
+ "pair_identity_sha256": "ffe0a7a67974112410d494a6e4104904108809aacd68b6f88e9232e052e75d31",
262
+ "pair_terminal_class_counts": {
263
+ "measured_numeric_mixed_terminal": 40,
264
+ "measured_numeric_only": 346,
265
+ "no_numeric_all_unsupported": 39
266
+ },
267
+ "partition_counts": {
268
+ "base_accepted": 416,
269
+ "exact_support_boundary": 8,
270
+ "isolated_bzip3_repair": 1
271
+ },
272
+ "partition_identity_sha256": {
273
+ "base_accepted": "d76358f9175db5a5edccb085da05bac62f6e9536f6b3db2d2724d8ce4f145164",
274
+ "exact_support_boundary": "2803060669d80fd2cf15c568cd802a2a273e751aea1f6cf09caf5c7da499c1d1",
275
+ "isolated_bzip3_repair": "9055d85295e5b3d3fe7c942fb147abecbf978ed6e11c568b22ba113df59bd82d"
276
+ },
277
+ "records": {
278
+ "bytes": 700127,
279
+ "file": "corrected-five425-portable-results.jsonl.gz",
280
+ "row_count": 425,
281
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
282
+ },
283
+ "schema": "compressionbenchmark-corrected-five425-independent-acceptance-v2",
284
+ "scientific_timing_accepted": false,
285
+ "selected_failed_frame_directories": [
286
+ {
287
+ "dataset_id": "magseven_ml_ready_high_frequency_anomaly",
288
+ "method": "BUFF",
289
+ "method_id": "ddca15a88639d8a0"
290
+ },
291
+ {
292
+ "dataset_id": "magseven_ml_ready_high_frequency_anomaly",
293
+ "method": "CORAD",
294
+ "method_id": "e5ea904ece91f756"
295
+ },
296
+ {
297
+ "dataset_id": "traqq_weekly_activity",
298
+ "method": "BUFF",
299
+ "method_id": "ddca15a88639d8a0"
300
+ },
301
+ {
302
+ "dataset_id": "traqq_weekly_activity",
303
+ "method": "CORAD",
304
+ "method_id": "e5ea904ece91f756"
305
+ },
306
+ {
307
+ "dataset_id": "trending_stocks_yahoo_finance",
308
+ "method": "BUFF",
309
+ "method_id": "ddca15a88639d8a0"
310
+ },
311
+ {
312
+ "dataset_id": "trending_stocks_yahoo_finance",
313
+ "method": "CORAD",
314
+ "method_id": "e5ea904ece91f756"
315
+ },
316
+ {
317
+ "dataset_id": "us_stock_financial_ratios",
318
+ "method": "BUFF",
319
+ "method_id": "ddca15a88639d8a0"
320
+ },
321
+ {
322
+ "dataset_id": "us_stock_financial_ratios",
323
+ "method": "Bzip3",
324
+ "method_id": "25a7dc986562ff7c"
325
+ },
326
+ {
327
+ "dataset_id": "us_stock_financial_ratios",
328
+ "method": "CORAD",
329
+ "method_id": "e5ea904ece91f756"
330
+ }
331
+ ],
332
+ "selected_source_active_pid_count": 0,
333
+ "selected_source_partial_path_count": 0,
334
+ "selected_source_scope_quiescent": true,
335
+ "source_manifest_sha256": "872a3c370a92a5a694a7e149af312b06f1753d8f2c6a9af506a82639aa330371",
336
+ "source_quiescence_scope": "exact_selected425_with_excluded_fresh_history",
337
+ "source_validators": {
338
+ "base_acceptor_sha256": "440b61548ffe0f38806d1520ff280aca5a8bfc0998270f0e4112f7836a5c6923",
339
+ "overlay_acceptor_sha256": "8aee16785fd9ef7b58ad549e25f9bd5da6d54829dbd3cf9d5b8a57c2b7e9c4c8",
340
+ "support_verifier_sha256": "8108b31c14ce99d8376e5ac77a2caab72342da38e096b2a834c4fa6f166383ed"
341
+ },
342
+ "status": "accepted",
343
+ "support_boundary_policy": "conclusion_only_never_numeric_ranking",
344
+ "timing_policy": "none_public_timing_null_pending_separate_admission",
345
+ "website_publication_approved": false
346
+ }
CORRECTED_FIVE425_PORTABLE_MANIFEST.json ADDED
@@ -0,0 +1,368 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "Fresh_excluded": true,
3
+ "actual_original_partial_census": {
4
+ "bytes": 2264,
5
+ "sha256": "48ce3bc099a19d6af0dcf00e5b73d67282561b1d713519c4840fda1344e54b35"
6
+ },
7
+ "aggregate_status_counts": {
8
+ "ok": 4498,
9
+ "unsupported": 687
10
+ },
11
+ "all_na_pair_count": 0,
12
+ "all_source_partial_count_observed": 4,
13
+ "all_unsupported_pair_count": 39,
14
+ "bzip_original_failure_exclusion": {
15
+ "dataset_id": "us_stock_financial_ratios",
16
+ "frame_files": [
17
+ {
18
+ "bytes": 162634,
19
+ "relative": "09/09e6689a6d9a4daf51af8cf960aea90423d30348414dbd29f183e8286fd3567f.ngb1",
20
+ "sha256": "09e6689a6d9a4daf51af8cf960aea90423d30348414dbd29f183e8286fd3567f"
21
+ },
22
+ {
23
+ "bytes": 161325,
24
+ "relative": "0e/0e23b9275b4d5925a61a4543fdbbde3c69373d42d97f3cb60cc4b9c4f1dbaf6f.ngb1",
25
+ "sha256": "0e23b9275b4d5925a61a4543fdbbde3c69373d42d97f3cb60cc4b9c4f1dbaf6f"
26
+ },
27
+ {
28
+ "bytes": 162602,
29
+ "relative": "1e/1ede9580cdd2d585d6844f5f5adf6a37006608632c3081a2fc42fb5a28a7801e.ngb1",
30
+ "sha256": "1ede9580cdd2d585d6844f5f5adf6a37006608632c3081a2fc42fb5a28a7801e"
31
+ },
32
+ {
33
+ "bytes": 162778,
34
+ "relative": "2f/2fd54c3a854590ffdcf36ab793a10b93ed045c343aeff9b8e9b77694a5d6f25e.ngb1",
35
+ "sha256": "2fd54c3a854590ffdcf36ab793a10b93ed045c343aeff9b8e9b77694a5d6f25e"
36
+ },
37
+ {
38
+ "bytes": 162722,
39
+ "relative": "39/39484d3d9df502bb100fad087243126119c285507b452e2bc4404802f46a2499.ngb1",
40
+ "sha256": "39484d3d9df502bb100fad087243126119c285507b452e2bc4404802f46a2499"
41
+ },
42
+ {
43
+ "bytes": 162257,
44
+ "relative": "3e/3e265cd4cd832639c04ccbf0f5aa752501f8fac121d928208059fc6f7dc35890.ngb1",
45
+ "sha256": "3e265cd4cd832639c04ccbf0f5aa752501f8fac121d928208059fc6f7dc35890"
46
+ },
47
+ {
48
+ "bytes": 162690,
49
+ "relative": "48/489aa8e4bb0a438c0aa135947475afc6b420f4b275938961894292a86a27ff42.ngb1",
50
+ "sha256": "489aa8e4bb0a438c0aa135947475afc6b420f4b275938961894292a86a27ff42"
51
+ },
52
+ {
53
+ "bytes": 162681,
54
+ "relative": "49/492395a40c812a42e479a0cd5b66279596b8edc99a670740aee2056d43d4cbe1.ngb1",
55
+ "sha256": "492395a40c812a42e479a0cd5b66279596b8edc99a670740aee2056d43d4cbe1"
56
+ },
57
+ {
58
+ "bytes": 156449,
59
+ "relative": "4b/4bba4fda60b2fe4c446af9fdd2553d6e5c1213d946f728317bc73fb5e8106df5.ngb1",
60
+ "sha256": "4bba4fda60b2fe4c446af9fdd2553d6e5c1213d946f728317bc73fb5e8106df5"
61
+ },
62
+ {
63
+ "bytes": 162746,
64
+ "relative": "50/50bf67b7eeb49a5f6b3deec5c77f93dfca04d6c8cfa6f0eb1e63a989c302a3e4.ngb1",
65
+ "sha256": "50bf67b7eeb49a5f6b3deec5c77f93dfca04d6c8cfa6f0eb1e63a989c302a3e4"
66
+ },
67
+ {
68
+ "bytes": 159653,
69
+ "relative": "55/5575c523509465af87ea488e16c2fd1a19ca432b0b317e5664462d1c7a5b523a.ngb1",
70
+ "sha256": "5575c523509465af87ea488e16c2fd1a19ca432b0b317e5664462d1c7a5b523a"
71
+ },
72
+ {
73
+ "bytes": 159734,
74
+ "relative": "56/565c11c2f684a4d664a63852153d7f51693925f8d010da287631f0cbaddf8ad1.ngb1",
75
+ "sha256": "565c11c2f684a4d664a63852153d7f51693925f8d010da287631f0cbaddf8ad1"
76
+ },
77
+ {
78
+ "bytes": 162690,
79
+ "relative": "6a/6a4f2c8d2ffbabbcc6bc2254e3b29208e06d3341fb27976b980c3a0afb87d5a3.ngb1",
80
+ "sha256": "6a4f2c8d2ffbabbcc6bc2254e3b29208e06d3341fb27976b980c3a0afb87d5a3"
81
+ },
82
+ {
83
+ "bytes": 162778,
84
+ "relative": "6d/6d321ca51d3ca39fd7059a17accc8cbc4f49b9d826307dba4087ce6bced01d17.ngb1",
85
+ "sha256": "6d321ca51d3ca39fd7059a17accc8cbc4f49b9d826307dba4087ce6bced01d17"
86
+ },
87
+ {
88
+ "bytes": 162634,
89
+ "relative": "72/724aec7f17c18d4942364d57854f85783882916d6b0ddaca994bfd1b5892b05e.ngb1",
90
+ "sha256": "724aec7f17c18d4942364d57854f85783882916d6b0ddaca994bfd1b5892b05e"
91
+ },
92
+ {
93
+ "bytes": 159734,
94
+ "relative": "7f/7f253558cc1ce560dcbf0e902659ae1ea47d8f0beec7f6f77493fecf579fcdc5.ngb1",
95
+ "sha256": "7f253558cc1ce560dcbf0e902659ae1ea47d8f0beec7f6f77493fecf579fcdc5"
96
+ },
97
+ {
98
+ "bytes": 162634,
99
+ "relative": "a4/a4f0310dc8b20072cd96d864325df6a81bae14fe51a6fdf997ddbdb924ed8eb8.ngb1",
100
+ "sha256": "a4f0310dc8b20072cd96d864325df6a81bae14fe51a6fdf997ddbdb924ed8eb8"
101
+ },
102
+ {
103
+ "bytes": 162690,
104
+ "relative": "b2/b279c95b04c000f39c960b00653288a2e6a3b533b763837825683d05b223aed3.ngb1",
105
+ "sha256": "b279c95b04c000f39c960b00653288a2e6a3b533b763837825683d05b223aed3"
106
+ },
107
+ {
108
+ "bytes": 161469,
109
+ "relative": "c1/c1248b8a653ff67fd0ec4c10d4e8dc430619368b13c003150af5fc87eaebf064.ngb1",
110
+ "sha256": "c1248b8a653ff67fd0ec4c10d4e8dc430619368b13c003150af5fc87eaebf064"
111
+ },
112
+ {
113
+ "bytes": 162690,
114
+ "relative": "c9/c941ee1fda779a4898c8a63d69d8400781aa315d4702ea77c23da819406ad74f.ngb1",
115
+ "sha256": "c941ee1fda779a4898c8a63d69d8400781aa315d4702ea77c23da819406ad74f"
116
+ },
117
+ {
118
+ "bytes": 162602,
119
+ "relative": "ca/cab513d76e0e524224b7c08eeaabb5df0930765643aa3e09da8432f3a474059a.ngb1",
120
+ "sha256": "cab513d76e0e524224b7c08eeaabb5df0930765643aa3e09da8432f3a474059a"
121
+ },
122
+ {
123
+ "bytes": 162494,
124
+ "relative": "dc/dcad62014ef50a04b0bac5e6f88ad1e302f2cbd346aaa98b52c3fd637288457d.ngb1",
125
+ "sha256": "dcad62014ef50a04b0bac5e6f88ad1e302f2cbd346aaa98b52c3fd637288457d"
126
+ },
127
+ {
128
+ "bytes": 161526,
129
+ "relative": "f9/f91a0cc90686fbe796642a8e2b4739aece96d8289c04e40ad4c23bc802603858.ngb1",
130
+ "sha256": "f91a0cc90686fbe796642a8e2b4739aece96d8289c04e40ad4c23bc802603858"
131
+ }
132
+ ],
133
+ "frame_inventory_sha256": "41bd03482e76ccfa4c6a3b3ffc5a25fb7e3605719e81ad1b9119156a3d7ff481",
134
+ "frame_root_present": true,
135
+ "isolated_repair_terminal": {
136
+ "bytes": 12095,
137
+ "sha256": "e87f15f684587b5e7df09808a5d95d04d77d89729824d7078a76fc6e804d94e1"
138
+ },
139
+ "method": "Bzip3",
140
+ "method_id": "25a7dc986562ff7c",
141
+ "original_failure_preserved_not_selected": true,
142
+ "terminal": {
143
+ "bytes": 12663,
144
+ "sha256": "d48ab792008c83788bd14aeb1784408c6bc59aa6693e3d3a1b5d31f8e8f28812"
145
+ },
146
+ "terminal_status": "failed_closed"
147
+ },
148
+ "collector": {
149
+ "bytes": 61974,
150
+ "sha256": "db07a2444c49a6ab45a2667f0971ae4ee19e8164e63c4d6f4115811c1aaaadac"
151
+ },
152
+ "comparison_profile": "cpp-native166-corrected-five-20261012-v1",
153
+ "created_at": "2026-10-13T07:51:43.793377+00:00",
154
+ "dataset_bindings_sha256": "c263fc568955bd54e4401ba7dc04bd38ee381fc3126bbcbc518ed596b3d89ec6",
155
+ "dataset_count": 5,
156
+ "dataset_ids": [
157
+ "trending_stocks_yahoo_finance",
158
+ "github_top_projects",
159
+ "traqq_weekly_activity",
160
+ "us_stock_financial_ratios",
161
+ "magseven_ml_ready_high_frequency_anomaly"
162
+ ],
163
+ "excluded_fresh_historical_partial_count": 4,
164
+ "excluded_fresh_historical_partials": [
165
+ {
166
+ "bytes": 13972793,
167
+ "failed_terminal_bytes": 13666,
168
+ "failed_terminal_sha256": "6ed3e8a9690354de6e73655b71c310114a4a8ac8e004f0dbae55bb122bcb3d36",
169
+ "method": "XZ",
170
+ "method_id": "3c01374a220b9818",
171
+ "relative": "attempts/freshretailnet_50k/3c01374a220b9818/frames/partial/139cf9bb678ccb11e27a8899b657ae44c325d396cbc77231c8a3ecf2bc782b73.ngb1.partial",
172
+ "sha256": "88c90ba6f4802bde9aa5e6991af5eabc2954b626cd8abaa53d23a60f70c88168",
173
+ "terminal_status": "failed_closed"
174
+ },
175
+ {
176
+ "bytes": 20414806,
177
+ "failed_terminal_bytes": 21911,
178
+ "failed_terminal_sha256": "5de774f9bdf599fb017874e1bedd9334212452e66e58e51ce46dc6e6f8c9b0f0",
179
+ "method": "Lizard",
180
+ "method_id": "943b1f9df88791bc",
181
+ "relative": "attempts/freshretailnet_50k/943b1f9df88791bc/frames/partial/08090fa0a5b038d9a40a76d75287dd42110a59d61ba51f810b39d220f8d87224.ngb1.partial",
182
+ "sha256": "581c0064b1e654e465dcbdd70b9c354545b9aebf1e50a7781e2d22025191e29f",
183
+ "terminal_status": "failed_closed"
184
+ },
185
+ {
186
+ "bytes": 25746919,
187
+ "failed_terminal_bytes": 17970,
188
+ "failed_terminal_sha256": "100b718d0a256c5d519f9f649e18607184846bcbb110a0066e4680974cc8d702",
189
+ "method": "LZHAM",
190
+ "method_id": "aee3568a55b5976b",
191
+ "relative": "attempts/freshretailnet_50k/aee3568a55b5976b/frames/partial/3e77b8fc0aec1534f29207fb52092e7bf00bff4e331291c7ad1d108256c84573.ngb1.partial",
192
+ "sha256": "915dffa8c258bcc54d81fc728ffab52b731e3dd2ce81e0d241439e388ebb0aa7",
193
+ "terminal_status": "failed_closed"
194
+ },
195
+ {
196
+ "bytes": 27598134,
197
+ "failed_terminal_bytes": 10629,
198
+ "failed_terminal_sha256": "c9dffe515d03e8972091c0e0d93db23b5efc6b68f919863ff346f5e9e28f8ad4",
199
+ "method": "Crush",
200
+ "method_id": "fd4982bc31020a05",
201
+ "relative": "attempts/freshretailnet_50k/fd4982bc31020a05/frames/partial/f90965abfe62d3d75d353a7e1a08e8dd03a0a4da03d789011ce216bc3758da22.ngb1.partial",
202
+ "sha256": "e6e6841c882d659be2fc2eb60ebd39cccb78f3253a448bc942c6b7392cb68b08",
203
+ "terminal_status": "failed_closed"
204
+ }
205
+ ],
206
+ "execution_host": "166.111.68.166",
207
+ "full_510_partial_clean_claimed": false,
208
+ "independent_acceptance": {
209
+ "accepted_universe_count": 425,
210
+ "bytes": 13246,
211
+ "file": "CORRECTED_FIVE425_INDEPENDENT_ACCEPTANCE.json",
212
+ "sha256": "f1e282b1a26b89128f71fdcc9edd9aa611141b4d25ad91cefaafd66317b44656",
213
+ "status": "accepted"
214
+ },
215
+ "input_cohort": "six-dataset-corrected-five-20261012-v1",
216
+ "method_count": 85,
217
+ "no_numeric_mixed_terminal_pair_count": 0,
218
+ "numeric_mixed_terminal_pair_count": 40,
219
+ "numeric_pair_count": 386,
220
+ "original_campaign_counts": {
221
+ "accepted": 495,
222
+ "failed_closed": 15
223
+ },
224
+ "original_campaign_start": {
225
+ "bytes": 6833,
226
+ "sha256": "10c890cb06210d081ee1a0a646fe95bbff3d713acda488e9aca8936531b0d9a3"
227
+ },
228
+ "original_campaign_terminal": {
229
+ "bytes": 369,
230
+ "sha256": "e2613fbd9206f65e7423ea57314a470643dae092d8a9c9c37d99c52415955d27"
231
+ },
232
+ "original_worker_returncodes": [
233
+ 1,
234
+ 1,
235
+ 1,
236
+ 1,
237
+ 1,
238
+ 1,
239
+ 1,
240
+ 1
241
+ ],
242
+ "original_worker_states": [
243
+ {
244
+ "bytes": 127,
245
+ "sha256": "b35ce998ac8e32a6ed4bf32a93668605962e906c42cc8dba3e5f6537aff1b597"
246
+ },
247
+ {
248
+ "bytes": 127,
249
+ "sha256": "513795128f8247832f6685fe75b6dc368430775aa27ec04c020a198675cc4dcb"
250
+ },
251
+ {
252
+ "bytes": 127,
253
+ "sha256": "e7c7e82e6cb1cfb5ce625dfa7ca2e31a899bde30d987f0c1bf448b79bd6d5268"
254
+ },
255
+ {
256
+ "bytes": 127,
257
+ "sha256": "f746d375d4735bcb27e2b1b50f7b52a60d50ae39016b0f597a362c40705b175d"
258
+ },
259
+ {
260
+ "bytes": 127,
261
+ "sha256": "bb735f944b6b0ecca752ba09fbd457c866a2054a3e05d50a1da30598fb7947ba"
262
+ },
263
+ {
264
+ "bytes": 127,
265
+ "sha256": "b8ed085bfc3e621f479343945077ecdcb895a028041a674bf1f8de015c6f2fb5"
266
+ },
267
+ {
268
+ "bytes": 127,
269
+ "sha256": "0eeccfd66715af1cc891e74f83a22083e450eefdfa51e98e2ac7e349825ce5c3"
270
+ },
271
+ {
272
+ "bytes": 127,
273
+ "sha256": "53d37e06cad843a3641f825ccb28bfc9ea47f612877d08b4955634f0c7fac0f3"
274
+ }
275
+ ],
276
+ "pair_count": 425,
277
+ "pair_identity_sha256": "ffe0a7a67974112410d494a6e4104904108809aacd68b6f88e9232e052e75d31",
278
+ "pair_terminal_class_counts": {
279
+ "measured_numeric_mixed_terminal": 40,
280
+ "measured_numeric_only": 346,
281
+ "no_numeric_all_unsupported": 39
282
+ },
283
+ "partition_counts": {
284
+ "base_accepted": 416,
285
+ "exact_support_boundary": 8,
286
+ "isolated_bzip3_repair": 1
287
+ },
288
+ "partition_identity_sha256": {
289
+ "base_accepted": "d76358f9175db5a5edccb085da05bac62f6e9536f6b3db2d2724d8ce4f145164",
290
+ "exact_support_boundary": "2803060669d80fd2cf15c568cd802a2a273e751aea1f6cf09caf5c7da499c1d1",
291
+ "isolated_bzip3_repair": "9055d85295e5b3d3fe7c942fb147abecbf978ed6e11c568b22ba113df59bd82d"
292
+ },
293
+ "records": {
294
+ "bytes": 700127,
295
+ "file": "corrected-five425-portable-results.jsonl.gz",
296
+ "row_count": 425,
297
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
298
+ },
299
+ "schema": "compressionbenchmark-corrected-five425-portable-manifest-v1",
300
+ "scientific_timing_accepted": false,
301
+ "selected_failed_frame_directories": [
302
+ {
303
+ "dataset_id": "magseven_ml_ready_high_frequency_anomaly",
304
+ "method": "BUFF",
305
+ "method_id": "ddca15a88639d8a0"
306
+ },
307
+ {
308
+ "dataset_id": "magseven_ml_ready_high_frequency_anomaly",
309
+ "method": "CORAD",
310
+ "method_id": "e5ea904ece91f756"
311
+ },
312
+ {
313
+ "dataset_id": "traqq_weekly_activity",
314
+ "method": "BUFF",
315
+ "method_id": "ddca15a88639d8a0"
316
+ },
317
+ {
318
+ "dataset_id": "traqq_weekly_activity",
319
+ "method": "CORAD",
320
+ "method_id": "e5ea904ece91f756"
321
+ },
322
+ {
323
+ "dataset_id": "trending_stocks_yahoo_finance",
324
+ "method": "BUFF",
325
+ "method_id": "ddca15a88639d8a0"
326
+ },
327
+ {
328
+ "dataset_id": "trending_stocks_yahoo_finance",
329
+ "method": "CORAD",
330
+ "method_id": "e5ea904ece91f756"
331
+ },
332
+ {
333
+ "dataset_id": "us_stock_financial_ratios",
334
+ "method": "BUFF",
335
+ "method_id": "ddca15a88639d8a0"
336
+ },
337
+ {
338
+ "dataset_id": "us_stock_financial_ratios",
339
+ "method": "Bzip3",
340
+ "method_id": "25a7dc986562ff7c"
341
+ },
342
+ {
343
+ "dataset_id": "us_stock_financial_ratios",
344
+ "method": "CORAD",
345
+ "method_id": "e5ea904ece91f756"
346
+ }
347
+ ],
348
+ "selected_source_active_pid_count": 0,
349
+ "selected_source_partial_path_count": 0,
350
+ "selected_source_scope_quiescent": true,
351
+ "source_manifest_sha256": "872a3c370a92a5a694a7e149af312b06f1753d8f2c6a9af506a82639aa330371",
352
+ "source_quiescence_scope": "exact_selected425_with_excluded_fresh_history",
353
+ "status": "accepted_portable_export",
354
+ "support_boundary_policy": "preserved_as_public_conclusion_coverage_never_numeric_ranking",
355
+ "timing_policy": "none_public_timing_null_pending_separate_admission",
356
+ "timing_profile": {
357
+ "repeats": 3,
358
+ "threads": 1,
359
+ "warmups": 1
360
+ },
361
+ "website_publication_approved": false,
362
+ "website_rows": {
363
+ "bytes": 112109,
364
+ "file": "corrected-five425-website-rows.jsonl.gz",
365
+ "row_count": 858,
366
+ "sha256": "536b91ec5f5914f20ea2567c64982151c86260ad5d38831b826a7360fb011b6a"
367
+ }
368
+ }
NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "baseline_revision": "a21e6ea95d9a6467431c4abb3ba07b3e3195702f",
3
+ "builder_sha256": "9db74a1d19fb9de9004431abad488ea10924e7d74e14c50e3f52e91d9183322c",
4
+ "data_sha256": "b7b542c5731786d0486e89de889f024c7e6f69eacb68a7df67bc00179b07af4c",
5
+ "manifest_sha256": "c236d7f305335beb2552fa0f1e57256a7e0e7babdec6c383a790dc3a89e6089a",
6
+ "new_dataset_result_count": 858,
7
+ "old_dataset_result_count": 91701,
8
+ "portable_manifest_sha256": "57718e15382db52fc01feb6de0358ac2d82119e63667e038f3d4c8990f7bfb8f",
9
+ "portable_records_sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11",
10
+ "schema": "compressionbenchmark-corrected-five425-integration-v1",
11
+ "scope": {
12
+ "active_method_count": 85,
13
+ "all_na_pair_count": 0,
14
+ "all_unsupported_pair_count": 39,
15
+ "comparison_profile": "cpp-native166-corrected-five-20261012-v1",
16
+ "conclusion_pair_count": 425,
17
+ "dataset_count": 5,
18
+ "dataset_ids": [
19
+ "github_top_projects",
20
+ "magseven_ml_ready_high_frequency_anomaly",
21
+ "traqq_weekly_activity",
22
+ "trending_stocks_yahoo_finance",
23
+ "us_stock_financial_ratios"
24
+ ],
25
+ "fresh114_result_count": 0,
26
+ "fresh114_status": "pending_new_server192_experiment",
27
+ "independent_acceptance_sha256": "f1e282b1a26b89128f71fdcc9edd9aa611141b4d25ad91cefaafd66317b44656",
28
+ "input_version": "six-numeric-repair-20261012-v1",
29
+ "numeric_mixed_terminal_pair_count": 40,
30
+ "numeric_pair_count": 386,
31
+ "old_profiles_retained": true,
32
+ "portable_manifest": {
33
+ "file": "CORRECTED_FIVE425_PORTABLE_MANIFEST.json",
34
+ "sha256": "57718e15382db52fc01feb6de0358ac2d82119e63667e038f3d4c8990f7bfb8f"
35
+ },
36
+ "portable_records": {
37
+ "file": "corrected-five425-portable-results.jsonl.gz",
38
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
39
+ },
40
+ "special_support_review_pair_count": 8,
41
+ "timing_admitted": false
42
+ },
43
+ "status": "passed_not_published",
44
+ "ui_data_sha256": "ef5aa05289f609f2f62ceed009ee17247c8b4767bba8f4aa8cd522ce83d3521d",
45
+ "unaffected_dataset_results_canonical_sha256": "8fc7e44d2ba90ce0d5b0416ecf561b320c0cd88dd286f7b1ea5c01496e3a48e4"
46
+ }
OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "artifacts": {
3
+ "full_union": {
4
+ "bytes": 5999174,
5
+ "content_encoding": "gzip",
6
+ "file": "operator-byte-effect-full-union.csv.gz",
7
+ "logical_csv": {
8
+ "bytes": 172774462,
9
+ "original_file": "operator-byte-effect-full-union.csv",
10
+ "sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2"
11
+ },
12
+ "media_type": "text/csv",
13
+ "row_count": 41090,
14
+ "schema": "paper164-operator-byte-effect-full-union-v1",
15
+ "sha256": "c6962b9e57a59b50a2e4fa0dc0db9789541a763ea46f4b0cfb7cafd3b88dd22d"
16
+ },
17
+ "recovered_overlay": {
18
+ "bytes": 3965730,
19
+ "content_encoding": "gzip",
20
+ "file": "operator-byte-effect-recovered-overlay.csv.gz",
21
+ "logical_csv": {
22
+ "bytes": 152130791,
23
+ "original_file": "operator-byte-effect-recovered-overlay.csv",
24
+ "sha256": "4f6e206ea2b7561e1332d994e563b2fdf69ed7c368b118745fc9560c15c23082"
25
+ },
26
+ "media_type": "text/csv",
27
+ "row_count": 970,
28
+ "schema": "paper164-operator970-byte-effect-overlay-v1",
29
+ "sha256": "4375b342f7d5eae7061c1016534b5939b4851e2ed162a130439cfac47b826b54"
30
+ }
31
+ },
32
+ "builder": {
33
+ "file": "build_gzip_storage_recovery.py",
34
+ "public_copy_sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401",
35
+ "sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401"
36
+ },
37
+ "csv_audit": {
38
+ "full_union": {
39
+ "row_count": 41090,
40
+ "status_counts": {
41
+ "N/A": 2734,
42
+ "ok": 25635,
43
+ "unsupported": 12721
44
+ },
45
+ "timing_null_field_count": 18
46
+ },
47
+ "recovered_overlay": {
48
+ "row_count": 970,
49
+ "status_counts": {
50
+ "ok": 970
51
+ },
52
+ "timing_null_field_count": 18
53
+ }
54
+ },
55
+ "derived_candidate": {
56
+ "index_file": "index.html",
57
+ "index_sha256": "850e01c007af6eb02b933f3e0e32c487f493198e1fbc3ec467c286b8b5ee8ccb",
58
+ "manifest_file": "manifest.json",
59
+ "manifest_sha256": "c226349a05d564cfc2498397c30e51308cc8dcfb65df94e9e7927527af955b88",
60
+ "operator_summary_file": "operator-byte-effect-summary.json",
61
+ "operator_summary_sha256": "f7c790574fe7d5ce4497eee5ed5ee4797cca319255ad0f1fbf775dc665212228"
62
+ },
63
+ "invariants": {
64
+ "all_18_timing_fields_null": true,
65
+ "data_ui_ranking_app_byte_identical": true,
66
+ "full_union_row_count": 41090,
67
+ "native_scientific_rows_changed": 0,
68
+ "original_uncompressed_csv_files_published": false,
69
+ "recovered_overlay_row_count": 970,
70
+ "source_native_integration_preserved_byte_identical": true,
71
+ "source_native_receipt_binds_source_manifest_not_derived_manifest": true,
72
+ "source_operator_integration_preserved_byte_identical": true
73
+ },
74
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1",
75
+ "scope": "lossless physical storage repack of two operator CSV artifacts only",
76
+ "source_candidate": {
77
+ "manifest_sha256": "c236d7f305335beb2552fa0f1e57256a7e0e7babdec6c383a790dc3a89e6089a",
78
+ "native_integration_file": "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json",
79
+ "native_integration_sha256": "925e5349498dfa99ae9577dff0885ead384ab56db7577d1cc26909e9b9684691",
80
+ "operator_integration_file": "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json",
81
+ "operator_integration_sha256": "e119538a094c51f32f0da868aacfc803e5b9b2a661e67162ceeed9a26540dc50",
82
+ "operator_summary_sha256": "a00f86daadd22121fca5444ee9800f1bdbe6db1805c47290bb2810284e5a6b9e",
83
+ "release_plan_sha256": "e3cb04f784e48dc639b11fab872713b09e8c8b972d6278eb760ea6b45958f1e6"
84
+ },
85
+ "status": "passed_not_published",
86
+ "unchanged_required_public_files": {
87
+ "app.js": {
88
+ "bytes": 54077,
89
+ "sha256": "efe5b9e89d7b0f75e765360f073f4f5d62889660d9cfc546c0e49813d79f2433"
90
+ },
91
+ "data.json": {
92
+ "bytes": 134675991,
93
+ "sha256": "b7b542c5731786d0486e89de889f024c7e6f69eacb68a7df67bc00179b07af4c"
94
+ },
95
+ "ranking.js": {
96
+ "bytes": 4438,
97
+ "sha256": "6e14543b42050ec7ad6a04948e8abd6f3589c477035708f9d01814d05a16c076"
98
+ },
99
+ "ui-data.json": {
100
+ "bytes": 8507043,
101
+ "sha256": "ef5aa05289f609f2f62ceed009ee17247c8b4767bba8f4aa8cd522ce83d3521d"
102
+ }
103
+ }
104
+ }
OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "accepted_input": {
3
+ "handoff_schema": "paper164-byte-effect-completion-handoff-v1",
4
+ "handoff_sha256": "7f769332f4d292ae0ae4743b1785cf6658e72b0394f061c6bac880fd497f241d",
5
+ "operator_union_sha256": "502f829935a69fca842a3ea17cede18b100d0173f95c0076e6c1c8a8089385c2",
6
+ "strict_gate_source_sha256": "16af8a6eafabf3eb7df40f74589d2aa320f4986018eafec86d1934c6fac979ae"
7
+ },
8
+ "composition": "operator evidence and UI added to corrected-five native component",
9
+ "independent_component_review_sha256": "2640195237512d252f20ab9e991cb7d578a2122052daa959c514d66748b13dd3",
10
+ "input_version_notice": "Recovered Fresh57 operator rows use the prior input cohort; they are not Fresh114 results.",
11
+ "invariants": {
12
+ "all_operator_timing_fields_null": 18,
13
+ "corrected_native_data_unchanged_by_operator_composition": true,
14
+ "corrected_native_ui_data_unchanged_by_operator_composition": true,
15
+ "native_rows_added_by_operator_composition": 0,
16
+ "operator_timing_rankings_added": false
17
+ },
18
+ "outputs": {
19
+ "full_union": {
20
+ "bytes": 172774462,
21
+ "file": "operator-byte-effect-full-union.csv",
22
+ "row_count": 41090,
23
+ "schema": "paper164-operator-byte-effect-full-union-v1",
24
+ "sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2"
25
+ },
26
+ "recovered_overlay": {
27
+ "bytes": 152130791,
28
+ "file": "operator-byte-effect-recovered-overlay.csv",
29
+ "row_count": 970,
30
+ "schema": "paper164-operator970-byte-effect-overlay-v1",
31
+ "sha256": "4f6e206ea2b7561e1332d994e563b2fdf69ed7c368b118745fc9560c15c23082"
32
+ },
33
+ "summary": {
34
+ "bytes": 41565,
35
+ "file": "operator-byte-effect-summary.json",
36
+ "schema": "compressionbenchmark-operator-byte-effect-summary-v1",
37
+ "sha256": "a00f86daadd22121fca5444ee9800f1bdbe6db1805c47290bb2810284e5a6b9e"
38
+ }
39
+ },
40
+ "schema": "compressionbenchmark-operator-byte-effect-integration-v2",
41
+ "status": "passed_not_published",
42
+ "strict_component_audit_sha256": "d90dbcb3317bb2209501ae6cbefb2bfc2d4de49c1607e8bfef8545b7cdfb1640",
43
+ "strict_component_freeze_sha256": "ca431c1ad964459db82aad9b229d17a169a61f3f590d9266e4cc9e59eb820342"
44
+ }
README.md CHANGED
@@ -75,3 +75,14 @@ The timing updater verifies the input hashes, replaces existing dataset/runtime/
75
  ## Native86 accepted completion v7
76
 
77
  The independently accepted 328-pair completion closes the 502 original Native86 problem identities for rate/byte reporting. Completion timing remains diagnostic and is excluded from timing and composite rankings. Host, campaign action, binary, adapter configuration and exact eligible support are retained as separate comparison dimensions.
 
 
 
 
 
 
 
 
 
 
 
 
75
  ## Native86 accepted completion v7
76
 
77
  The independently accepted 328-pair completion closes the 502 original Native86 problem identities for rate/byte reporting. Completion timing remains diagnostic and is excluded from timing and composite rankings. Host, campaign action, binary, adapter configuration and exact eligible support are retained as separate comparison dimensions.
78
+
79
+ ## Operator evidence storage packaging
80
+
81
+ The 41,090-row operator evidence download is published as
82
+ `operator-byte-effect-full-union.csv.gz`; decompress it with a standard gzip
83
+ reader to recover the original CSV bytes. The manifest and
84
+ `OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json` record both the physical gzip
85
+ SHA-256 and the logical decompressed CSV SHA-256. The unchanged Native V1 and
86
+ Operator V2 receipts bind the source candidate; the gzip packaging receipt
87
+ binds this derived manifest and preserves the accepted row semantics.
88
+
app.js CHANGED
@@ -37,6 +37,7 @@ const cols = [
37
  ];
38
  let snapshot, records=[], methods=new Map(), datasets=new Map(), currentRows=[], activeTab='overall';
39
  let referenceCatalog=null,referenceCatalogError=null,datasetCatalog=null,datasetCatalogError=null;
 
40
  let sort={key:'compression_rate',direction:1};
41
  let selectedMethod=null;
42
  const state = () => ({runtime:$('runtime').value,dataset:$('dataset').value,dtype:$('dtype').value,precision:$('precision').value,family:$('family').value,mode:$('row-mode').value,search:$('search').value.trim().toLowerCase(),complete:$('complete-only').checked});
@@ -216,6 +217,21 @@ function renderMethodDocumentation() {
216
  status.textContent=`${rows.length} of ${families.length} measured method families shown · ${described} descriptions available`;
217
  container.innerHTML=rows.length?rows.map(({family,entry,names,note})=>{const display=entry.display_name||family;return `<article class="documentation-card"><div class="documentation-card-head"><div><h3>${escape(display)}</h3>${display!==family?`<span class="documentation-code">${escape(family)}</span>`:''}</div><span class="documentation-count">${names.length} configuration${names.length===1?'':'s'}</span></div><p class="documentation-description">${escape(entry.description||'A reference description is not available for this measured family.')}</p>${note?`<p class="documentation-note">${escape(note)}</p>`:''}${renderReferences(entry.reference_ids)}<details class="configuration-details"><summary>Published configurations (${names.length})</summary><ul>${names.map(name=>`<li>${escape(name)}</li>`).join('')}</ul></details></article>`;}).join(''):'<p class="documentation-empty">No method documentation matches this search.</p>';
218
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
219
  function renderOperatorDocumentation() {
220
  const container=$('operator-catalog'),status=$('operator-doc-status');
221
  if(!container||!status)return;
@@ -248,10 +264,10 @@ function renderOperatorImplementation(entry) {
248
  const name=publicText(entry.name_en??entry.name,entry.id||'Implementation entry'),nativeName=publicText(entry.name_zh),layer=publicText(entry.layer,'entry'),fields=[['Principle',entry.description],['Input',entry.inputs],['Output',entry.outputs],['Example',entry.example],['Status',entry.status]].filter(([,value])=>publicText(value));
249
  return `<article class="implementation-entry"><div class="implementation-head"><div><strong>${escape(name)}</strong>${nativeName&&nativeName!==name?`<span class="documentation-native-name">${escape(nativeName)}</span>`:''}${entry.id?`<span class="documentation-code">${escape(publicText(entry.id))}</span>`:''}</div><span class="implementation-layer">${escape(layer)}</span></div>${fields.length?`<dl>${fields.map(([label,value])=>`<div><dt>${escape(label)}</dt><dd>${escape(publicText(value))}</dd></div>`).join('')}</dl>`:''}${entry.reference_ids?.length?renderReferences(entry.reference_ids):''}</article>`;
250
  }
251
- function renderDocumentationViews() { renderMethodDocumentation();renderOperatorDocumentation(); }
252
  async function loadReferenceCatalog() {
253
  try {
254
- const response=await fetch('./reference-catalog.json?v=20261011-native-v6',{cache:'no-cache'});
255
  if(!response.ok)throw new Error(`Reference catalog request returned ${response.status}.`);
256
  const catalog=await response.json();
257
  if(!catalog||!Array.isArray(catalog.methods)||!Array.isArray(catalog.operators)||!Array.isArray(catalog.references))throw new Error('Reference catalog has an invalid schema.');
@@ -297,7 +313,7 @@ function renderDatasetEntry(entry,isMeasured) {
297
  }
298
  async function loadDatasetCatalog() {
299
  try {
300
- const response=await fetch('./dataset-catalog.json?v=20261011-native-v6',{cache:'no-cache'});if(!response.ok)throw new Error(`Dataset catalog request returned ${response.status}.`);
301
  const catalog=await response.json();if(!catalog||!Array.isArray(catalog.datasets)||!catalog.summary)throw new Error('Dataset catalog has an invalid schema.');datasetCatalog=catalog;
302
  } catch(error) { datasetCatalogError=error instanceof Error?error:new Error('Dataset catalog is unavailable.'); }
303
  if(snapshot){populateDatasetControls();renderDatasetCatalog();renderAbout();}
@@ -322,6 +338,8 @@ function init() {
322
  const runtimeOrder=['cpp','java','python'];
323
  const runtimes=[...new Set(records.map(r=>r.runtime))].sort((a,b)=>{const ai=runtimeOrder.indexOf(a),bi=runtimeOrder.indexOf(b);return (ai<0?runtimeOrder.length:ai)-(bi<0?runtimeOrder.length:bi)||a.localeCompare(b);});
324
  $('runtime').innerHTML=runtimes.map(r=>`<option value="${escape(r)}">${escape(runtimeName(r))}</option>`).join('');
 
 
325
  populateDatasetControls();
326
  $('family').innerHTML='<option value="all">All method families</option>'+[...new Set(records.map(r=>r.family))].sort().map(f=>`<option value="${escape(f)}">${escape(f)}</option>`).join('');
327
  $('method-count').textContent=countFmt(new Set(records.map(r=>r.family)).size);$('runtime-count').textContent=runtimes.length;$('record-count').textContent=countFmt(snapshot.coverage?.runtime_configuration_count??new Set(records.map(r=>`${r.runtime}\0${r.method}`)).size);
@@ -352,6 +370,7 @@ function setupTheme() {
352
  }
353
  setupTheme();
354
  void loadReferenceCatalog();
 
355
  void loadDatasetCatalog();
356
- try { const response=await fetch('./ui-data.json?v=20261011-native-v6',{cache:'no-cache'});if(!response.ok)throw new Error(`Snapshot request returned ${response.status}`);snapshot=await response.json();init(); }
357
  catch(e){$('load-error').hidden=false;$('load-error').textContent=`The result snapshot could not be loaded. Please reload the page or download the JSON from the repository. ${e.message}`;$('snapshot').textContent='Snapshot unavailable';$('leaderboard').querySelector('tbody').innerHTML='<tr><td class="empty-cell">Results unavailable.</td></tr>';}
 
37
  ];
38
  let snapshot, records=[], methods=new Map(), datasets=new Map(), currentRows=[], activeTab='overall';
39
  let referenceCatalog=null,referenceCatalogError=null,datasetCatalog=null,datasetCatalogError=null;
40
+ let operatorEffect=null,operatorEffectError=null;
41
  let sort={key:'compression_rate',direction:1};
42
  let selectedMethod=null;
43
  const state = () => ({runtime:$('runtime').value,dataset:$('dataset').value,dtype:$('dtype').value,precision:$('precision').value,family:$('family').value,mode:$('row-mode').value,search:$('search').value.trim().toLowerCase(),complete:$('complete-only').checked});
 
217
  status.textContent=`${rows.length} of ${families.length} measured method families shown · ${described} descriptions available`;
218
  container.innerHTML=rows.length?rows.map(({family,entry,names,note})=>{const display=entry.display_name||family;return `<article class="documentation-card"><div class="documentation-card-head"><div><h3>${escape(display)}</h3>${display!==family?`<span class="documentation-code">${escape(family)}</span>`:''}</div><span class="documentation-count">${names.length} configuration${names.length===1?'':'s'}</span></div><p class="documentation-description">${escape(entry.description||'A reference description is not available for this measured family.')}</p>${note?`<p class="documentation-note">${escape(note)}</p>`:''}${renderReferences(entry.reference_ids)}<details class="configuration-details"><summary>Published configurations (${names.length})</summary><ul>${names.map(name=>`<li>${escape(name)}</li>`).join('')}</ul></details></article>`;}).join(''):'<p class="documentation-empty">No method documentation matches this search.</p>';
219
  }
220
+ function renderOperatorEffect() {
221
+ const status=$('operator-effect-status'),body=$('operator-effect-table')?.querySelector('tbody');if(!status||!body)return;
222
+ if(operatorEffectError){status.textContent='Verified byte-effect results could not be loaded.';body.innerHTML=`<tr><td colspan="7" class="empty-cell">${escape(operatorEffectError.message)}</td></tr>`;return;}
223
+ if(!operatorEffect){status.textContent='Loading verified byte effects…';return;}
224
+ const rows=operatorEffect.rows||[],audit=operatorEffect.audit||{};
225
+ status.textContent=`${rows.length} omitted operators · ${countFmt(audit.admitted_ok_row_count||0)} admitted rows from the exact ${countFmt(audit.input_row_count||0)}-row union · timing unavailable`;
226
+ body.innerHTML=rows.length?rows.map(row=>`<tr><td>${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>';
227
+ }
228
+ async function loadOperatorEffect() {
229
+ try {
230
+ 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 ${response.status}.`);
231
+ const value=await response.json();if(value?.schema!=='compressionbenchmark-operator-byte-effect-summary-v1'||value?.status!=='accepted'||value?.timing?.status!=='unavailable'||!Array.isArray(value.rows))throw new Error('Operator byte-effect summary has an invalid schema.');operatorEffect=value;
232
+ } catch(error) { operatorEffectError=error instanceof Error?error:new Error('Operator byte-effect summary is unavailable.'); }
233
+ renderOperatorEffect();
234
+ }
235
  function renderOperatorDocumentation() {
236
  const container=$('operator-catalog'),status=$('operator-doc-status');
237
  if(!container||!status)return;
 
264
  const name=publicText(entry.name_en??entry.name,entry.id||'Implementation entry'),nativeName=publicText(entry.name_zh),layer=publicText(entry.layer,'entry'),fields=[['Principle',entry.description],['Input',entry.inputs],['Output',entry.outputs],['Example',entry.example],['Status',entry.status]].filter(([,value])=>publicText(value));
265
  return `<article class="implementation-entry"><div class="implementation-head"><div><strong>${escape(name)}</strong>${nativeName&&nativeName!==name?`<span class="documentation-native-name">${escape(nativeName)}</span>`:''}${entry.id?`<span class="documentation-code">${escape(publicText(entry.id))}</span>`:''}</div><span class="implementation-layer">${escape(layer)}</span></div>${fields.length?`<dl>${fields.map(([label,value])=>`<div><dt>${escape(label)}</dt><dd>${escape(publicText(value))}</dd></div>`).join('')}</dl>`:''}${entry.reference_ids?.length?renderReferences(entry.reference_ids):''}</article>`;
266
  }
267
+ function renderDocumentationViews() { renderMethodDocumentation();renderOperatorDocumentation();renderOperatorEffect(); }
268
  async function loadReferenceCatalog() {
269
  try {
270
+ const response=await fetch('./reference-catalog.json?v=20261013-corrected-five-v1',{cache:'no-cache'});
271
  if(!response.ok)throw new Error(`Reference catalog request returned ${response.status}.`);
272
  const catalog=await response.json();
273
  if(!catalog||!Array.isArray(catalog.methods)||!Array.isArray(catalog.operators)||!Array.isArray(catalog.references))throw new Error('Reference catalog has an invalid schema.');
 
313
  }
314
  async function loadDatasetCatalog() {
315
  try {
316
+ const response=await fetch('./dataset-catalog.json?v=20261013-corrected-five-v1',{cache:'no-cache'});if(!response.ok)throw new Error(`Dataset catalog request returned ${response.status}.`);
317
  const catalog=await response.json();if(!catalog||!Array.isArray(catalog.datasets)||!catalog.summary)throw new Error('Dataset catalog has an invalid schema.');datasetCatalog=catalog;
318
  } catch(error) { datasetCatalogError=error instanceof Error?error:new Error('Dataset catalog is unavailable.'); }
319
  if(snapshot){populateDatasetControls();renderDatasetCatalog();renderAbout();}
 
338
  const runtimeOrder=['cpp','java','python'];
339
  const runtimes=[...new Set(records.map(r=>r.runtime))].sort((a,b)=>{const ai=runtimeOrder.indexOf(a),bi=runtimeOrder.indexOf(b);return (ai<0?runtimeOrder.length:ai)-(bi<0?runtimeOrder.length:bi)||a.localeCompare(b);});
340
  $('runtime').innerHTML=runtimes.map(r=>`<option value="${escape(r)}">${escape(runtimeName(r))}</option>`).join('');
341
+ const requestedProfile=new URLSearchParams(location.search).get('profile');
342
+ if(runtimes.includes(requestedProfile))$('runtime').value=requestedProfile;
343
  populateDatasetControls();
344
  $('family').innerHTML='<option value="all">All method families</option>'+[...new Set(records.map(r=>r.family))].sort().map(f=>`<option value="${escape(f)}">${escape(f)}</option>`).join('');
345
  $('method-count').textContent=countFmt(new Set(records.map(r=>r.family)).size);$('runtime-count').textContent=runtimes.length;$('record-count').textContent=countFmt(snapshot.coverage?.runtime_configuration_count??new Set(records.map(r=>`${r.runtime}\0${r.method}`)).size);
 
370
  }
371
  setupTheme();
372
  void loadReferenceCatalog();
373
+ void loadOperatorEffect();
374
  void loadDatasetCatalog();
375
+ try { const response=await fetch('./ui-data.json?v=20261013-corrected-five-v1',{cache:'no-cache'});if(!response.ok)throw new Error(`Snapshot request returned ${response.status}`);snapshot=await response.json();init(); }
376
  catch(e){$('load-error').hidden=false;$('load-error').textContent=`The result snapshot could not be loaded. Please reload the page or download the JSON from the repository. ${e.message}`;$('snapshot').textContent='Snapshot unavailable';$('leaderboard').querySelector('tbody').innerHTML='<tr><td class="empty-cell">Results unavailable.</td></tr>';}
build_corrected425_site.py ADDED
@@ -0,0 +1,572 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """Add an independently exported corrected-five cohort to immutable site v7.
3
+
4
+ This consumes only the exact 425-pair portable contract. It preserves every
5
+ old dataset result and does not admit diagnostic timing or Fresh114 results.
6
+ Publishing is deliberately a separate operation.
7
+ """
8
+ from __future__ import annotations
9
+
10
+ import argparse
11
+ from collections import Counter, defaultdict
12
+ import datetime as dt
13
+ import gzip
14
+ import hashlib
15
+ import importlib.util
16
+ import json
17
+ import math
18
+ from pathlib import Path
19
+ import re
20
+ import shutil
21
+ import subprocess
22
+ import sys
23
+
24
+ HERE = Path(__file__).resolve().parent
25
+ PROFILE = "cpp-native166-corrected-five-20261012-v1"
26
+ BASE_REVISION = "a21e6ea95d9a6467431c4abb3ba07b3e3195702f"
27
+ V7_BUILDER_SHA = "ce40ab62b9548e69f9ab143b3f0e877aa218cb74be397cea4d06ea3b7fef1130"
28
+ SOURCE_MANIFEST_SHA = "872a3c370a92a5a694a7e149af312b06f1753d8f2c6a9af506a82639aa330371"
29
+ IDENTITY_SHA = "ffe0a7a67974112410d494a6e4104904108809aacd68b6f88e9232e052e75d31"
30
+ DATASETS = {"trending_stocks_yahoo_finance", "github_top_projects",
31
+ "traqq_weekly_activity", "us_stock_financial_ratios",
32
+ "magseven_ml_ready_high_frequency_anomaly"}
33
+ PUBLIC_RECORDS = "corrected-five425-portable-results.jsonl.gz"
34
+ PUBLIC_MANIFEST = "CORRECTED_FIVE425_PORTABLE_MANIFEST.json"
35
+ PUBLIC_ACCEPTANCE = "CORRECTED_FIVE425_INDEPENDENT_ACCEPTANCE.json"
36
+ PUBLIC_WEBSITE_ROWS = "corrected-five425-website-rows.jsonl.gz"
37
+ PUBLIC_INTEGRATION = "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json"
38
+ VERSION = "20261013-corrected-five-v1"
39
+ HEX64 = re.compile(r"[0-9a-f]{64}")
40
+
41
+
42
+ def require(value, message):
43
+ if not value:
44
+ raise ValueError(message)
45
+
46
+
47
+ def sha(path):
48
+ h = hashlib.sha256()
49
+ with Path(path).open("rb") as stream:
50
+ for block in iter(lambda: stream.read(1 << 20), b""):
51
+ h.update(block)
52
+ return h.hexdigest()
53
+
54
+
55
+ def canonical(value):
56
+ return json.dumps(value, ensure_ascii=False, sort_keys=True,
57
+ separators=(",", ":"), allow_nan=False).encode()
58
+
59
+
60
+ def identity_sha(pairs):
61
+ return hashlib.sha256(json.dumps(sorted(
62
+ f"{p['dataset_id']}\0{p['method']}" for p in pairs),
63
+ ensure_ascii=False, separators=(",", ":")).encode()).hexdigest()
64
+
65
+
66
+ def read(path):
67
+ return json.loads(Path(path).read_text())
68
+
69
+
70
+ def write(path, value):
71
+ Path(path).write_text(json.dumps(value, ensure_ascii=False, indent=2,
72
+ sort_keys=True, allow_nan=False) + "\n")
73
+
74
+
75
+ def stable_ref(path):
76
+ path = Path(path)
77
+ before = path.lstat()
78
+ require(not path.is_symlink() and path.is_file(), "input must be a regular file")
79
+ digest = sha(path)
80
+ after = path.lstat()
81
+ fingerprint = lambda s: (s.st_dev, s.st_ino, s.st_size, s.st_mtime_ns, s.st_ctime_ns)
82
+ require(fingerprint(before) == fingerprint(after), "input changed while hashing")
83
+ return {"bytes": after.st_size, "sha256": digest, "stat": fingerprint(after)}
84
+
85
+
86
+ def validate_baseline_paths(files):
87
+ require(len(files) == 32 and len({f["path"] for f in files}) == 32,
88
+ "baseline file identities differ")
89
+ for ref in files:
90
+ name = Path(ref["path"])
91
+ require(set(ref) == {"path", "bytes", "sha256"} and
92
+ not name.is_absolute() and len(name.parts) == 1 and
93
+ ref["path"] not in {"", ".", ".."} and
94
+ type(ref["bytes"]) is int and ref["bytes"] >= 0 and
95
+ HEX64.fullmatch(str(ref["sha256"])),
96
+ "unsafe or malformed baseline file reference")
97
+
98
+
99
+ def integrate_operator_component(args, output, site_manifest):
100
+ """Compose an actually reviewed strict operator component before final hashes."""
101
+ if args.operator_component is None:
102
+ require(args.operator_freeze_sha256 is None and args.operator_review is None and
103
+ args.operator_review_sha256 is None, "partial operator component arguments")
104
+ return
105
+ component = args.operator_component.resolve()
106
+ freeze_path = component / "qa/SITE_OPERATOR_BYTE_EFFECT_FREEZE_RECEIPT.json"
107
+ require(sha(freeze_path) == args.operator_freeze_sha256 and
108
+ sha(args.operator_review) == args.operator_review_sha256,
109
+ "operator component freeze/review SHA differs")
110
+ freeze, review = read(freeze_path), read(args.operator_review)
111
+ require(freeze.get("status") == "passed_not_published" and
112
+ freeze.get("publish_file_count") == 36 and
113
+ isinstance(freeze.get("publish_files"), dict) and
114
+ len(freeze["publish_files"]) == 36 and
115
+ review.get("status") == "passed" and
116
+ review.get("approved_for_composition") is True and
117
+ review.get("candidate_freeze_sha256") == args.operator_freeze_sha256,
118
+ "operator component lacks actual independent approval")
119
+ for name, digest in freeze["publish_files"].items():
120
+ require(len(Path(name).parts) == 1 and not Path(name).is_absolute() and
121
+ not (component / name).is_symlink() and
122
+ sha(component / name) == digest, "operator component file drift")
123
+ audit_path = component / "qa/SITE_OPERATOR_BYTE_EFFECT_SEMANTIC_AUDIT.json"
124
+ require(sha(audit_path) == freeze["semantic_audit_sha256"] and
125
+ read(audit_path).get("status") == "PASS", "operator component audit differs")
126
+ for name in ("data.json", "ui-data.json", "ranking.js"):
127
+ require(sha(component / name) == sha(args.base / name),
128
+ "operator component changed frozen native/ranking input")
129
+ source = HERE.parent / "site_operator_byte_effect_20261011_v1/build_operator_byte_effect_site.py"
130
+ require(sha(source) == "87e5562ff1ba512a5e8d447e13a85d678cd87a87626116f890a121d4d0ceda01",
131
+ "frozen operator component builder differs")
132
+ spec = importlib.util.spec_from_file_location("corrected425_operator_component", source)
133
+ operator = importlib.util.module_from_spec(spec)
134
+ sys.modules[spec.name] = operator
135
+ spec.loader.exec_module(operator)
136
+ full_name = "operator-byte-effect-full-union.csv"
137
+ overlay_name = "operator-byte-effect-recovered-overlay.csv"
138
+ summary_name = "operator-byte-effect-summary.json"
139
+ rows, overlay = operator.read_csv(component / full_name), operator.read_csv(component / overlay_name)
140
+ operator.validate_public_rows(rows, overlay)
141
+ summary_rows, _ = operator.aggregate_rows(rows)
142
+ summary = read(component / summary_name)
143
+ require(summary.get("status") == "accepted" and summary["rows"] == summary_rows and
144
+ summary["timing"]["field_count"] == 18 and
145
+ summary["timing"]["admission"] == "none_all_fields_null_cross_host_timing_forbidden",
146
+ "operator summary or timing boundary differs")
147
+ for name in (full_name, overlay_name, summary_name):
148
+ shutil.copy2(component / name, output / name)
149
+ require(sha(output / name) == freeze["publish_files"][name], "operator copy drift")
150
+ old = read(component / "OPERATOR970_BYTE_EFFECT_INTEGRATION_V1.json")
151
+ actual_outputs = {
152
+ "full_union": operator.public_ref(component / full_name, schema=operator.FULL_SCHEMA, row_count=41090),
153
+ "recovered_overlay": operator.public_ref(component / overlay_name, schema=operator.OVERLAY_SCHEMA, row_count=970),
154
+ "summary": operator.public_ref(component / summary_name, schema=summary["schema"]),
155
+ }
156
+ require(old.get("status") == "passed_not_published" and
157
+ old.get("outputs") == actual_outputs and
158
+ old["accepted_input"]["strict_gate_source_sha256"] ==
159
+ "16af8a6eafabf3eb7df40f74589d2aa320f4986018eafec86d1934c6fac979ae",
160
+ "operator component acceptance binding differs")
161
+ integration_name = "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json"
162
+ integration = {
163
+ "schema": "compressionbenchmark-operator-byte-effect-integration-v2",
164
+ "status": "passed_not_published", "accepted_input": old["accepted_input"],
165
+ "outputs": old["outputs"], "strict_component_freeze_sha256": args.operator_freeze_sha256,
166
+ "strict_component_audit_sha256": freeze["semantic_audit_sha256"],
167
+ "independent_component_review_sha256": args.operator_review_sha256,
168
+ "composition": "operator evidence and UI added to corrected-five native component",
169
+ "invariants": {"corrected_native_data_unchanged_by_operator_composition": True,
170
+ "corrected_native_ui_data_unchanged_by_operator_composition": True,
171
+ "native_rows_added_by_operator_composition": 0,
172
+ "all_operator_timing_fields_null": 18,
173
+ "operator_timing_rankings_added": False},
174
+ "input_version_notice": "Recovered Fresh57 operator rows use the prior input cohort; they are not Fresh114 results.",
175
+ }
176
+ write(output / integration_name, integration)
177
+ operator.modify_ui(output)
178
+ component_manifest = read(component / "manifest.json")
179
+ section = component_manifest["operator_byte_effect"]
180
+ require(all(section.get(k) == actual_outputs[k] for k in actual_outputs) and
181
+ section.get("timing_admission") == "none_all_fields_null_cross_host_timing_forbidden" and
182
+ section.get("integration") == operator.public_ref(
183
+ component / "OPERATOR970_BYTE_EFFECT_INTEGRATION_V1.json", schema=old["schema"]),
184
+ "operator component manifest evidence closure differs")
185
+ section["integration"] = operator.public_ref(output / integration_name, schema=integration["schema"])
186
+ section["input_version_notice"] = integration["input_version_notice"]
187
+ site_manifest["operator_byte_effect"] = section
188
+
189
+
190
+ def validate_portable_closure(manifest, records_path, acceptance_path,
191
+ website_rows_path, expected_acceptance_sha):
192
+ """Keep accepted portable basenames and validate every direct file reference."""
193
+ for field, path, name in (("records", records_path, PUBLIC_RECORDS),
194
+ ("independent_acceptance", acceptance_path, PUBLIC_ACCEPTANCE),
195
+ ("website_rows", website_rows_path, PUBLIC_WEBSITE_ROWS)):
196
+ ref = manifest.get(field) or {}
197
+ require(Path(path).name == name and ref.get("file") == name and
198
+ not Path(path).is_symlink() and Path(path).is_file() and
199
+ ref.get("bytes") == Path(path).stat().st_size and
200
+ ref.get("sha256") == sha(path),
201
+ f"portable {field} closure has a missing, renamed, or changed file")
202
+ require(sha(acceptance_path) == expected_acceptance_sha,
203
+ "actual acceptance receipt SHA differs")
204
+ accepted = read(acceptance_path)
205
+ require(accepted.get("schema") ==
206
+ "compressionbenchmark-corrected-five425-independent-acceptance-v2" and
207
+ accepted.get("status") == "accepted" and accepted.get("pair_count") == 425 and
208
+ accepted.get("pair_identity_sha256") == IDENTITY_SHA and
209
+ accepted.get("source_manifest_sha256") == SOURCE_MANIFEST_SHA and
210
+ accepted.get("selected_source_scope_quiescent") is True and
211
+ accepted.get("source_quiescence_scope") ==
212
+ "exact_selected425_with_excluded_fresh_history" and
213
+ accepted.get("selected_source_active_pid_count") == 0 and
214
+ accepted.get("selected_source_partial_path_count") == 0 and
215
+ accepted.get("excluded_fresh_historical_partial_count") == 4 and
216
+ accepted.get("all_source_partial_count_observed") == 4 and
217
+ accepted.get("full_510_partial_clean_claimed") is False and
218
+ accepted.get("scientific_timing_accepted") is False and
219
+ accepted.get("records") == manifest.get("records") and
220
+ accepted.get("partition_counts") == {
221
+ "base_accepted": 416, "exact_support_boundary": 8,
222
+ "isolated_bzip3_repair": 1},
223
+ "actual independent acceptance scope, provenance, or closure differs")
224
+ excluded = accepted.get("excluded_fresh_historical_partials") or []
225
+ require(len(excluded) == 4 and {row.get("method_id") for row in excluded} == {
226
+ "3c01374a220b9818", "943b1f9df88791bc", "fd4982bc31020a05", "aee3568a55b5976b"},
227
+ "excluded history is not the observed four Fresh attempts")
228
+ for row in excluded:
229
+ require(str(row.get("relative", "")).startswith("attempts/freshretailnet_50k/")
230
+ and HEX64.fullmatch(str(row.get("sha256", ""))) and
231
+ type(row.get("bytes")) is int and row["bytes"] > 0,
232
+ "excluded Fresh history lacks exact preserved bytes")
233
+ require(accepted.get("source_validators") == {
234
+ "base_acceptor_sha256": "440b61548ffe0f38806d1520ff280aca5a8bfc0998270f0e4112f7836a5c6923",
235
+ "support_verifier_sha256": "8108b31c14ce99d8376e5ac77a2caab72342da38e096b2a834c4fa6f166383ed",
236
+ "overlay_acceptor_sha256": "8aee16785fd9ef7b58ad549e25f9bd5da6d54829dbd3cf9d5b8a57c2b7e9c4c8",
237
+ }, "independent acceptance validators differ")
238
+ with gzip.open(website_rows_path, "rt") as stream:
239
+ website = [json.loads(line) for line in stream if line.strip()]
240
+ require(len(website) == manifest["website_rows"].get("row_count") and
241
+ all(r.get("comparison_profile") == PROFILE for r in website),
242
+ "source-side website projection count/profile differs")
243
+ return accepted
244
+
245
+
246
+ def load_portable(manifest_path, records_path, expected_manifest_sha,
247
+ expected_acceptance_sha):
248
+ require(sha(manifest_path) == expected_manifest_sha,
249
+ "portable manifest SHA differs from independently reviewed input")
250
+ manifest = read(manifest_path)
251
+ require(manifest.get("schema") ==
252
+ "compressionbenchmark-corrected-five425-portable-manifest-v1" and
253
+ manifest.get("status") == "accepted_portable_export" and
254
+ manifest.get("pair_count") == 425 and
255
+ set(manifest.get("dataset_ids", [])) == DATASETS and
256
+ manifest.get("Fresh_excluded") is True and
257
+ manifest.get("source_manifest_sha256") == SOURCE_MANIFEST_SHA and
258
+ manifest.get("pair_identity_sha256") == IDENTITY_SHA and
259
+ manifest.get("timing_policy") ==
260
+ "none_public_timing_null_pending_separate_admission",
261
+ "portable scope, input identity, or timing contract differs")
262
+ acceptance = manifest.get("independent_acceptance") or {}
263
+ require(acceptance.get("sha256") == expected_acceptance_sha and
264
+ HEX64.fullmatch(expected_acceptance_sha),
265
+ "portable independent acceptance binding differs")
266
+ ref = manifest.get("records") or {}
267
+ require(ref.get("sha256") == sha(records_path) and
268
+ ref.get("bytes") == Path(records_path).stat().st_size and
269
+ ref.get("row_count") == 425, "portable records SHA/size/count differs")
270
+ with gzip.open(records_path, "rt") as stream:
271
+ pairs = [json.loads(line) for line in stream if line.strip()]
272
+ require(len(pairs) == 425 and identity_sha(pairs) == IDENTITY_SHA,
273
+ "portable exact 425-pair identity differs")
274
+ keys = [(p["dataset_id"], p["method"]) for p in pairs]
275
+ methods = {p["method"] for p in pairs}
276
+ require(len(set(keys)) == 425 and len(methods) == 85 and "GLZA" not in methods
277
+ and set(keys) == {(d, m) for d in DATASETS for m in methods},
278
+ "portable is not exact five datasets by 85 active methods")
279
+ require(not any(token in json.dumps(pairs) for token in
280
+ ("/Users/", "/data/", "analysis_outputs/")),
281
+ "portable contains a private path")
282
+ for pair in pairs:
283
+ require(HEX64.fullmatch(pair.get("binary_sha256", "")),
284
+ "pair has no exact binary identity")
285
+ values = pair.get("result_rows")
286
+ require(isinstance(values, list) and values,
287
+ "pair lacks actual aggregate result conclusions")
288
+ ids = [v.get("aggregate_id") for v in values]
289
+ require(all(ids) and len(ids) == len(set(ids)),
290
+ "pair aggregate identities missing or duplicated")
291
+ for row in values:
292
+ require(row.get("status") in {"ok", "N/A", "unsupported"},
293
+ "nonterminal or failed aggregate in portable export")
294
+ require(all(row.get(field) is None for field in row
295
+ if ("time" in field or "_ns" in field)
296
+ and field not in {"timestamp"}),
297
+ "portable timing must be null")
298
+ if row["status"] == "ok":
299
+ original, compressed = (row.get("original_numeric_bytes"),
300
+ row.get("complete_frame_bytes"))
301
+ require(type(original) is int and original > 0 and
302
+ type(compressed) is int and compressed > 0 and
303
+ type(row.get("row_count")) is int and row["row_count"] > 0,
304
+ "numeric row byte/point count is invalid")
305
+ rate = row.get("compression_rate")
306
+ require(isinstance(rate, (float, int)) and math.isfinite(rate) and
307
+ math.isclose(rate, compressed / original, rel_tol=1e-12),
308
+ "numeric row rate differs from complete frame bytes")
309
+ return manifest, pairs
310
+
311
+
312
+ def result_rows(pairs, acceptance_sha):
313
+ output = []
314
+ for pair in pairs:
315
+ measured = [r for r in pair["result_rows"] if r["status"] == "ok"]
316
+ if not measured:
317
+ continue
318
+ config = pair.get("exact_configuration") or measured[0].get("configuration")
319
+ require(isinstance(config, str) and config and all(
320
+ r.get("configuration", config) == config for r in measured),
321
+ "pair spans inconsistent adapter configurations")
322
+ groups = defaultdict(list)
323
+ for row in measured:
324
+ dtype = str(row["dtype"]).lower()
325
+ scope = "float" if dtype.startswith("float") else "integer" if (
326
+ dtype.startswith("int") or dtype.startswith("uint")) else None
327
+ require(scope is not None, "non-numeric dtype entered numeric ranking")
328
+ groups[scope].append(row)
329
+ if len(measured) == len(pair["result_rows"]):
330
+ groups["overall"] = measured
331
+ for scope, values in sorted(groups.items()):
332
+ original = sum(r["original_numeric_bytes"] for r in values)
333
+ compressed = sum(r["complete_frame_bytes"] for r in values)
334
+ support = hashlib.sha256(json.dumps(sorted(
335
+ str(r["aggregate_id"]) for r in values), ensure_ascii=False,
336
+ separators=(",", ":")).encode()).hexdigest()
337
+ binary = pair["binary_sha256"]
338
+ data_identity = [{
339
+ "aggregate_id": r["aggregate_id"],
340
+ "original_numeric_bytes": r["original_numeric_bytes"],
341
+ "complete_frame_bytes": r["complete_frame_bytes"],
342
+ "complete_frame_sha256": r["complete_frame_sha256"],
343
+ } for r in sorted(values, key=lambda r: str(r["aggregate_id"]))]
344
+ output.append({
345
+ "schema": "compressionbenchmark-corrected-five425-website-row-v1",
346
+ "dataset": pair["dataset_id"], "scope": scope,
347
+ "runtime": pair.get("runtime", f"cpp-native166-corrected-five-{binary[:8]}"),
348
+ "comparison_profile": PROFILE, "family": pair["method"],
349
+ "method": config, "algorithm_variant": f"{config} [{binary[:8]}]",
350
+ "is_best_rate_in_family": True,
351
+ "original_size_bytes": original, "compressed_size_bytes": compressed,
352
+ "point_count": sum(r["row_count"] for r in values),
353
+ "compression_rate": compressed / original,
354
+ "compression_time_ns": None, "decompression_time_ns": None,
355
+ "compression_time_ns_per_point": None,
356
+ "decompression_time_ns_per_point": None,
357
+ "timing_column_count": 0, "timing_aggregation": "unavailable",
358
+ "eligible_dtype_scope": scope,
359
+ "eligible_column_set_sha256": support,
360
+ "data_identity_sha256": hashlib.sha256(canonical(data_identity)).hexdigest(),
361
+ "eligible_column_set_status": "exact_sorted_aggregate_ids_sha256",
362
+ "measurement_status": "corrected_five_source_revalidated_result_dual_cold_archive_bound",
363
+ "timing_profile_status": "timing_not_admitted_public_fields_null",
364
+ "execution_host": pair.get("execution_host", "166.111.68.166"), "binary_sha256": binary,
365
+ "input_cohort": "six-dataset-corrected-five-20261012-v1",
366
+ "profile_version": pair["profile_version"],
367
+ "input_version": "six-numeric-repair-20261012-v1",
368
+ "acceptance_sha256": acceptance_sha,
369
+ "receipt_sha256": pair["receipt_sha256"],
370
+ "result_sha256": pair["result_sha256"],
371
+ "cold_sha256": pair["cold_sha256"],
372
+ "independent_cold_sha256": pair["independent_cold_sha256"],
373
+ "input_binding_sha256": pair.get("input_binding_sha256"),
374
+ })
375
+ return output
376
+
377
+
378
+ def build(args):
379
+ base = args.base.resolve()
380
+ require(sha(args.baseline_receipt) == args.expected_baseline_receipt_sha256,
381
+ "immutable baseline receipt SHA differs")
382
+ baseline = read(args.baseline_receipt)
383
+ require(baseline.get("status") == "passed" and
384
+ baseline.get("revision") == BASE_REVISION and
385
+ baseline.get("file_count") == 32, "immutable v7 baseline not verified")
386
+ files = baseline["files"]
387
+ validate_baseline_paths(files)
388
+ for ref in files:
389
+ p = base / ref["path"]
390
+ require(not p.is_symlink() and p.is_file() and p.stat().st_size == ref["bytes"] and
391
+ sha(p) == ref["sha256"],
392
+ f"baseline file drift: {ref['path']}")
393
+ v7path = base / "build_accepted_completion_v7.py"
394
+ require(sha(v7path) == V7_BUILDER_SHA, "frozen aggregate helper differs")
395
+ spec = importlib.util.spec_from_file_location("corrected425_frozen_v7", v7path)
396
+ module = importlib.util.module_from_spec(spec)
397
+ spec.loader.exec_module(module)
398
+ portable_inputs = [args.portable_manifest, args.portable_records,
399
+ args.acceptance_receipt, args.website_rows]
400
+ portable_before = {str(p): stable_ref(p) for p in portable_inputs}
401
+ manifest, pairs = load_portable(args.portable_manifest, args.portable_records,
402
+ args.expected_manifest_sha256,
403
+ args.expected_acceptance_sha256)
404
+ acceptance = validate_portable_closure(manifest, args.portable_records,
405
+ args.acceptance_receipt, args.website_rows,
406
+ args.expected_acceptance_sha256)
407
+ additions = result_rows(pairs, args.expected_acceptance_sha256)
408
+ require(additions, "no accepted numeric additions")
409
+ with gzip.open(args.website_rows, "rt") as stream:
410
+ source_projection = [json.loads(line) for line in stream if line.strip()]
411
+ projection_key = lambda r: (r["dataset"], r["scope"], r["family"], r["algorithm_variant"])
412
+ source_by_key = {projection_key(r): r for r in source_projection}
413
+ require(len(source_by_key) == len(additions) and
414
+ set(source_by_key) == {projection_key(r) for r in additions},
415
+ "independent and builder numeric projection identities differ")
416
+ for row in additions:
417
+ old = source_by_key[projection_key(row)]
418
+ derived_projection = {k: v for k, v in row.items()
419
+ if k not in {"acceptance_sha256", "input_version"}}
420
+ require(canonical(old) == canonical(derived_projection),
421
+ "builder metrics/support/provenance differ from source-side projection")
422
+ output = args.output.resolve()
423
+ require(not output.exists(), "candidate exists; preserve it and use a new attempt")
424
+ output.mkdir(parents=True)
425
+ for ref in files:
426
+ shutil.copy2(base / ref["path"], output / ref["path"])
427
+ for ref in files:
428
+ require((output / ref["path"]).stat().st_size == ref["bytes"] and
429
+ sha(output / ref["path"]) == ref["sha256"], "baseline copy drift")
430
+ data = read(output / "data.json")
431
+ untouched = hashlib.sha256(canonical(data["dataset_results"])).hexdigest()
432
+ require(not any(r.get("comparison_profile") == PROFILE for r in data["dataset_results"]),
433
+ "corrected-five profile already integrated; refuse duplicate import")
434
+ old_count = len(data["dataset_results"])
435
+ data["dataset_results"].extend(additions)
436
+ require(hashlib.sha256(canonical(data["dataset_results"][:old_count])).hexdigest()
437
+ == untouched, "unaffected native or legacy rows changed")
438
+ module.recompute(data)
439
+ module.update_methods(data, additions)
440
+ profiles = sorted({r.get("comparison_profile", r["runtime"])
441
+ for r in data["dataset_results"]})
442
+ data["benchmark"]["implementation_runtimes"] = profiles
443
+ data["benchmark"]["exact_source_profiles"] = sorted({r["runtime"] for r in data["dataset_results"]})
444
+ data["benchmark"].setdefault("runtime_labels", {})[PROFILE] = (
445
+ "Native C++ · 166 · corrected numeric inputs (5 datasets)")
446
+ data["benchmark"].setdefault("runtime_hosts", {})[PROFILE] = "166"
447
+ summary = {
448
+ "comparison_profile": PROFILE, "dataset_count": 5,
449
+ "dataset_ids": sorted(DATASETS), "active_method_count": 85,
450
+ "conclusion_pair_count": 425,
451
+ "numeric_pair_count": sum(any(r["status"] == "ok" for r in p["result_rows"]) for p in pairs),
452
+ "all_na_pair_count": sum(all(r["status"] == "N/A" for r in p["result_rows"]) for p in pairs),
453
+ "all_unsupported_pair_count": sum(all(r["status"] == "unsupported" for r in p["result_rows"]) for p in pairs),
454
+ "numeric_mixed_terminal_pair_count": sum(
455
+ any(r["status"] == "ok" for r in p["result_rows"]) and
456
+ any(r["status"] != "ok" for r in p["result_rows"]) for p in pairs),
457
+ "special_support_review_pair_count": 8, "fresh114_result_count": 0,
458
+ "fresh114_status": "pending_new_server192_experiment",
459
+ "timing_admitted": False, "input_version": "six-numeric-repair-20261012-v1",
460
+ "old_profiles_retained": True,
461
+ "portable_manifest": {"file": PUBLIC_MANIFEST, "sha256": sha(args.portable_manifest)},
462
+ "portable_records": {"file": PUBLIC_RECORDS, "sha256": sha(args.portable_records)},
463
+ "independent_acceptance_sha256": args.expected_acceptance_sha256,
464
+ }
465
+ require(all(summary[k] == acceptance.get(k) for k in (
466
+ "numeric_pair_count", "all_na_pair_count", "all_unsupported_pair_count",
467
+ "numeric_mixed_terminal_pair_count")),
468
+ "displayed numeric/N/A conclusions differ from independent acceptance")
469
+ coverage = data["coverage"]
470
+ coverage.update(dataset_result_row_count=len(data["dataset_results"]),
471
+ configuration_aggregate_row_count=len(data["configuration_aggregates"]),
472
+ family_best_aggregate_row_count=len(data["family_best_aggregates"]),
473
+ method_family_count=len({r["family"] for r in data["dataset_results"]}),
474
+ method_configuration_count=len({r["algorithm_variant"] for r in data["dataset_results"]}),
475
+ runtime_configuration_count=len({(r.get("comparison_profile",r["runtime"]),r["algorithm_variant"]) for r in data["dataset_results"]}),
476
+ runtime_count=len(profiles), runtimes=profiles,
477
+ timing_unavailable_dataset_result_count=sum(r.get("timing_aggregation")=="unavailable" for r in data["dataset_results"]))
478
+ coverage["corrected_five425"] = summary
479
+ data["source"].setdefault("measurement_runs", []).append({
480
+ "schema": "corrected-five425-site-import-v1", **summary,
481
+ "baseline_revision": BASE_REVISION,
482
+ })
483
+ write(output / "data.json", data)
484
+ shutil.copy2(args.portable_records, output / PUBLIC_RECORDS)
485
+ shutil.copy2(args.portable_manifest, output / PUBLIC_MANIFEST)
486
+ shutil.copy2(args.acceptance_receipt, output / PUBLIC_ACCEPTANCE)
487
+ shutil.copy2(args.website_rows, output / PUBLIC_WEBSITE_ROWS)
488
+ for p in portable_inputs:
489
+ require(stable_ref(p) == portable_before[str(p)], "portable input changed during build")
490
+ require(sha(output / p.name) == portable_before[str(p)]["sha256"],
491
+ "portable evidence copy drift")
492
+ app_path = output / "app.js"
493
+ app = app_path.read_text()
494
+ require(app.count("20261011-native-v6") == 3, "UI payload cache-version anchors differ")
495
+ app = app.replace("20261011-native-v6", VERSION)
496
+ old = " populateDatasetControls();"
497
+ require(app.count(old) == 1, "profile selection UI anchor differs")
498
+ app = app.replace(old, " const requestedProfile=new URLSearchParams(location.search).get('profile');\n"
499
+ " if(runtimes.includes(requestedProfile))$('runtime').value=requestedProfile;\n" + old)
500
+ app_path.write_text(app)
501
+ index_path = output / "index.html"
502
+ index = index_path.read_text()
503
+ require(index.count("<main") == 1, "main page anchor differs")
504
+ at = index.index(">", index.index("<main")) + 1
505
+ notice = (f'\n<section class="snapshot-notice" aria-label="Corrected input results">'
506
+ f'<strong>Corrected numeric inputs · 5 datasets</strong>'
507
+ f'<p>425 algorithm–dataset conclusions: {summary["numeric_pair_count"]} pairs contain numerical results, '
508
+ f'{summary["all_unsupported_pair_count"]} pairs contain only unsupported conclusions; '
509
+ f'{summary["numeric_mixed_terminal_pair_count"]} of the numerical pairs also contain N/A or unsupported column conclusions. '
510
+ f'FreshRetailNet-50K full114 is pending a new run. Earlier input versions remain available as separate profiles. '
511
+ f'Corrected-input timing is not admitted to timing or composite rankings.</p>'
512
+ f'<a href="?profile={PROFILE}#overall">View corrected-input results</a></section>\n')
513
+ index = index[:at] + notice + index[at:]
514
+ index, count = re.subn(r'(app\.js\?v=)[^"\s]+', r'\g<1>' + VERSION, index)
515
+ require(count == 1, "index app cache-version anchor differs")
516
+ index, count = re.subn(r'(style\.css\?v=)[^"\s]+', r'\g<1>' + VERSION, index)
517
+ require(count == 1, "index style cache-version anchor differs")
518
+ index_path.write_text(index)
519
+ style = output / "style.css"
520
+ style.write_text(style.read_text() + '\n.snapshot-notice{margin:0 0 1.5rem;padding:1rem 1.25rem;border:1px solid var(--border,#cbd5e1);border-radius:12px}.snapshot-notice p{margin:.5rem 0;line-height:1.5}\n')
521
+ # Rebuild the compact payload last from this candidate's real full snapshot.
522
+ result = subprocess.run([sys.executable, str(output / "build_ui_payload.py")],
523
+ capture_output=True, text=True, check=True)
524
+ ui = read(output / "ui-data.json")
525
+ require(ui["source_data_sha256"] == sha(output / "data.json") and
526
+ len(ui["compact_records"]) == len(data["dataset_results"]),
527
+ "full/compact hash/count closure differs")
528
+ site_manifest = read(output / "manifest.json")
529
+ site_manifest["counts"] = coverage
530
+ site_manifest["data_sha256"] = sha(output / "data.json")
531
+ site_manifest["corrected_five425"] = summary
532
+ site_manifest["measurement_runs"] = data["source"]["measurement_runs"]
533
+ integrate_operator_component(args, output, site_manifest)
534
+ write(output / "manifest.json", site_manifest)
535
+ integration = {
536
+ "schema": "compressionbenchmark-corrected-five425-integration-v1",
537
+ "status": "passed_not_published", "baseline_revision": BASE_REVISION,
538
+ "scope": summary, "old_dataset_result_count": old_count,
539
+ "new_dataset_result_count": len(additions),
540
+ "unaffected_dataset_results_canonical_sha256": untouched,
541
+ "data_sha256": sha(output / "data.json"),
542
+ "ui_data_sha256": sha(output / "ui-data.json"),
543
+ "manifest_sha256": sha(output / "manifest.json"),
544
+ "builder_sha256": sha(Path(__file__)),
545
+ "portable_manifest_sha256": sha(args.portable_manifest),
546
+ "portable_records_sha256": sha(args.portable_records),
547
+ }
548
+ write(output / PUBLIC_INTEGRATION, integration)
549
+ shutil.copy2(Path(__file__), output / Path(__file__).name)
550
+ subprocess.run(["node", "--check", str(app_path)], check=True, capture_output=True)
551
+ write(output / "qa-corrected425-local.json", {"status": "passed_not_published", **integration})
552
+ print(json.dumps({"status": "passed_not_published", "output": str(output),
553
+ "new_dataset_rows": len(additions)}))
554
+
555
+
556
+ if __name__ == "__main__":
557
+ parser = argparse.ArgumentParser(description=__doc__)
558
+ parser.add_argument("--base", type=Path, required=True)
559
+ parser.add_argument("--baseline-receipt", type=Path, required=True)
560
+ parser.add_argument("--expected-baseline-receipt-sha256", required=True)
561
+ parser.add_argument("--portable-manifest", type=Path, required=True)
562
+ parser.add_argument("--portable-records", type=Path, required=True)
563
+ parser.add_argument("--acceptance-receipt", type=Path, required=True)
564
+ parser.add_argument("--website-rows", type=Path, required=True)
565
+ parser.add_argument("--expected-manifest-sha256", required=True)
566
+ parser.add_argument("--expected-acceptance-sha256", required=True)
567
+ parser.add_argument("--output", type=Path, required=True)
568
+ parser.add_argument("--operator-component", type=Path)
569
+ parser.add_argument("--operator-freeze-sha256")
570
+ parser.add_argument("--operator-review", type=Path)
571
+ parser.add_argument("--operator-review-sha256")
572
+ build(parser.parse_args())
build_gzip_storage_recovery.py ADDED
@@ -0,0 +1,388 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """Build a storage-minimized, lossless derivative of final_combined_v1.
3
+
4
+ Only the two public operator CSV artifacts are repackaged. Their logical CSV
5
+ bytes remain authoritative and are bound by both the original V2 integration
6
+ receipt and this derivative packaging receipt. The Native data/UI/ranking
7
+ payload is copied byte-for-byte.
8
+ """
9
+
10
+ from __future__ import annotations
11
+
12
+ import argparse
13
+ import csv
14
+ import gzip
15
+ import hashlib
16
+ import json
17
+ import os
18
+ import shutil
19
+ from pathlib import Path
20
+ from typing import Any
21
+
22
+
23
+ SOURCE_PLAN_SHA256 = "e3cb04f784e48dc639b11fab872713b09e8c8b972d6278eb760ea6b45958f1e6"
24
+ SOURCE_MANIFEST_SHA256 = "c236d7f305335beb2552fa0f1e57256a7e0e7babdec6c383a790dc3a89e6089a"
25
+ SOURCE_OPERATOR_INTEGRATION_SHA256 = "e119538a094c51f32f0da868aacfc803e5b9b2a661e67162ceeed9a26540dc50"
26
+ SOURCE_NATIVE_INTEGRATION_SHA256 = "925e5349498dfa99ae9577dff0885ead384ab56db7577d1cc26909e9b9684691"
27
+ SOURCE_SUMMARY_SHA256 = "a00f86daadd22121fca5444ee9800f1bdbe6db1805c47290bb2810284e5a6b9e"
28
+ SOURCE_INDEX_SHA256 = "41ac9010fa0887788b476e24a1551b10b4eb3fb4ce4d4023770850af60534ef1"
29
+ UNCHANGED_REQUIRED = {
30
+ "data.json": "b7b542c5731786d0486e89de889f024c7e6f69eacb68a7df67bc00179b07af4c",
31
+ "ui-data.json": "ef5aa05289f609f2f62ceed009ee17247c8b4767bba8f4aa8cd522ce83d3521d",
32
+ "app.js": "efe5b9e89d7b0f75e765360f073f4f5d62889660d9cfc546c0e49813d79f2433",
33
+ "ranking.js": "6e14543b42050ec7ad6a04948e8abd6f3589c477035708f9d01814d05a16c076",
34
+ }
35
+ CSV_SPECS = {
36
+ "full_union": {
37
+ "source": "operator-byte-effect-full-union.csv",
38
+ "target": "operator-byte-effect-full-union.csv.gz",
39
+ "bytes": 172774462,
40
+ "sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2",
41
+ "row_count": 41090,
42
+ "schema": "paper164-operator-byte-effect-full-union-v1",
43
+ },
44
+ "recovered_overlay": {
45
+ "source": "operator-byte-effect-recovered-overlay.csv",
46
+ "target": "operator-byte-effect-recovered-overlay.csv.gz",
47
+ "bytes": 152130791,
48
+ "sha256": "4f6e206ea2b7561e1332d994e563b2fdf69ed7c368b118745fc9560c15c23082",
49
+ "row_count": 970,
50
+ "schema": "paper164-operator970-byte-effect-overlay-v1",
51
+ },
52
+ }
53
+ TIMING_FIELDS = (
54
+ "compression_time_ns",
55
+ "decompression_time_ns",
56
+ "baseline_compression_ns",
57
+ "baseline_decompression_ns",
58
+ "omission_compression_ns",
59
+ "omission_decompression_ns",
60
+ "baseline_compression_ns_samples",
61
+ "baseline_decompression_ns_samples",
62
+ "omission_compression_ns_samples",
63
+ "omission_decompression_ns_samples",
64
+ "baseline_compression_ns_per_byte",
65
+ "baseline_decompression_ns_per_byte",
66
+ "omission_compression_ns_per_byte",
67
+ "omission_decompression_ns_per_byte",
68
+ "baseline_compression_ns_per_point",
69
+ "baseline_decompression_ns_per_point",
70
+ "omission_compression_ns_per_point",
71
+ "omission_decompression_ns_per_point",
72
+ )
73
+ RECEIPT_NAME = "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json"
74
+ PACKAGER_NAME = "build_gzip_storage_recovery.py"
75
+ README_NOTE = """
76
+
77
+ ## Operator evidence storage packaging
78
+
79
+ The 41,090-row operator evidence download is published as
80
+ `operator-byte-effect-full-union.csv.gz`; decompress it with a standard gzip
81
+ reader to recover the original CSV bytes. The manifest and
82
+ `OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json` record both the physical gzip
83
+ SHA-256 and the logical decompressed CSV SHA-256. The unchanged Native V1 and
84
+ Operator V2 receipts bind the source candidate; the gzip packaging receipt
85
+ binds this derived manifest and preserves the accepted row semantics.
86
+ """
87
+
88
+
89
+ def sha256_file(path: Path) -> str:
90
+ digest = hashlib.sha256()
91
+ with path.open("rb") as handle:
92
+ for block in iter(lambda: handle.read(1024 * 1024), b""):
93
+ digest.update(block)
94
+ return digest.hexdigest()
95
+
96
+
97
+ def canonical_json_bytes(value: Any) -> bytes:
98
+ return (json.dumps(value, ensure_ascii=False, indent=2, sort_keys=True) + "\n").encode()
99
+
100
+
101
+ def write_json(path: Path, value: Any) -> None:
102
+ path.write_bytes(canonical_json_bytes(value))
103
+
104
+
105
+ def assert_file(path: Path, *, expected_sha256: str, expected_bytes: int | None = None) -> None:
106
+ if not path.is_file():
107
+ raise RuntimeError(f"required file missing: {path}")
108
+ if expected_bytes is not None and path.stat().st_size != expected_bytes:
109
+ raise RuntimeError(f"byte-size mismatch for {path.name}")
110
+ actual = sha256_file(path)
111
+ if actual != expected_sha256:
112
+ raise RuntimeError(f"SHA-256 mismatch for {path.name}: {actual}")
113
+
114
+
115
+ def inspect_csv(path: Path, expected_rows: int) -> dict[str, Any]:
116
+ csv.field_size_limit(2**31 - 1)
117
+ rows = 0
118
+ statuses: dict[str, int] = {}
119
+ with path.open("r", encoding="utf-8", newline="") as handle:
120
+ reader = csv.DictReader(handle)
121
+ if reader.fieldnames is None:
122
+ raise RuntimeError(f"CSV has no header: {path}")
123
+ missing = sorted(set(TIMING_FIELDS) - set(reader.fieldnames))
124
+ if missing:
125
+ raise RuntimeError(f"CSV missing timing fields: {missing}")
126
+ for row in reader:
127
+ rows += 1
128
+ if any(row[field] not in ("", "null", "None") for field in TIMING_FIELDS):
129
+ raise RuntimeError(f"non-null timing field at logical row {rows}: {path.name}")
130
+ status = row.get("status", "")
131
+ statuses[status] = statuses.get(status, 0) + 1
132
+ if rows != expected_rows:
133
+ raise RuntimeError(f"row-count mismatch for {path.name}: {rows} != {expected_rows}")
134
+ return {"row_count": rows, "status_counts": dict(sorted(statuses.items())), "timing_null_field_count": 18}
135
+
136
+
137
+ def deterministic_gzip(source: Path, target: Path) -> None:
138
+ with source.open("rb") as src, target.open("wb") as raw:
139
+ with gzip.GzipFile(filename="", mode="wb", fileobj=raw, compresslevel=9, mtime=0) as dst:
140
+ shutil.copyfileobj(src, dst, length=1024 * 1024)
141
+
142
+
143
+ def decompressed_sha256(path: Path) -> tuple[str, int]:
144
+ digest = hashlib.sha256()
145
+ total = 0
146
+ with gzip.open(path, "rb") as handle:
147
+ for block in iter(lambda: handle.read(1024 * 1024), b""):
148
+ total += len(block)
149
+ digest.update(block)
150
+ return digest.hexdigest(), total
151
+
152
+
153
+ def packaged_entry(spec: dict[str, Any], target: Path) -> dict[str, Any]:
154
+ logical_sha, logical_bytes = decompressed_sha256(target)
155
+ if logical_sha != spec["sha256"] or logical_bytes != spec["bytes"]:
156
+ raise RuntimeError(f"gzip round-trip mismatch: {target.name}")
157
+ return {
158
+ "file": spec["target"],
159
+ "media_type": "text/csv",
160
+ "content_encoding": "gzip",
161
+ "bytes": target.stat().st_size,
162
+ "sha256": sha256_file(target),
163
+ "row_count": spec["row_count"],
164
+ "schema": spec["schema"],
165
+ "logical_csv": {
166
+ "original_file": spec["source"],
167
+ "bytes": spec["bytes"],
168
+ "sha256": spec["sha256"],
169
+ },
170
+ }
171
+
172
+
173
+ def main() -> None:
174
+ parser = argparse.ArgumentParser()
175
+ parser.add_argument("--source", type=Path, required=True)
176
+ parser.add_argument("--source-plan", type=Path, required=True)
177
+ parser.add_argument("--output", type=Path, required=True)
178
+ args = parser.parse_args()
179
+
180
+ source = args.source.resolve()
181
+ plan_path = args.source_plan.resolve()
182
+ output = args.output.resolve()
183
+ if output.exists() and any(output.iterdir()):
184
+ raise RuntimeError(f"output exists and is not empty: {output}")
185
+ output.mkdir(parents=True, exist_ok=True)
186
+
187
+ assert_file(plan_path, expected_sha256=SOURCE_PLAN_SHA256)
188
+ plan = json.loads(plan_path.read_text())
189
+ entries = plan.get("files")
190
+ if not isinstance(entries, list) or len(entries) != 42:
191
+ raise RuntimeError("source release plan is not the approved 42-file closure")
192
+ planned = {entry["path"]: entry for entry in entries}
193
+ if set(spec["source"] for spec in CSV_SPECS.values()) - set(planned):
194
+ raise RuntimeError("source release plan omits an operator CSV")
195
+
196
+ for relative, entry in sorted(planned.items()):
197
+ source_file = source / relative
198
+ assert_file(source_file, expected_sha256=entry["sha256"], expected_bytes=entry["bytes"])
199
+ if relative not in {spec["source"] for spec in CSV_SPECS.values()}:
200
+ destination = output / relative
201
+ destination.parent.mkdir(parents=True, exist_ok=True)
202
+ shutil.copy2(source_file, destination)
203
+
204
+ packager_path = Path(__file__).resolve()
205
+ packager_sha256 = sha256_file(packager_path)
206
+ shutil.copy2(packager_path, output / PACKAGER_NAME)
207
+
208
+ assert_file(source / "manifest.json", expected_sha256=SOURCE_MANIFEST_SHA256)
209
+ assert_file(source / "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json", expected_sha256=SOURCE_OPERATOR_INTEGRATION_SHA256)
210
+ assert_file(source / "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json", expected_sha256=SOURCE_NATIVE_INTEGRATION_SHA256)
211
+ assert_file(source / "operator-byte-effect-summary.json", expected_sha256=SOURCE_SUMMARY_SHA256)
212
+ assert_file(source / "index.html", expected_sha256=SOURCE_INDEX_SHA256)
213
+ for relative, expected in UNCHANGED_REQUIRED.items():
214
+ assert_file(source / relative, expected_sha256=expected)
215
+
216
+ audits: dict[str, Any] = {}
217
+ packages: dict[str, Any] = {}
218
+ for key, spec in CSV_SPECS.items():
219
+ src = source / spec["source"]
220
+ assert_file(src, expected_sha256=spec["sha256"], expected_bytes=spec["bytes"])
221
+ audits[key] = inspect_csv(src, spec["row_count"])
222
+ target = output / spec["target"]
223
+ deterministic_gzip(src, target)
224
+ packages[key] = packaged_entry(spec, target)
225
+
226
+ summary = json.loads((source / "operator-byte-effect-summary.json").read_text())
227
+ if summary["audit"]["input_row_count"] != 41090 or summary["audit"]["recovered_overlay_row_count"] != 970:
228
+ raise RuntimeError("source operator summary row contract changed")
229
+ if summary["timing"]["field_count"] != 18 or summary["timing"]["status"] != "unavailable":
230
+ raise RuntimeError("source operator summary timing contract changed")
231
+ summary["evidence"] = {
232
+ "full_union": packages["full_union"],
233
+ "recovered_overlay": packages["recovered_overlay"],
234
+ }
235
+ summary["storage_packaging"] = {
236
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1",
237
+ "lossless": True,
238
+ "logical_csv_sha256_preserved": True,
239
+ "receipt_file": RECEIPT_NAME,
240
+ }
241
+ write_json(output / "operator-byte-effect-summary.json", summary)
242
+ new_summary_sha = sha256_file(output / "operator-byte-effect-summary.json")
243
+
244
+ index = (source / "index.html").read_text()
245
+ old_link = 'href="operator-byte-effect-full-union.csv" download'
246
+ new_link = 'href="operator-byte-effect-full-union.csv.gz" download'
247
+ if index.count(old_link) != 1:
248
+ raise RuntimeError("operator evidence download link is not uniquely replaceable")
249
+ (output / "index.html").write_text(index.replace(old_link, new_link))
250
+
251
+ readme_path = output / "README.md"
252
+ readme = readme_path.read_text()
253
+ if "## Operator evidence storage packaging" in readme:
254
+ raise RuntimeError("source README unexpectedly already contains the derived packaging note")
255
+ readme_path.write_text(readme.rstrip() + README_NOTE + "\n")
256
+
257
+ manifest = json.loads((source / "manifest.json").read_text())
258
+ operator = manifest.get("operator_byte_effect")
259
+ if operator is None or operator.get("status") != "accepted":
260
+ raise RuntimeError("source manifest operator section is not accepted")
261
+ operator["full_union"] = packages["full_union"]
262
+ operator["recovered_overlay"] = packages["recovered_overlay"]
263
+ operator["summary"] = {
264
+ "file": "operator-byte-effect-summary.json",
265
+ "bytes": (output / "operator-byte-effect-summary.json").stat().st_size,
266
+ "sha256": new_summary_sha,
267
+ "schema": "compressionbenchmark-operator-byte-effect-summary-v1",
268
+ }
269
+ operator["integration"]["role"] = "source_semantic_integration_before_lossless_storage_repack"
270
+ operator["integration"]["source_manifest_sha256"] = SOURCE_MANIFEST_SHA256
271
+ operator["storage_packaging"] = {
272
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1",
273
+ "status": "passed_not_published",
274
+ "receipt_file": RECEIPT_NAME,
275
+ "receipt_binding": "receipt binds this derived manifest; receipt SHA is frozen externally to avoid a hash cycle",
276
+ }
277
+ manifest["storage_derivation"] = {
278
+ "schema": "compressionbenchmark-lossless-storage-derivation-v1",
279
+ "source_manifest_sha256": SOURCE_MANIFEST_SHA256,
280
+ "source_native_integration": {
281
+ "file": "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json",
282
+ "sha256": SOURCE_NATIVE_INTEGRATION_SHA256,
283
+ "binding": "source candidate manifest only; scientific payload remains byte-identical",
284
+ },
285
+ "source_operator_integration": {
286
+ "file": "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json",
287
+ "sha256": SOURCE_OPERATOR_INTEGRATION_SHA256,
288
+ "binding": "source logical CSV identities and accepted operator semantics",
289
+ },
290
+ "derived_packaging_receipt_file": RECEIPT_NAME,
291
+ "public_packager": {
292
+ "file": PACKAGER_NAME,
293
+ "sha256": packager_sha256,
294
+ },
295
+ "receipt_binding": "derived receipt binds this manifest; its own SHA is frozen by the external publication plan and review",
296
+ }
297
+ write_json(output / "manifest.json", manifest)
298
+ new_manifest_sha = sha256_file(output / "manifest.json")
299
+
300
+ unchanged = {}
301
+ for relative, expected in UNCHANGED_REQUIRED.items():
302
+ actual = sha256_file(output / relative)
303
+ if actual != expected:
304
+ raise RuntimeError(f"required unchanged public payload drifted: {relative}")
305
+ unchanged[relative] = {"bytes": (output / relative).stat().st_size, "sha256": actual}
306
+
307
+ receipt = {
308
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1",
309
+ "status": "passed_not_published",
310
+ "scope": "lossless physical storage repack of two operator CSV artifacts only",
311
+ "builder": {
312
+ "file": PACKAGER_NAME,
313
+ "sha256": packager_sha256,
314
+ "public_copy_sha256": sha256_file(output / PACKAGER_NAME),
315
+ },
316
+ "source_candidate": {
317
+ "release_plan_sha256": SOURCE_PLAN_SHA256,
318
+ "manifest_sha256": SOURCE_MANIFEST_SHA256,
319
+ "operator_integration_file": "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json",
320
+ "operator_integration_sha256": SOURCE_OPERATOR_INTEGRATION_SHA256,
321
+ "native_integration_file": "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json",
322
+ "native_integration_sha256": SOURCE_NATIVE_INTEGRATION_SHA256,
323
+ "operator_summary_sha256": SOURCE_SUMMARY_SHA256,
324
+ },
325
+ "derived_candidate": {
326
+ "manifest_file": "manifest.json",
327
+ "manifest_sha256": new_manifest_sha,
328
+ "operator_summary_file": "operator-byte-effect-summary.json",
329
+ "operator_summary_sha256": new_summary_sha,
330
+ "index_file": "index.html",
331
+ "index_sha256": sha256_file(output / "index.html"),
332
+ },
333
+ "artifacts": packages,
334
+ "csv_audit": audits,
335
+ "invariants": {
336
+ "full_union_row_count": 41090,
337
+ "recovered_overlay_row_count": 970,
338
+ "all_18_timing_fields_null": True,
339
+ "native_scientific_rows_changed": 0,
340
+ "data_ui_ranking_app_byte_identical": True,
341
+ "source_operator_integration_preserved_byte_identical": True,
342
+ "source_native_integration_preserved_byte_identical": True,
343
+ "source_native_receipt_binds_source_manifest_not_derived_manifest": True,
344
+ "original_uncompressed_csv_files_published": False,
345
+ },
346
+ "unchanged_required_public_files": unchanged,
347
+ }
348
+ write_json(output / RECEIPT_NAME, receipt)
349
+
350
+ final_files = sorted(path.relative_to(output).as_posix() for path in output.rglob("*") if path.is_file())
351
+ expected_files = (set(planned) - {spec["source"] for spec in CSV_SPECS.values()}) | {
352
+ spec["target"] for spec in CSV_SPECS.values()
353
+ } | {RECEIPT_NAME}
354
+ expected_files.add(PACKAGER_NAME)
355
+ if set(final_files) != expected_files:
356
+ raise RuntimeError("derived public closure differs from the expected 44-file closure")
357
+
358
+ output_total = sum((output / relative).stat().st_size for relative in final_files)
359
+ result = {
360
+ "status": "passed_not_published",
361
+ "candidate": str(output),
362
+ "public_file_count": len(final_files),
363
+ "public_bytes": output_total,
364
+ "source_public_bytes": sum(entry["bytes"] for entry in entries),
365
+ "storage_bytes_saved": sum(entry["bytes"] for entry in entries) - output_total,
366
+ "manifest_sha256": new_manifest_sha,
367
+ "packaging_receipt_sha256": sha256_file(output / RECEIPT_NAME),
368
+ "public_files": [
369
+ {"path": relative, "bytes": (output / relative).stat().st_size, "sha256": sha256_file(output / relative)}
370
+ for relative in final_files
371
+ ],
372
+ "changed_or_added_files": [
373
+ "index.html",
374
+ "manifest.json",
375
+ "operator-byte-effect-summary.json",
376
+ "operator-byte-effect-full-union.csv.gz",
377
+ "operator-byte-effect-recovered-overlay.csv.gz",
378
+ RECEIPT_NAME,
379
+ "README.md",
380
+ PACKAGER_NAME,
381
+ ],
382
+ "removed_from_public_closure": [spec["source"] for spec in CSV_SPECS.values()],
383
+ }
384
+ print(json.dumps(result, indent=2, sort_keys=True))
385
+
386
+
387
+ if __name__ == "__main__":
388
+ main()
corrected-five425-portable-results.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11
3
+ size 700127
corrected-five425-website-rows.jsonl.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536b91ec5f5914f20ea2567c64982151c86260ad5d38831b826a7360fb011b6a
3
+ size 112109
data.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd2b20a29b87e4703fcc6601ee3bea2f5eb62f7c145291373aded904430bba73
3
- size 132322373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b542c5731786d0486e89de889f024c7e6f69eacb68a7df67bc00179b07af4c
3
+ size 134675991
index.html CHANGED
@@ -6,8 +6,8 @@
6
  <meta name="description" content="THULab time-series compression benchmark: measured compression rates, compression and decompression costs, and dataset coverage.">
7
  <meta name="color-scheme" content="light dark">
8
  <title>THULab | Time Series Compression Benchmark</title>
9
- <link rel="stylesheet" href="style.css?v=20261009-thulab-dataset-badge-v1">
10
- <script src="app.js?v=20261011-native-v6-full-matrix" type="module"></script>
11
  </head>
12
  <body>
13
  <a class="skip-link" href="#content">Skip to results</a>
@@ -16,6 +16,8 @@
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="intro" aria-labelledby="title">
20
  <p class="eyebrow">Time-series systems research</p>
21
  <h1 id="title">Time Series Compression Leaderboard</h1>
@@ -95,6 +97,12 @@
95
  <div><h2>Operators</h2><p class="muted">Thirty operator families organize a 102-entry implementation directory. Directory entries include mechanisms, configurations, compositions, and adapters; they are not 102 distinct atomic operators.</p></div>
96
  <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>
97
  </div>
 
 
 
 
 
 
98
  <div id="operator-summary" class="operator-summary" aria-label="Operator catalog summary"></div>
99
  <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>
100
  <p id="operator-doc-status" class="documentation-status" aria-live="polite">Loading operator documentation…</p>
 
6
  <meta name="description" content="THULab time-series compression benchmark: measured compression rates, compression and decompression costs, and dataset coverage.">
7
  <meta name="color-scheme" content="light dark">
8
  <title>THULab | Time Series Compression Benchmark</title>
9
+ <link rel="stylesheet" href="style.css?v=20261013-corrected-five-v1">
10
+ <script src="app.js?v=20261013-corrected-five-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="Corrected input results"><strong>Corrected numeric inputs · 5 datasets</strong><p>425 algorithm–dataset conclusions: 386 pairs contain numerical results, 39 pairs contain only unsupported conclusions; 40 of the numerical pairs also contain N/A or unsupported column conclusions. FreshRetailNet-50K full114 is pending a new run. Earlier input versions remain available as separate profiles. Corrected-input timing is not admitted to timing or composite rankings.</p><a href="?profile=cpp-native166-corrected-five-20261012-v1#overall">View corrected-input results</a></section>
20
+
21
  <section class="intro" aria-labelledby="title">
22
  <p class="eyebrow">Time-series systems research</p>
23
  <h1 id="title">Time Series Compression Leaderboard</h1>
 
97
  <div><h2>Operators</h2><p class="muted">Thirty operator families organize a 102-entry implementation directory. Directory entries include mechanisms, configurations, compositions, and adapters; they are not 102 distinct atomic operators.</p></div>
98
  <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>
99
  </div>
100
+ <section id="operator-effect-results" class="operator-effect-results" aria-labelledby="operator-effect-title">
101
+ <div class="operator-effect-head"><div><h3 id="operator-effect-title">Verified matched-omission byte effects</h3><p class="muted">Byte-only measurements from the independently accepted full union. 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>
102
+ <p id="operator-effect-status" class="documentation-status" aria-live="polite">Loading verified byte effects…</p>
103
+ <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>
104
+ <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>
105
+ </section>
106
  <div id="operator-summary" class="operator-summary" aria-label="Operator catalog summary"></div>
107
  <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>
108
  <p id="operator-doc-status" class="documentation-status" aria-live="polite">Loading operator documentation…</p>
manifest.json CHANGED
@@ -1,9 +1,73 @@
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "counts": {
3
  "catalog_dataset_count": 164,
4
- "configuration_aggregate_row_count": 4966,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "dataset_count": 164,
6
- "dataset_result_row_count": 91701,
7
  "excluded_datasets": [
8
  "Arade",
9
  "app_flow",
@@ -15,9 +79,9 @@
15
  "tiktok_trending_hashtags_music",
16
  "youtube_trending_2019_2020"
17
  ],
18
- "family_best_aggregate_row_count": 1687,
19
  "measured_dataset_count": 164,
20
- "method_configuration_count": 411,
21
  "method_family_count": 104,
22
  "missing_measurement_policy": "Missing report and dataset/scope/runtime/configuration combinations are omitted; the UI must display them as unavailable, never as zero.",
23
  "missing_source_report_count": 0,
@@ -316,10 +380,11 @@
316
  "native86_unresolved_problem_pair_count": 0,
317
  "native86_v9_recovered_pair_count": 154,
318
  "paper_leaderboard_row_count": 0,
319
- "runtime_configuration_count": 1041,
320
- "runtime_count": 11,
321
  "runtimes": [
322
  "cpp",
 
323
  "cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3",
324
  "cpp-native166-main-458a218f",
325
  "cpp-native166-row-support-v4-baseline86-fixed-profiles-20260919-v3",
@@ -336,10 +401,10 @@
336
  "timing_column_mean_dataset_result_count": 25449,
337
  "timing_column_observation_count": 519087,
338
  "timing_dataset_aggregate_result_count": 0,
339
- "timing_unavailable_dataset_result_count": 66252
340
  },
341
  "data_file": "data.json",
342
- "data_sha256": "fd2b20a29b87e4703fcc6601ee3bea2f5eb62f7c145291373aded904430bba73",
343
  "dataset_catalog_sha256": "47869c8078e8c864810d4f961fa5879e120943bb3f371b39f0adc74f3de2ee2d",
344
  "excluded_content": [
345
  "raw datasets",
@@ -573,6 +638,371 @@
573
  "timing_aggregation": "column_mean",
574
  "timing_column_count_per_row": 1,
575
  "validation_status": "passed_byte_for_byte_lossless"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
576
  }
577
  ],
578
  "native86_imports": {
@@ -846,6 +1276,61 @@
846
  "sha256": "f538e84dd2b4fee3c1b0d68408095fc88714eafe3ac0e6a57d6dc674f39e47a0"
847
  }
848
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
849
  "reference_catalog_sha256": "15fc0b3931c87bc7f3012b2cbd72b200fcbae811f159d200568af6fb45a10e88",
850
  "result_csv_files": [
851
  {
@@ -1410,6 +1895,26 @@
1410
  "status": "reviewed_public_catalog"
1411
  }
1412
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1413
  "timing_recalculation": {
1414
  "aggregate_only_dataset_fallback_row_count": 452,
1415
  "dbp_float_audit_path": "analysis_outputs/dbp_float_e2e_20261009/publish_payload/dbp-audit.json",
 
1
  {
2
+ "corrected_five425": {
3
+ "active_method_count": 85,
4
+ "all_na_pair_count": 0,
5
+ "all_unsupported_pair_count": 39,
6
+ "comparison_profile": "cpp-native166-corrected-five-20261012-v1",
7
+ "conclusion_pair_count": 425,
8
+ "dataset_count": 5,
9
+ "dataset_ids": [
10
+ "github_top_projects",
11
+ "magseven_ml_ready_high_frequency_anomaly",
12
+ "traqq_weekly_activity",
13
+ "trending_stocks_yahoo_finance",
14
+ "us_stock_financial_ratios"
15
+ ],
16
+ "fresh114_result_count": 0,
17
+ "fresh114_status": "pending_new_server192_experiment",
18
+ "independent_acceptance_sha256": "f1e282b1a26b89128f71fdcc9edd9aa611141b4d25ad91cefaafd66317b44656",
19
+ "input_version": "six-numeric-repair-20261012-v1",
20
+ "numeric_mixed_terminal_pair_count": 40,
21
+ "numeric_pair_count": 386,
22
+ "old_profiles_retained": true,
23
+ "portable_manifest": {
24
+ "file": "CORRECTED_FIVE425_PORTABLE_MANIFEST.json",
25
+ "sha256": "57718e15382db52fc01feb6de0358ac2d82119e63667e038f3d4c8990f7bfb8f"
26
+ },
27
+ "portable_records": {
28
+ "file": "corrected-five425-portable-results.jsonl.gz",
29
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
30
+ },
31
+ "special_support_review_pair_count": 8,
32
+ "timing_admitted": false
33
+ },
34
  "counts": {
35
  "catalog_dataset_count": 164,
36
+ "configuration_aggregate_row_count": 5197,
37
+ "corrected_five425": {
38
+ "active_method_count": 85,
39
+ "all_na_pair_count": 0,
40
+ "all_unsupported_pair_count": 39,
41
+ "comparison_profile": "cpp-native166-corrected-five-20261012-v1",
42
+ "conclusion_pair_count": 425,
43
+ "dataset_count": 5,
44
+ "dataset_ids": [
45
+ "github_top_projects",
46
+ "magseven_ml_ready_high_frequency_anomaly",
47
+ "traqq_weekly_activity",
48
+ "trending_stocks_yahoo_finance",
49
+ "us_stock_financial_ratios"
50
+ ],
51
+ "fresh114_result_count": 0,
52
+ "fresh114_status": "pending_new_server192_experiment",
53
+ "independent_acceptance_sha256": "f1e282b1a26b89128f71fdcc9edd9aa611141b4d25ad91cefaafd66317b44656",
54
+ "input_version": "six-numeric-repair-20261012-v1",
55
+ "numeric_mixed_terminal_pair_count": 40,
56
+ "numeric_pair_count": 386,
57
+ "old_profiles_retained": true,
58
+ "portable_manifest": {
59
+ "file": "CORRECTED_FIVE425_PORTABLE_MANIFEST.json",
60
+ "sha256": "57718e15382db52fc01feb6de0358ac2d82119e63667e038f3d4c8990f7bfb8f"
61
+ },
62
+ "portable_records": {
63
+ "file": "corrected-five425-portable-results.jsonl.gz",
64
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
65
+ },
66
+ "special_support_review_pair_count": 8,
67
+ "timing_admitted": false
68
+ },
69
  "dataset_count": 164,
70
+ "dataset_result_row_count": 92559,
71
  "excluded_datasets": [
72
  "Arade",
73
  "app_flow",
 
79
  "tiktok_trending_hashtags_music",
80
  "youtube_trending_2019_2020"
81
  ],
82
+ "family_best_aggregate_row_count": 1916,
83
  "measured_dataset_count": 164,
84
+ "method_configuration_count": 476,
85
  "method_family_count": 104,
86
  "missing_measurement_policy": "Missing report and dataset/scope/runtime/configuration combinations are omitted; the UI must display them as unavailable, never as zero.",
87
  "missing_source_report_count": 0,
 
380
  "native86_unresolved_problem_pair_count": 0,
381
  "native86_v9_recovered_pair_count": 154,
382
  "paper_leaderboard_row_count": 0,
383
+ "runtime_configuration_count": 1117,
384
+ "runtime_count": 12,
385
  "runtimes": [
386
  "cpp",
387
+ "cpp-native166-corrected-five-20261012-v1",
388
  "cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3",
389
  "cpp-native166-main-458a218f",
390
  "cpp-native166-row-support-v4-baseline86-fixed-profiles-20260919-v3",
 
401
  "timing_column_mean_dataset_result_count": 25449,
402
  "timing_column_observation_count": 519087,
403
  "timing_dataset_aggregate_result_count": 0,
404
+ "timing_unavailable_dataset_result_count": 67110
405
  },
406
  "data_file": "data.json",
407
+ "data_sha256": "b7b542c5731786d0486e89de889f024c7e6f69eacb68a7df67bc00179b07af4c",
408
  "dataset_catalog_sha256": "47869c8078e8c864810d4f961fa5879e120943bb3f371b39f0adc74f3de2ee2d",
409
  "excluded_content": [
410
  "raw datasets",
 
638
  "timing_aggregation": "column_mean",
639
  "timing_column_count_per_row": 1,
640
  "validation_status": "passed_byte_for_byte_lossless"
641
+ },
642
+ {
643
+ "accepted_repair_overlap_pair_count": 1,
644
+ "accepted_unique_repair_pair_count": 174,
645
+ "comparison_profiles": {
646
+ "cpp-native166-main-458a218f": {
647
+ "dataset_result_count": 25443,
648
+ "exact_source_profiles": [
649
+ "cpp-native166-main-458a218f"
650
+ ],
651
+ "execution_host": "166.111.68.166",
652
+ "pair_count": 11164,
653
+ "timing_admitted": true
654
+ },
655
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3": {
656
+ "dataset_result_count": 383,
657
+ "exact_source_profiles": [
658
+ "cpp-native166-recovery-3452a998",
659
+ "cpp-native166-recovery-39dc8c5d",
660
+ "cpp-native166-recovery-458a218f",
661
+ "cpp-native166-recovery-813812e1",
662
+ "cpp-native166-recovery-82297044",
663
+ "cpp-native166-recovery-9abdc80f"
664
+ ],
665
+ "execution_host": "166.111.68.166",
666
+ "pair_count": 154,
667
+ "timing_admitted": false
668
+ },
669
+ "cpp-native192-first12-baseline86-fixed-profiles-20260919-v3": {
670
+ "dataset_result_count": 29,
671
+ "exact_source_profiles": [
672
+ "cpp-native192-first12-3452a998",
673
+ "cpp-native192-first12-39dc8c5d",
674
+ "cpp-native192-first12-9abdc80f",
675
+ "cpp-native192-first12-bf0a069f"
676
+ ],
677
+ "execution_host": "192.168.99.20",
678
+ "pair_count": 12,
679
+ "timing_admitted": false
680
+ },
681
+ "cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-empty-fixed-20261010-v2": {
682
+ "dataset_result_count": 5,
683
+ "exact_source_profiles": [
684
+ "cpp-native192-lzg-level5-fastfalse-41d0e8fc"
685
+ ],
686
+ "execution_host": "192.168.99.20",
687
+ "pair_count": 2,
688
+ "timing_admitted": false
689
+ },
690
+ "cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-fixed-20261010-v1": {
691
+ "dataset_result_count": 6,
692
+ "exact_source_profiles": [
693
+ "cpp-native192-lzg-level5-fastfalse-00f34de8"
694
+ ],
695
+ "execution_host": "192.168.99.20",
696
+ "pair_count": 2,
697
+ "timing_admitted": false
698
+ },
699
+ "cpp-native192-next5-baseline86-fixed-profiles-20260919-v3": {
700
+ "dataset_result_count": 15,
701
+ "exact_source_profiles": [
702
+ "cpp-native192-next5-39dc8c5d",
703
+ "cpp-native192-next5-9abdc80f",
704
+ "cpp-native192-next5-bf0a069f"
705
+ ],
706
+ "execution_host": "192.168.99.20",
707
+ "pair_count": 5,
708
+ "timing_admitted": false
709
+ }
710
+ },
711
+ "evidence_tier_counts": {
712
+ "active_controller_strict_done_bound": 12475,
713
+ "archived_controller_strict_admission": 1068,
714
+ "self_binding_strict_controller_done_bound": 397
715
+ },
716
+ "host192_independently_verified_pair_count": 21,
717
+ "integrated_at": "2026-10-11T08:53:16.002086+00:00",
718
+ "legacy_timing_policy": {
719
+ "dbp_medium_posts_admitted_rows": 6,
720
+ "dbp_medium_posts_independent_review_sha256": "a200679cddddd96e7bd7488d499dcdeace7f098195e8ead502f70dc49af49043",
721
+ "dbp_medium_posts_receipt_sha256": "10359f6f1153655710f7ce9b59d04e5460babe5606487b7794a47ba874ef4324",
722
+ "diagnostic_rows_published_as_unavailable": 65010
723
+ },
724
+ "main_all_na_pair_count": 2274,
725
+ "main_numeric_pair_count": 11164,
726
+ "main_problem_pair_count": 502,
727
+ "main_timing_proof": {
728
+ "binary_sha256": "458a218fd2e8668dbbac6b70f132db8ffe9de786718db4c28424b6e62b7d5664",
729
+ "path": "native86-main166-timing-proof.json",
730
+ "schema": "paper164-old-main166-timing-provenance-readonly-v1",
731
+ "sha256": "f0f502d348fa20f336911f960efb63da07ddfbe922327acc636554e36d62590c",
732
+ "status": "passed"
733
+ },
734
+ "profiles": {
735
+ "cpp-native166-main-458a218f": {
736
+ "aggregate_count": 290745,
737
+ "binary_sha256": "458a218fd2e8668dbbac6b70f132db8ffe9de786718db4c28424b6e62b7d5664",
738
+ "comparison_profiles": [
739
+ "cpp-native166-main-458a218f"
740
+ ],
741
+ "dataset_result_count": 25443,
742
+ "execution_host": "166.111.68.166",
743
+ "pair_count": 11164,
744
+ "timing_profile_status": "timing_admitted_frozen_source_build_binary_boundary_bound"
745
+ },
746
+ "cpp-native166-recovery-3452a998": {
747
+ "aggregate_count": 2157,
748
+ "binary_sha256": "3452a998adb5d5aba2906397d43637ae06e2fbe9fa5bed34425c283c0a896c03",
749
+ "comparison_profiles": [
750
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
751
+ ],
752
+ "dataset_result_count": 119,
753
+ "execution_host": "166.111.68.166",
754
+ "pair_count": 48,
755
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
756
+ },
757
+ "cpp-native166-recovery-39dc8c5d": {
758
+ "aggregate_count": 1178,
759
+ "binary_sha256": "39dc8c5d9287ddc31aff21474e20c5c65880991a40f6d3f096f870ba22d89bf5",
760
+ "comparison_profiles": [
761
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
762
+ ],
763
+ "dataset_result_count": 141,
764
+ "execution_host": "166.111.68.166",
765
+ "pair_count": 57,
766
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
767
+ },
768
+ "cpp-native166-recovery-458a218f": {
769
+ "aggregate_count": 642,
770
+ "binary_sha256": "458a218fd2e8668dbbac6b70f132db8ffe9de786718db4c28424b6e62b7d5664",
771
+ "comparison_profiles": [
772
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
773
+ ],
774
+ "dataset_result_count": 14,
775
+ "execution_host": "166.111.68.166",
776
+ "pair_count": 6,
777
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
778
+ },
779
+ "cpp-native166-recovery-813812e1": {
780
+ "aggregate_count": 163,
781
+ "binary_sha256": "813812e15013991a809e82fafe710aae77e29c96fa5d2d9101d8323a9cd07e30",
782
+ "comparison_profiles": [
783
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
784
+ ],
785
+ "dataset_result_count": 6,
786
+ "execution_host": "166.111.68.166",
787
+ "pair_count": 2,
788
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
789
+ },
790
+ "cpp-native166-recovery-82297044": {
791
+ "aggregate_count": 39,
792
+ "binary_sha256": "822970447c25f2b5f18e2d750c2a9407b6a23f22cb9f59c40565273599e20fc0",
793
+ "comparison_profiles": [
794
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
795
+ ],
796
+ "dataset_result_count": 2,
797
+ "execution_host": "166.111.68.166",
798
+ "pair_count": 1,
799
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
800
+ },
801
+ "cpp-native166-recovery-9abdc80f": {
802
+ "aggregate_count": 1117,
803
+ "binary_sha256": "9abdc80f9d1d6aeba52a93af9648e37fef964fb57b056b0716a31990e828c48b",
804
+ "comparison_profiles": [
805
+ "cpp-native166-v9-recovery-baseline86-fixed-profiles-20260919-v3"
806
+ ],
807
+ "dataset_result_count": 101,
808
+ "execution_host": "166.111.68.166",
809
+ "pair_count": 40,
810
+ "timing_profile_status": "timing_diagnostic_recovery_campaign_binary_receipt_bound"
811
+ },
812
+ "cpp-native192-first12-3452a998": {
813
+ "aggregate_count": 493,
814
+ "binary_sha256": "3452a998adb5d5aba2906397d43637ae06e2fbe9fa5bed34425c283c0a896c03",
815
+ "comparison_profiles": [
816
+ "cpp-native192-first12-baseline86-fixed-profiles-20260919-v3"
817
+ ],
818
+ "dataset_result_count": 5,
819
+ "execution_host": "192.168.99.20",
820
+ "pair_count": 2,
821
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
822
+ },
823
+ "cpp-native192-first12-39dc8c5d": {
824
+ "aggregate_count": 568,
825
+ "binary_sha256": "39dc8c5d9287ddc31aff21474e20c5c65880991a40f6d3f096f870ba22d89bf5",
826
+ "comparison_profiles": [
827
+ "cpp-native192-first12-baseline86-fixed-profiles-20260919-v3"
828
+ ],
829
+ "dataset_result_count": 10,
830
+ "execution_host": "192.168.99.20",
831
+ "pair_count": 4,
832
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
833
+ },
834
+ "cpp-native192-first12-9abdc80f": {
835
+ "aggregate_count": 148,
836
+ "binary_sha256": "9abdc80f9d1d6aeba52a93af9648e37fef964fb57b056b0716a31990e828c48b",
837
+ "comparison_profiles": [
838
+ "cpp-native192-first12-baseline86-fixed-profiles-20260919-v3"
839
+ ],
840
+ "dataset_result_count": 11,
841
+ "execution_host": "192.168.99.20",
842
+ "pair_count": 5,
843
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
844
+ },
845
+ "cpp-native192-first12-bf0a069f": {
846
+ "aggregate_count": 66,
847
+ "binary_sha256": "bf0a069fc311f2eff2e0cfbb7d389b296c7582b03ed3689004fc397dd837374f",
848
+ "comparison_profiles": [
849
+ "cpp-native192-first12-baseline86-fixed-profiles-20260919-v3"
850
+ ],
851
+ "dataset_result_count": 3,
852
+ "execution_host": "192.168.99.20",
853
+ "pair_count": 1,
854
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
855
+ },
856
+ "cpp-native192-lzg-level5-fastfalse-00f34de8": {
857
+ "aggregate_count": 140,
858
+ "binary_sha256": "00f34de8d145e114d19bc592935fe33b241394692c4a28fd9b8597d809dd3351",
859
+ "comparison_profiles": [
860
+ "cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-fixed-20261010-v1"
861
+ ],
862
+ "dataset_result_count": 6,
863
+ "execution_host": "192.168.99.20",
864
+ "pair_count": 2,
865
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
866
+ },
867
+ "cpp-native192-lzg-level5-fastfalse-41d0e8fc": {
868
+ "aggregate_count": 56,
869
+ "binary_sha256": "41d0e8fc01f94ffa9d2f07796f7fc1bc45a194491535ec927ef627d663f62b08",
870
+ "comparison_profiles": [
871
+ "cpp-native192-lzg-level5-fastfalse-lzg-level5-fast0-ngf1-empty-fixed-20261010-v2"
872
+ ],
873
+ "dataset_result_count": 5,
874
+ "execution_host": "192.168.99.20",
875
+ "pair_count": 2,
876
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
877
+ },
878
+ "cpp-native192-next5-39dc8c5d": {
879
+ "aggregate_count": 118,
880
+ "binary_sha256": "39dc8c5d9287ddc31aff21474e20c5c65880991a40f6d3f096f870ba22d89bf5",
881
+ "comparison_profiles": [
882
+ "cpp-native192-next5-baseline86-fixed-profiles-20260919-v3"
883
+ ],
884
+ "dataset_result_count": 6,
885
+ "execution_host": "192.168.99.20",
886
+ "pair_count": 2,
887
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
888
+ },
889
+ "cpp-native192-next5-9abdc80f": {
890
+ "aggregate_count": 44,
891
+ "binary_sha256": "9abdc80f9d1d6aeba52a93af9648e37fef964fb57b056b0716a31990e828c48b",
892
+ "comparison_profiles": [
893
+ "cpp-native192-next5-baseline86-fixed-profiles-20260919-v3"
894
+ ],
895
+ "dataset_result_count": 3,
896
+ "execution_host": "192.168.99.20",
897
+ "pair_count": 1,
898
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
899
+ },
900
+ "cpp-native192-next5-bf0a069f": {
901
+ "aggregate_count": 118,
902
+ "binary_sha256": "bf0a069fc311f2eff2e0cfbb7d389b296c7582b03ed3689004fc397dd837374f",
903
+ "comparison_profiles": [
904
+ "cpp-native192-next5-baseline86-fixed-profiles-20260919-v3"
905
+ ],
906
+ "dataset_result_count": 6,
907
+ "execution_host": "192.168.99.20",
908
+ "pair_count": 2,
909
+ "timing_profile_status": "timing_diagnostic_external_host_pair_verified_without_source_build_boundary_proof"
910
+ }
911
+ },
912
+ "schema": "site-native86-full-matrix-import-v2",
913
+ "terminal_pair_count": 13940,
914
+ "unresolved_problem_pair_count": 328,
915
+ "v9_recovered_pair_count": 154
916
+ },
917
+ {
918
+ "accepted_completion_pair_count": 328,
919
+ "accepted_unique_repair_pair_count": 502,
920
+ "comparison_profiles": {
921
+ "cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3": {
922
+ "dataset_result_count": 768,
923
+ "exact_source_profiles": [
924
+ "cpp-native166-current-recovery-v3-d528da93"
925
+ ],
926
+ "execution_host": "166.111.68.166",
927
+ "pair_count": 301,
928
+ "timing_admitted": false
929
+ },
930
+ "cpp-native166-row-support-v4-baseline86-fixed-profiles-20260919-v3": {
931
+ "dataset_result_count": 36,
932
+ "exact_source_profiles": [
933
+ "cpp-native166-row-support-v4-d528da93"
934
+ ],
935
+ "execution_host": "166.111.68.166",
936
+ "pair_count": 27,
937
+ "timing_admitted": false
938
+ }
939
+ },
940
+ "execution_host": "166.111.68.166",
941
+ "independent_acceptance_sha256": "801b1f024ccf2adf08f5b948038c9c443f5e6de059190efb7c3a870c0c57ef77",
942
+ "integrated_at": "2026-10-11T13:26:58.196444+00:00",
943
+ "portable_manifest_sha256": "0f3334e929beceb683ada70b7df9f38ec6c007491525c586495de5e31c6f6cbe",
944
+ "portable_records_sha256": "fc01b845db5a54b90555ec25dfb0c363bf1abea6bc2d1c8f025d5424df08a714",
945
+ "profiles": {
946
+ "cpp-native166-current-recovery-v3-d528da93": {
947
+ "aggregate_count": 10834,
948
+ "binary_sha256": "d528da93470af747b3ecf6cfd9a9b4c883f07caf74731f03e00320a8b583b8fb",
949
+ "comparison_profiles": [
950
+ "cpp-native166-current-recovery-v3-baseline86-fixed-profiles-20260919-v3"
951
+ ],
952
+ "dataset_result_count": 768,
953
+ "execution_host": "166.111.68.166",
954
+ "pair_count": 301,
955
+ "timing_profile_status": "timing_diagnostic_rate_bytes_accepted_without_separate_timing_admission"
956
+ },
957
+ "cpp-native166-row-support-v4-d528da93": {
958
+ "aggregate_count": 3653,
959
+ "binary_sha256": "d528da93470af747b3ecf6cfd9a9b4c883f07caf74731f03e00320a8b583b8fb",
960
+ "comparison_profiles": [
961
+ "cpp-native166-row-support-v4-baseline86-fixed-profiles-20260919-v3"
962
+ ],
963
+ "dataset_result_count": 36,
964
+ "execution_host": "166.111.68.166",
965
+ "pair_count": 27,
966
+ "timing_profile_status": "timing_diagnostic_rate_bytes_accepted_without_separate_timing_admission"
967
+ }
968
+ },
969
+ "schema": "site-native86-accepted-completion-import-v3",
970
+ "timing_policy": "diagnostic_only_public_ranking_fields_null_until_separate_exact_timing_admission",
971
+ "unresolved_problem_pair_count": 0
972
+ },
973
+ {
974
+ "active_method_count": 85,
975
+ "all_na_pair_count": 0,
976
+ "all_unsupported_pair_count": 39,
977
+ "baseline_revision": "a21e6ea95d9a6467431c4abb3ba07b3e3195702f",
978
+ "comparison_profile": "cpp-native166-corrected-five-20261012-v1",
979
+ "conclusion_pair_count": 425,
980
+ "dataset_count": 5,
981
+ "dataset_ids": [
982
+ "github_top_projects",
983
+ "magseven_ml_ready_high_frequency_anomaly",
984
+ "traqq_weekly_activity",
985
+ "trending_stocks_yahoo_finance",
986
+ "us_stock_financial_ratios"
987
+ ],
988
+ "fresh114_result_count": 0,
989
+ "fresh114_status": "pending_new_server192_experiment",
990
+ "independent_acceptance_sha256": "f1e282b1a26b89128f71fdcc9edd9aa611141b4d25ad91cefaafd66317b44656",
991
+ "input_version": "six-numeric-repair-20261012-v1",
992
+ "numeric_mixed_terminal_pair_count": 40,
993
+ "numeric_pair_count": 386,
994
+ "old_profiles_retained": true,
995
+ "portable_manifest": {
996
+ "file": "CORRECTED_FIVE425_PORTABLE_MANIFEST.json",
997
+ "sha256": "57718e15382db52fc01feb6de0358ac2d82119e63667e038f3d4c8990f7bfb8f"
998
+ },
999
+ "portable_records": {
1000
+ "file": "corrected-five425-portable-results.jsonl.gz",
1001
+ "sha256": "3f9b7febad064f6aa47b0f68402432335c417caa76c12f612f7db0aa7d683c11"
1002
+ },
1003
+ "schema": "corrected-five425-site-import-v1",
1004
+ "special_support_review_pair_count": 8,
1005
+ "timing_admitted": false
1006
  }
1007
  ],
1008
  "native86_imports": {
 
1276
  "sha256": "f538e84dd2b4fee3c1b0d68408095fc88714eafe3ac0e6a57d6dc674f39e47a0"
1277
  }
1278
  },
1279
+ "operator_byte_effect": {
1280
+ "claim_boundary": "matched diagnostic recipes; byte effects only; no timing ranking or universal causal attribution",
1281
+ "full_union": {
1282
+ "bytes": 5999174,
1283
+ "content_encoding": "gzip",
1284
+ "file": "operator-byte-effect-full-union.csv.gz",
1285
+ "logical_csv": {
1286
+ "bytes": 172774462,
1287
+ "original_file": "operator-byte-effect-full-union.csv",
1288
+ "sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2"
1289
+ },
1290
+ "media_type": "text/csv",
1291
+ "row_count": 41090,
1292
+ "schema": "paper164-operator-byte-effect-full-union-v1",
1293
+ "sha256": "c6962b9e57a59b50a2e4fa0dc0db9789541a763ea46f4b0cfb7cafd3b88dd22d"
1294
+ },
1295
+ "input_version_notice": "Recovered Fresh57 operator rows use the prior input cohort; they are not Fresh114 results.",
1296
+ "integration": {
1297
+ "bytes": 2157,
1298
+ "file": "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json",
1299
+ "role": "source_semantic_integration_before_lossless_storage_repack",
1300
+ "schema": "compressionbenchmark-operator-byte-effect-integration-v2",
1301
+ "sha256": "e119538a094c51f32f0da868aacfc803e5b9b2a661e67162ceeed9a26540dc50",
1302
+ "source_manifest_sha256": "c236d7f305335beb2552fa0f1e57256a7e0e7babdec6c383a790dc3a89e6089a"
1303
+ },
1304
+ "recovered_overlay": {
1305
+ "bytes": 3965730,
1306
+ "content_encoding": "gzip",
1307
+ "file": "operator-byte-effect-recovered-overlay.csv.gz",
1308
+ "logical_csv": {
1309
+ "bytes": 152130791,
1310
+ "original_file": "operator-byte-effect-recovered-overlay.csv",
1311
+ "sha256": "4f6e206ea2b7561e1332d994e563b2fdf69ed7c368b118745fc9560c15c23082"
1312
+ },
1313
+ "media_type": "text/csv",
1314
+ "row_count": 970,
1315
+ "schema": "paper164-operator970-byte-effect-overlay-v1",
1316
+ "sha256": "4375b342f7d5eae7061c1016534b5939b4851e2ed162a130439cfac47b826b54"
1317
+ },
1318
+ "schema": "compressionbenchmark-operator-byte-effect-summary-v1",
1319
+ "status": "accepted",
1320
+ "storage_packaging": {
1321
+ "receipt_binding": "receipt binds this derived manifest; receipt SHA is frozen externally to avoid a hash cycle",
1322
+ "receipt_file": "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json",
1323
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1",
1324
+ "status": "passed_not_published"
1325
+ },
1326
+ "summary": {
1327
+ "bytes": 42356,
1328
+ "file": "operator-byte-effect-summary.json",
1329
+ "schema": "compressionbenchmark-operator-byte-effect-summary-v1",
1330
+ "sha256": "f7c790574fe7d5ce4497eee5ed5ee4797cca319255ad0f1fbf775dc665212228"
1331
+ },
1332
+ "timing_admission": "none_all_fields_null_cross_host_timing_forbidden"
1333
+ },
1334
  "reference_catalog_sha256": "15fc0b3931c87bc7f3012b2cbd72b200fcbae811f159d200568af6fb45a10e88",
1335
  "result_csv_files": [
1336
  {
 
1895
  "status": "reviewed_public_catalog"
1896
  }
1897
  ],
1898
+ "storage_derivation": {
1899
+ "derived_packaging_receipt_file": "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json",
1900
+ "public_packager": {
1901
+ "file": "build_gzip_storage_recovery.py",
1902
+ "sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401"
1903
+ },
1904
+ "receipt_binding": "derived receipt binds this manifest; its own SHA is frozen by the external publication plan and review",
1905
+ "schema": "compressionbenchmark-lossless-storage-derivation-v1",
1906
+ "source_manifest_sha256": "c236d7f305335beb2552fa0f1e57256a7e0e7babdec6c383a790dc3a89e6089a",
1907
+ "source_native_integration": {
1908
+ "binding": "source candidate manifest only; scientific payload remains byte-identical",
1909
+ "file": "NATIVE_CORRECTED_FIVE425_INTEGRATION_V1.json",
1910
+ "sha256": "925e5349498dfa99ae9577dff0885ead384ab56db7577d1cc26909e9b9684691"
1911
+ },
1912
+ "source_operator_integration": {
1913
+ "binding": "source logical CSV identities and accepted operator semantics",
1914
+ "file": "OPERATOR970_BYTE_EFFECT_INTEGRATION_V2.json",
1915
+ "sha256": "e119538a094c51f32f0da868aacfc803e5b9b2a661e67162ceeed9a26540dc50"
1916
+ }
1917
+ },
1918
  "timing_recalculation": {
1919
  "aggregate_only_dataset_fallback_row_count": 452,
1920
  "dbp_float_audit_path": "analysis_outputs/dbp_float_e2e_20261009/publish_payload/dbp-audit.json",
operator-byte-effect-full-union.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6962b9e57a59b50a2e4fa0dc0db9789541a763ea46f4b0cfb7cafd3b88dd22d
3
+ size 5999174
operator-byte-effect-recovered-overlay.csv.gz ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4375b342f7d5eae7061c1016534b5939b4851e2ed162a130439cfac47b826b54
3
+ size 3965730
operator-byte-effect-summary.json ADDED
@@ -0,0 +1,1404 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "aggregation": "equal row weight within dataset/operator, then equal dataset weight per operator",
3
+ "audit": {
4
+ "admitted_ok_row_count": 25635,
5
+ "aggregation": "equal row weight within dataset/operator, then equal dataset weight per operator",
6
+ "full_keyset_sha256": "1ba9231528da435bb4fa11e9853fcb32d0499c13089c44d7831d1fd95c3e6d3a",
7
+ "input_row_count": 41090,
8
+ "operator_count": 9,
9
+ "overlay_keyset_sha256": "5ad13cf396cb6fa191bfe4b7812d9c243c81b8b831c5a3bea7c31cf7ea8f0ebd",
10
+ "presentation_order": "operator_id_ascending_no_cross_support_ranking",
11
+ "recovered_overlay_row_count": 970,
12
+ "status_counts": {
13
+ "N/A": 2734,
14
+ "ok": 25635,
15
+ "unsupported": 12721
16
+ }
17
+ },
18
+ "claim_boundary": "matched diagnostic recipes; byte effects only; no timing ranking or universal causal attribution",
19
+ "evidence": {
20
+ "full_union": {
21
+ "bytes": 5999174,
22
+ "content_encoding": "gzip",
23
+ "file": "operator-byte-effect-full-union.csv.gz",
24
+ "logical_csv": {
25
+ "bytes": 172774462,
26
+ "original_file": "operator-byte-effect-full-union.csv",
27
+ "sha256": "0916fffde56b10f56bc94b1e94aa36f1572710dfc03cb5bd0813cbb1301f75f2"
28
+ },
29
+ "media_type": "text/csv",
30
+ "row_count": 41090,
31
+ "schema": "paper164-operator-byte-effect-full-union-v1",
32
+ "sha256": "c6962b9e57a59b50a2e4fa0dc0db9789541a763ea46f4b0cfb7cafd3b88dd22d"
33
+ },
34
+ "recovered_overlay": {
35
+ "bytes": 3965730,
36
+ "content_encoding": "gzip",
37
+ "file": "operator-byte-effect-recovered-overlay.csv.gz",
38
+ "logical_csv": {
39
+ "bytes": 152130791,
40
+ "original_file": "operator-byte-effect-recovered-overlay.csv",
41
+ "sha256": "4f6e206ea2b7561e1332d994e563b2fdf69ed7c368b118745fc9560c15c23082"
42
+ },
43
+ "media_type": "text/csv",
44
+ "row_count": 970,
45
+ "schema": "paper164-operator970-byte-effect-overlay-v1",
46
+ "sha256": "4375b342f7d5eae7061c1016534b5939b4851e2ed162a130439cfac47b826b54"
47
+ }
48
+ },
49
+ "measurement_contract": {
50
+ "baseline_bytes_field": "baseline_column_reconstructable_bytes_excluding_shared_dataset_metadata",
51
+ "baseline_roundtrip_required": true,
52
+ "common_denominator_field": "original_numeric_bytes",
53
+ "lossless_required": true,
54
+ "omission_bytes_field": "omission_column_reconstructable_bytes_excluding_shared_dataset_metadata",
55
+ "omission_roundtrip_required": true,
56
+ "same_denominator_required": true
57
+ },
58
+ "provenance": {
59
+ "accepted_handoff_sha256": "7f769332f4d292ae0ae4743b1785cf6658e72b0394f061c6bac880fd497f241d",
60
+ "accepted_operator_union_sha256": "502f829935a69fca842a3ea17cede18b100d0173f95c0076e6c1c8a8089385c2",
61
+ "partition_support": [
62
+ {
63
+ "accepted_rows": 94,
64
+ "source_server": "compression-166"
65
+ },
66
+ {
67
+ "accepted_rows": 876,
68
+ "source_server": "192.168.99.20"
69
+ }
70
+ ],
71
+ "public_base_commit": "a21e6ea95d9a6467431c4abb3ba07b3e3195702f",
72
+ "strict_acceptance_gate_sha256": "16af8a6eafabf3eb7df40f74589d2aa320f4986018eafec86d1934c6fac979ae"
73
+ },
74
+ "rows": [
75
+ {
76
+ "dataset_count": 105,
77
+ "dataset_ids": [
78
+ "Air-Quality",
79
+ "Bar-Crawl",
80
+ "Bird-migration",
81
+ "Comments",
82
+ "IGlocations2",
83
+ "Metro-Traffic",
84
+ "NYC_Yellow_Taxi_Trip",
85
+ "RealEstate1",
86
+ "RealEstate2",
87
+ "Romance",
88
+ "SpatialEpiBench",
89
+ "Telco",
90
+ "TrainsUK2",
91
+ "Uberlandia",
92
+ "Wins",
93
+ "YaleLanguages",
94
+ "africa_senegal_mauritania_crops_spi",
95
+ "ahr999-dataset",
96
+ "ast_spacemobile_fleet_data",
97
+ "australian_electricity_demand",
98
+ "bitcoin",
99
+ "bitcoin_price_timeseries",
100
+ "car_parts",
101
+ "covid_deaths-monash",
102
+ "crypto_data",
103
+ "deep-space-probes",
104
+ "dmi-aarhus-weather-data",
105
+ "dst-index",
106
+ "eea_pm25_forecasting",
107
+ "electricity_demand",
108
+ "faang_engineered_time_series_features_2013_2025",
109
+ "forex_factory_calendar",
110
+ "fred_md",
111
+ "freshretailnet_50k",
112
+ "freshretailnet_lt",
113
+ "fulus_lyd_rates_2025",
114
+ "geomagnetic_kp_index",
115
+ "github_top_projects",
116
+ "globalstar_fleet_data",
117
+ "gluco_tsfm_benchmark",
118
+ "goes_omni_electron_flux_forecasting",
119
+ "hospital-monash",
120
+ "hourly-stock-data-2023",
121
+ "indian_stock_hourly_2017_2021",
122
+ "jovian_lightning",
123
+ "kaggle_web_traffic_weekly",
124
+ "kdd_cup_2018",
125
+ "knowable",
126
+ "kraken-trading-data",
127
+ "kuiper_fleet_data",
128
+ "meteoblue",
129
+ "multi_model_trading_data",
130
+ "nasa_maven_kp_insitu",
131
+ "niederschlag_station_4091_bavaria_germany",
132
+ "nifty50_market_regime",
133
+ "nn5_daily",
134
+ "nn5_weekly",
135
+ "oikolab_weather",
136
+ "omie_blockchain_study",
137
+ "ooni_censorship_historical",
138
+ "orbital_chaos_nasa_ssc",
139
+ "pedestrian_counts",
140
+ "phenology_normal_hawaii",
141
+ "polymarket_crypto_5m_15m",
142
+ "quitobench",
143
+ "rating",
144
+ "reg_forecasting_v2",
145
+ "rideshare",
146
+ "salesforecastingwomartstore",
147
+ "saugeenday-monash",
148
+ "sleep_score_fitbit",
149
+ "solar_10_minutes",
150
+ "solar_4_seconds",
151
+ "solar_weekly",
152
+ "solusdt_enhanced_180",
153
+ "spx",
154
+ "stock_dataset",
155
+ "substorm_onsets",
156
+ "sunspot",
157
+ "timeseries-1m-QQQ-10y",
158
+ "timeseries-finance-ETF",
159
+ "timeseries_1mn_sp500",
160
+ "timeseries_1mn_stocks",
161
+ "timeseries_finance_etf_missing",
162
+ "tourism_monthly",
163
+ "tourism_monthly-zaai-ai",
164
+ "tourism_quarterly",
165
+ "tourism_residuals",
166
+ "tourism_yearly",
167
+ "traffic_hourly",
168
+ "traffic_weekly",
169
+ "traqq_weekly_activity",
170
+ "trending_stocks_yahoo_finance",
171
+ "uk_electricity_generation_mix_2019_2026",
172
+ "us_births-monash",
173
+ "us_stock_financial_ratios",
174
+ "vehicle_trips",
175
+ "weather_data_NC",
176
+ "weather_data_bavaria",
177
+ "wids2023_competition_weather_forecasting",
178
+ "wind_4_seconds",
179
+ "wordle_mcm_dataset",
180
+ "xauusd",
181
+ "xauusd_1m",
182
+ "zillow_viewer"
183
+ ],
184
+ "mean_baseline_to_original_ratio": 11.915614084805055,
185
+ "mean_byte_change_percent": -22.307198264409212,
186
+ "mean_omission_to_baseline_ratio": 0.7769280173559079,
187
+ "mean_omission_to_original_ratio": 6.610665764582475,
188
+ "operator": "dictionary",
189
+ "row_count": 1895
190
+ },
191
+ {
192
+ "dataset_count": 160,
193
+ "dataset_ids": [
194
+ "Air-Quality",
195
+ "Bar-Crawl",
196
+ "Bird-migration",
197
+ "Comments",
198
+ "ETDataset-ett",
199
+ "IGlocations2",
200
+ "Metro-Traffic",
201
+ "NYC_Yellow_Taxi_Trip",
202
+ "RealEstate1",
203
+ "RealEstate2",
204
+ "Romance",
205
+ "SpatialEpiBench",
206
+ "Telco",
207
+ "TrainsUK2",
208
+ "Uberlandia",
209
+ "Wins",
210
+ "YaleLanguages",
211
+ "africa_senegal_mauritania_crops_spi",
212
+ "ahr999-dataset",
213
+ "ast_spacemobile_fleet_data",
214
+ "australia_solar",
215
+ "australian_electricity_demand",
216
+ "auto_production_sf",
217
+ "azure2019_u",
218
+ "bitcoin",
219
+ "bitcoin_price_timeseries",
220
+ "car_parts",
221
+ "coastal_t_s",
222
+ "commodity_import",
223
+ "commodity_production",
224
+ "covid_deaths-monash",
225
+ "cphl",
226
+ "crypto",
227
+ "crypto_data",
228
+ "current_velocity",
229
+ "deep-space-probes",
230
+ "dmi-aarhus-weather-data",
231
+ "dst-index",
232
+ "ecdc_covid",
233
+ "eea_pm25_forecasting",
234
+ "electricity_demand",
235
+ "electricity_load_2011_2014",
236
+ "electricity_production",
237
+ "enedis-with-holidays",
238
+ "epf_electricity_price",
239
+ "eweld_load",
240
+ "exchange_rate",
241
+ "faang_engineered_time_series_features_2013_2025",
242
+ "finland_traffic",
243
+ "forex_factory_calendar",
244
+ "fred_md",
245
+ "freshretailnet_50k",
246
+ "freshretailnet_lt",
247
+ "fulus_lyd_rates_2025",
248
+ "geomagnetic_kp_index",
249
+ "github_top_projects",
250
+ "global_influenza",
251
+ "global_price",
252
+ "globalstar_fleet_data",
253
+ "gluco_tsfm_benchmark",
254
+ "goes_omni_electron_flux_forecasting",
255
+ "greatplains_multisource_2000_2024",
256
+ "hospital-monash",
257
+ "hourly-stock-data-2023",
258
+ "hourly_electricity_demand_brazil",
259
+ "housing_inventory",
260
+ "indian_stock_hourly_2017_2021",
261
+ "job_claims",
262
+ "jolts",
263
+ "jovian_lightning",
264
+ "kaggle_web_traffic",
265
+ "kaggle_web_traffic_weekly",
266
+ "kdd_cup_2018",
267
+ "knowable",
268
+ "kraken-trading-data",
269
+ "kuiper_fleet_data",
270
+ "london_smart_meters",
271
+ "macroecon",
272
+ "magseven_ml_ready_high_frequency_anomaly",
273
+ "meteoblue",
274
+ "metropt_3",
275
+ "multi_model_trading_data",
276
+ "nasa_maven_kp_insitu",
277
+ "national_illness",
278
+ "ne_china_wind",
279
+ "niederschlag_station_4091_bavaria_germany",
280
+ "nifty50_market_regime",
281
+ "nn5_daily",
282
+ "nn5_weekly",
283
+ "oikolab_weather",
284
+ "oil_price",
285
+ "omie_blockchain_study",
286
+ "online_retail_2_uci",
287
+ "ooni_censorship_historical",
288
+ "openelectricity_nem",
289
+ "orbital_chaos_nasa_ssc",
290
+ "pedestrian_counts",
291
+ "phenology_normal_hawaii",
292
+ "polymarket_crypto_5m_15m",
293
+ "port_activity",
294
+ "quitobench",
295
+ "rating",
296
+ "reg_forecasting_v2",
297
+ "rideshare",
298
+ "salesforecastingwomartstore",
299
+ "saugeenday-monash",
300
+ "scaphandre_cpu_usage",
301
+ "sg_carpark",
302
+ "sg_pm25",
303
+ "sg_weather",
304
+ "sleep_score_fitbit",
305
+ "solar_10_minutes",
306
+ "solar_4_seconds",
307
+ "solar_weekly",
308
+ "solusdt_enhanced_180",
309
+ "spx",
310
+ "stock_dataset",
311
+ "substorm_onsets",
312
+ "sunspot",
313
+ "telangana_weather",
314
+ "temperature_rain",
315
+ "timeseries-1m-QQQ-10y",
316
+ "timeseries-finance-ETF",
317
+ "timeseries_1mn_sp500",
318
+ "timeseries_1mn_stocks",
319
+ "timeseries_finance_etf_missing",
320
+ "tourism_monthly",
321
+ "tourism_monthly-zaai-ai",
322
+ "tourism_quarterly",
323
+ "tourism_residuals",
324
+ "tourism_yearly",
325
+ "traffic",
326
+ "traffic_hourly",
327
+ "traffic_weekly",
328
+ "traqq_weekly_activity",
329
+ "trending_stocks_yahoo_finance",
330
+ "trxusdt_spot_1m_05_2021_to_03_2026",
331
+ "uk_electricity_generation_mix_2019_2026",
332
+ "uncertainty_1m",
333
+ "us_births-monash",
334
+ "us_labor",
335
+ "us_stock_financial_ratios",
336
+ "us_term_structure",
337
+ "vehicle_sales",
338
+ "vehicle_supply",
339
+ "vehicle_trips",
340
+ "water_quality_darwin",
341
+ "weather_data_NC",
342
+ "weather_data_bavaria",
343
+ "wids2023_competition_weather_forecasting",
344
+ "wind_4_seconds",
345
+ "wind_farms_minutely",
346
+ "wordle_mcm_dataset",
347
+ "wui_global",
348
+ "xauusd",
349
+ "xauusd_1m",
350
+ "xinyi_public_gym",
351
+ "xrpusdt_spot_1m_05_2021_to_03_2026",
352
+ "yongchun_public_gym",
353
+ "zillow_viewer"
354
+ ],
355
+ "mean_baseline_to_original_ratio": 12.816043454476262,
356
+ "mean_byte_change_percent": 51.659185467012534,
357
+ "mean_omission_to_baseline_ratio": 1.5165918546701254,
358
+ "mean_omission_to_original_ratio": 3.5127479764942295,
359
+ "operator": "entropy_fse",
360
+ "row_count": 3611
361
+ },
362
+ {
363
+ "dataset_count": 160,
364
+ "dataset_ids": [
365
+ "Air-Quality",
366
+ "Bar-Crawl",
367
+ "Bird-migration",
368
+ "Comments",
369
+ "ETDataset-ett",
370
+ "IGlocations2",
371
+ "Metro-Traffic",
372
+ "NYC_Yellow_Taxi_Trip",
373
+ "RealEstate1",
374
+ "RealEstate2",
375
+ "Romance",
376
+ "SpatialEpiBench",
377
+ "Telco",
378
+ "TrainsUK2",
379
+ "Uberlandia",
380
+ "Wins",
381
+ "YaleLanguages",
382
+ "africa_senegal_mauritania_crops_spi",
383
+ "ahr999-dataset",
384
+ "ast_spacemobile_fleet_data",
385
+ "australia_solar",
386
+ "australian_electricity_demand",
387
+ "auto_production_sf",
388
+ "azure2019_u",
389
+ "bitcoin",
390
+ "bitcoin_price_timeseries",
391
+ "car_parts",
392
+ "coastal_t_s",
393
+ "commodity_import",
394
+ "commodity_production",
395
+ "covid_deaths-monash",
396
+ "cphl",
397
+ "crypto",
398
+ "crypto_data",
399
+ "current_velocity",
400
+ "deep-space-probes",
401
+ "dmi-aarhus-weather-data",
402
+ "dst-index",
403
+ "ecdc_covid",
404
+ "eea_pm25_forecasting",
405
+ "electricity_demand",
406
+ "electricity_load_2011_2014",
407
+ "electricity_production",
408
+ "enedis-with-holidays",
409
+ "epf_electricity_price",
410
+ "eweld_load",
411
+ "exchange_rate",
412
+ "faang_engineered_time_series_features_2013_2025",
413
+ "finland_traffic",
414
+ "forex_factory_calendar",
415
+ "fred_md",
416
+ "freshretailnet_50k",
417
+ "freshretailnet_lt",
418
+ "fulus_lyd_rates_2025",
419
+ "geomagnetic_kp_index",
420
+ "github_top_projects",
421
+ "global_influenza",
422
+ "global_price",
423
+ "globalstar_fleet_data",
424
+ "gluco_tsfm_benchmark",
425
+ "goes_omni_electron_flux_forecasting",
426
+ "greatplains_multisource_2000_2024",
427
+ "hospital-monash",
428
+ "hourly-stock-data-2023",
429
+ "hourly_electricity_demand_brazil",
430
+ "housing_inventory",
431
+ "indian_stock_hourly_2017_2021",
432
+ "job_claims",
433
+ "jolts",
434
+ "jovian_lightning",
435
+ "kaggle_web_traffic",
436
+ "kaggle_web_traffic_weekly",
437
+ "kdd_cup_2018",
438
+ "knowable",
439
+ "kraken-trading-data",
440
+ "kuiper_fleet_data",
441
+ "london_smart_meters",
442
+ "macroecon",
443
+ "magseven_ml_ready_high_frequency_anomaly",
444
+ "meteoblue",
445
+ "metropt_3",
446
+ "multi_model_trading_data",
447
+ "nasa_maven_kp_insitu",
448
+ "national_illness",
449
+ "ne_china_wind",
450
+ "niederschlag_station_4091_bavaria_germany",
451
+ "nifty50_market_regime",
452
+ "nn5_daily",
453
+ "nn5_weekly",
454
+ "oikolab_weather",
455
+ "oil_price",
456
+ "omie_blockchain_study",
457
+ "online_retail_2_uci",
458
+ "ooni_censorship_historical",
459
+ "openelectricity_nem",
460
+ "orbital_chaos_nasa_ssc",
461
+ "pedestrian_counts",
462
+ "phenology_normal_hawaii",
463
+ "polymarket_crypto_5m_15m",
464
+ "port_activity",
465
+ "quitobench",
466
+ "rating",
467
+ "reg_forecasting_v2",
468
+ "rideshare",
469
+ "salesforecastingwomartstore",
470
+ "saugeenday-monash",
471
+ "scaphandre_cpu_usage",
472
+ "sg_carpark",
473
+ "sg_pm25",
474
+ "sg_weather",
475
+ "sleep_score_fitbit",
476
+ "solar_10_minutes",
477
+ "solar_4_seconds",
478
+ "solar_weekly",
479
+ "solusdt_enhanced_180",
480
+ "spx",
481
+ "stock_dataset",
482
+ "substorm_onsets",
483
+ "sunspot",
484
+ "telangana_weather",
485
+ "temperature_rain",
486
+ "timeseries-1m-QQQ-10y",
487
+ "timeseries-finance-ETF",
488
+ "timeseries_1mn_sp500",
489
+ "timeseries_1mn_stocks",
490
+ "timeseries_finance_etf_missing",
491
+ "tourism_monthly",
492
+ "tourism_monthly-zaai-ai",
493
+ "tourism_quarterly",
494
+ "tourism_residuals",
495
+ "tourism_yearly",
496
+ "traffic",
497
+ "traffic_hourly",
498
+ "traffic_weekly",
499
+ "traqq_weekly_activity",
500
+ "trending_stocks_yahoo_finance",
501
+ "trxusdt_spot_1m_05_2021_to_03_2026",
502
+ "uk_electricity_generation_mix_2019_2026",
503
+ "uncertainty_1m",
504
+ "us_births-monash",
505
+ "us_labor",
506
+ "us_stock_financial_ratios",
507
+ "us_term_structure",
508
+ "vehicle_sales",
509
+ "vehicle_supply",
510
+ "vehicle_trips",
511
+ "water_quality_darwin",
512
+ "weather_data_NC",
513
+ "weather_data_bavaria",
514
+ "wids2023_competition_weather_forecasting",
515
+ "wind_4_seconds",
516
+ "wind_farms_minutely",
517
+ "wordle_mcm_dataset",
518
+ "wui_global",
519
+ "xauusd",
520
+ "xauusd_1m",
521
+ "xinyi_public_gym",
522
+ "xrpusdt_spot_1m_05_2021_to_03_2026",
523
+ "yongchun_public_gym",
524
+ "zillow_viewer"
525
+ ],
526
+ "mean_baseline_to_original_ratio": 18.45363936534965,
527
+ "mean_byte_change_percent": 19.416725032550232,
528
+ "mean_omission_to_baseline_ratio": 1.1941672503255023,
529
+ "mean_omission_to_original_ratio": 3.5127479764942295,
530
+ "operator": "entropy_huffman",
531
+ "row_count": 3611
532
+ },
533
+ {
534
+ "dataset_count": 160,
535
+ "dataset_ids": [
536
+ "Air-Quality",
537
+ "Bar-Crawl",
538
+ "Bird-migration",
539
+ "Comments",
540
+ "ETDataset-ett",
541
+ "IGlocations2",
542
+ "Metro-Traffic",
543
+ "NYC_Yellow_Taxi_Trip",
544
+ "RealEstate1",
545
+ "RealEstate2",
546
+ "Romance",
547
+ "SpatialEpiBench",
548
+ "Telco",
549
+ "TrainsUK2",
550
+ "Uberlandia",
551
+ "Wins",
552
+ "YaleLanguages",
553
+ "africa_senegal_mauritania_crops_spi",
554
+ "ahr999-dataset",
555
+ "ast_spacemobile_fleet_data",
556
+ "australia_solar",
557
+ "australian_electricity_demand",
558
+ "auto_production_sf",
559
+ "azure2019_u",
560
+ "bitcoin",
561
+ "bitcoin_price_timeseries",
562
+ "car_parts",
563
+ "coastal_t_s",
564
+ "commodity_import",
565
+ "commodity_production",
566
+ "covid_deaths-monash",
567
+ "cphl",
568
+ "crypto",
569
+ "crypto_data",
570
+ "current_velocity",
571
+ "deep-space-probes",
572
+ "dmi-aarhus-weather-data",
573
+ "dst-index",
574
+ "ecdc_covid",
575
+ "eea_pm25_forecasting",
576
+ "electricity_demand",
577
+ "electricity_load_2011_2014",
578
+ "electricity_production",
579
+ "enedis-with-holidays",
580
+ "epf_electricity_price",
581
+ "eweld_load",
582
+ "exchange_rate",
583
+ "faang_engineered_time_series_features_2013_2025",
584
+ "finland_traffic",
585
+ "forex_factory_calendar",
586
+ "fred_md",
587
+ "freshretailnet_50k",
588
+ "freshretailnet_lt",
589
+ "fulus_lyd_rates_2025",
590
+ "geomagnetic_kp_index",
591
+ "github_top_projects",
592
+ "global_influenza",
593
+ "global_price",
594
+ "globalstar_fleet_data",
595
+ "gluco_tsfm_benchmark",
596
+ "goes_omni_electron_flux_forecasting",
597
+ "greatplains_multisource_2000_2024",
598
+ "hospital-monash",
599
+ "hourly-stock-data-2023",
600
+ "hourly_electricity_demand_brazil",
601
+ "housing_inventory",
602
+ "indian_stock_hourly_2017_2021",
603
+ "job_claims",
604
+ "jolts",
605
+ "jovian_lightning",
606
+ "kaggle_web_traffic",
607
+ "kaggle_web_traffic_weekly",
608
+ "kdd_cup_2018",
609
+ "knowable",
610
+ "kraken-trading-data",
611
+ "kuiper_fleet_data",
612
+ "london_smart_meters",
613
+ "macroecon",
614
+ "magseven_ml_ready_high_frequency_anomaly",
615
+ "meteoblue",
616
+ "metropt_3",
617
+ "multi_model_trading_data",
618
+ "nasa_maven_kp_insitu",
619
+ "national_illness",
620
+ "ne_china_wind",
621
+ "niederschlag_station_4091_bavaria_germany",
622
+ "nifty50_market_regime",
623
+ "nn5_daily",
624
+ "nn5_weekly",
625
+ "oikolab_weather",
626
+ "oil_price",
627
+ "omie_blockchain_study",
628
+ "online_retail_2_uci",
629
+ "ooni_censorship_historical",
630
+ "openelectricity_nem",
631
+ "orbital_chaos_nasa_ssc",
632
+ "pedestrian_counts",
633
+ "phenology_normal_hawaii",
634
+ "polymarket_crypto_5m_15m",
635
+ "port_activity",
636
+ "quitobench",
637
+ "rating",
638
+ "reg_forecasting_v2",
639
+ "rideshare",
640
+ "salesforecastingwomartstore",
641
+ "saugeenday-monash",
642
+ "scaphandre_cpu_usage",
643
+ "sg_carpark",
644
+ "sg_pm25",
645
+ "sg_weather",
646
+ "sleep_score_fitbit",
647
+ "solar_10_minutes",
648
+ "solar_4_seconds",
649
+ "solar_weekly",
650
+ "solusdt_enhanced_180",
651
+ "spx",
652
+ "stock_dataset",
653
+ "substorm_onsets",
654
+ "sunspot",
655
+ "telangana_weather",
656
+ "temperature_rain",
657
+ "timeseries-1m-QQQ-10y",
658
+ "timeseries-finance-ETF",
659
+ "timeseries_1mn_sp500",
660
+ "timeseries_1mn_stocks",
661
+ "timeseries_finance_etf_missing",
662
+ "tourism_monthly",
663
+ "tourism_monthly-zaai-ai",
664
+ "tourism_quarterly",
665
+ "tourism_residuals",
666
+ "tourism_yearly",
667
+ "traffic",
668
+ "traffic_hourly",
669
+ "traffic_weekly",
670
+ "traqq_weekly_activity",
671
+ "trending_stocks_yahoo_finance",
672
+ "trxusdt_spot_1m_05_2021_to_03_2026",
673
+ "uk_electricity_generation_mix_2019_2026",
674
+ "uncertainty_1m",
675
+ "us_births-monash",
676
+ "us_labor",
677
+ "us_stock_financial_ratios",
678
+ "us_term_structure",
679
+ "vehicle_sales",
680
+ "vehicle_supply",
681
+ "vehicle_trips",
682
+ "water_quality_darwin",
683
+ "weather_data_NC",
684
+ "weather_data_bavaria",
685
+ "wids2023_competition_weather_forecasting",
686
+ "wind_4_seconds",
687
+ "wind_farms_minutely",
688
+ "wordle_mcm_dataset",
689
+ "wui_global",
690
+ "xauusd",
691
+ "xauusd_1m",
692
+ "xinyi_public_gym",
693
+ "xrpusdt_spot_1m_05_2021_to_03_2026",
694
+ "yongchun_public_gym",
695
+ "zillow_viewer"
696
+ ],
697
+ "mean_baseline_to_original_ratio": 17.622831462975775,
698
+ "mean_byte_change_percent": 38.548345667981955,
699
+ "mean_omission_to_baseline_ratio": 1.3854834566798195,
700
+ "mean_omission_to_original_ratio": 3.7447667780616194,
701
+ "operator": "entropy_range",
702
+ "row_count": 5015
703
+ },
704
+ {
705
+ "dataset_count": 105,
706
+ "dataset_ids": [
707
+ "Air-Quality",
708
+ "Bar-Crawl",
709
+ "Bird-migration",
710
+ "Comments",
711
+ "IGlocations2",
712
+ "Metro-Traffic",
713
+ "NYC_Yellow_Taxi_Trip",
714
+ "RealEstate1",
715
+ "RealEstate2",
716
+ "Romance",
717
+ "SpatialEpiBench",
718
+ "Telco",
719
+ "TrainsUK2",
720
+ "Uberlandia",
721
+ "Wins",
722
+ "YaleLanguages",
723
+ "africa_senegal_mauritania_crops_spi",
724
+ "ahr999-dataset",
725
+ "ast_spacemobile_fleet_data",
726
+ "australian_electricity_demand",
727
+ "bitcoin",
728
+ "bitcoin_price_timeseries",
729
+ "car_parts",
730
+ "covid_deaths-monash",
731
+ "crypto_data",
732
+ "deep-space-probes",
733
+ "dmi-aarhus-weather-data",
734
+ "dst-index",
735
+ "eea_pm25_forecasting",
736
+ "electricity_demand",
737
+ "faang_engineered_time_series_features_2013_2025",
738
+ "forex_factory_calendar",
739
+ "fred_md",
740
+ "freshretailnet_50k",
741
+ "freshretailnet_lt",
742
+ "fulus_lyd_rates_2025",
743
+ "geomagnetic_kp_index",
744
+ "github_top_projects",
745
+ "globalstar_fleet_data",
746
+ "gluco_tsfm_benchmark",
747
+ "goes_omni_electron_flux_forecasting",
748
+ "hospital-monash",
749
+ "hourly-stock-data-2023",
750
+ "indian_stock_hourly_2017_2021",
751
+ "jovian_lightning",
752
+ "kaggle_web_traffic_weekly",
753
+ "kdd_cup_2018",
754
+ "knowable",
755
+ "kraken-trading-data",
756
+ "kuiper_fleet_data",
757
+ "meteoblue",
758
+ "multi_model_trading_data",
759
+ "nasa_maven_kp_insitu",
760
+ "niederschlag_station_4091_bavaria_germany",
761
+ "nifty50_market_regime",
762
+ "nn5_daily",
763
+ "nn5_weekly",
764
+ "oikolab_weather",
765
+ "omie_blockchain_study",
766
+ "ooni_censorship_historical",
767
+ "orbital_chaos_nasa_ssc",
768
+ "pedestrian_counts",
769
+ "phenology_normal_hawaii",
770
+ "polymarket_crypto_5m_15m",
771
+ "quitobench",
772
+ "rating",
773
+ "reg_forecasting_v2",
774
+ "rideshare",
775
+ "salesforecastingwomartstore",
776
+ "saugeenday-monash",
777
+ "sleep_score_fitbit",
778
+ "solar_10_minutes",
779
+ "solar_4_seconds",
780
+ "solar_weekly",
781
+ "solusdt_enhanced_180",
782
+ "spx",
783
+ "stock_dataset",
784
+ "substorm_onsets",
785
+ "sunspot",
786
+ "timeseries-1m-QQQ-10y",
787
+ "timeseries-finance-ETF",
788
+ "timeseries_1mn_sp500",
789
+ "timeseries_1mn_stocks",
790
+ "timeseries_finance_etf_missing",
791
+ "tourism_monthly",
792
+ "tourism_monthly-zaai-ai",
793
+ "tourism_quarterly",
794
+ "tourism_residuals",
795
+ "tourism_yearly",
796
+ "traffic_hourly",
797
+ "traffic_weekly",
798
+ "traqq_weekly_activity",
799
+ "trending_stocks_yahoo_finance",
800
+ "uk_electricity_generation_mix_2019_2026",
801
+ "us_births-monash",
802
+ "us_stock_financial_ratios",
803
+ "vehicle_trips",
804
+ "weather_data_NC",
805
+ "weather_data_bavaria",
806
+ "wids2023_competition_weather_forecasting",
807
+ "wind_4_seconds",
808
+ "wordle_mcm_dataset",
809
+ "xauusd",
810
+ "xauusd_1m",
811
+ "zillow_viewer"
812
+ ],
813
+ "mean_baseline_to_original_ratio": 9.947525259971032,
814
+ "mean_byte_change_percent": 253.1640312099212,
815
+ "mean_omission_to_baseline_ratio": 3.531640312099212,
816
+ "mean_omission_to_original_ratio": 7.696221477336916,
817
+ "operator": "entropy_special",
818
+ "row_count": 1895
819
+ },
820
+ {
821
+ "dataset_count": 81,
822
+ "dataset_ids": [
823
+ "Air-Quality",
824
+ "Bird-migration",
825
+ "Comments",
826
+ "IGlocations2",
827
+ "Metro-Traffic",
828
+ "NYC_Yellow_Taxi_Trip",
829
+ "RealEstate1",
830
+ "RealEstate2",
831
+ "Romance",
832
+ "SpatialEpiBench",
833
+ "Telco",
834
+ "TrainsUK2",
835
+ "Uberlandia",
836
+ "Wins",
837
+ "YaleLanguages",
838
+ "ast_spacemobile_fleet_data",
839
+ "australian_electricity_demand",
840
+ "bitcoin",
841
+ "car_parts",
842
+ "covid_deaths-monash",
843
+ "dmi-aarhus-weather-data",
844
+ "eea_pm25_forecasting",
845
+ "faang_engineered_time_series_features_2013_2025",
846
+ "fred_md",
847
+ "freshretailnet_50k",
848
+ "freshretailnet_lt",
849
+ "fulus_lyd_rates_2025",
850
+ "geomagnetic_kp_index",
851
+ "github_top_projects",
852
+ "globalstar_fleet_data",
853
+ "hospital-monash",
854
+ "hourly-stock-data-2023",
855
+ "jovian_lightning",
856
+ "kaggle_web_traffic_weekly",
857
+ "kdd_cup_2018",
858
+ "knowable",
859
+ "kraken-trading-data",
860
+ "kuiper_fleet_data",
861
+ "multi_model_trading_data",
862
+ "nifty50_market_regime",
863
+ "nn5_daily",
864
+ "nn5_weekly",
865
+ "oikolab_weather",
866
+ "omie_blockchain_study",
867
+ "ooni_censorship_historical",
868
+ "pedestrian_counts",
869
+ "phenology_normal_hawaii",
870
+ "polymarket_crypto_5m_15m",
871
+ "rating",
872
+ "reg_forecasting_v2",
873
+ "rideshare",
874
+ "salesforecastingwomartstore",
875
+ "saugeenday-monash",
876
+ "sleep_score_fitbit",
877
+ "solar_10_minutes",
878
+ "solar_4_seconds",
879
+ "solar_weekly",
880
+ "spx",
881
+ "stock_dataset",
882
+ "sunspot",
883
+ "timeseries-1m-QQQ-10y",
884
+ "timeseries-finance-ETF",
885
+ "timeseries_finance_etf_missing",
886
+ "tourism_monthly",
887
+ "tourism_monthly-zaai-ai",
888
+ "tourism_quarterly",
889
+ "tourism_yearly",
890
+ "traffic_hourly",
891
+ "traffic_weekly",
892
+ "traqq_weekly_activity",
893
+ "trending_stocks_yahoo_finance",
894
+ "uk_electricity_generation_mix_2019_2026",
895
+ "us_births-monash",
896
+ "vehicle_trips",
897
+ "weather_data_NC",
898
+ "wids2023_competition_weather_forecasting",
899
+ "wind_4_seconds",
900
+ "wordle_mcm_dataset",
901
+ "xauusd",
902
+ "xauusd_1m",
903
+ "zillow_viewer"
904
+ ],
905
+ "mean_baseline_to_original_ratio": 8.254010471814926,
906
+ "mean_byte_change_percent": 66.35038979287349,
907
+ "mean_omission_to_baseline_ratio": 1.6635038979287349,
908
+ "mean_omission_to_original_ratio": 5.889324165391926,
909
+ "operator": "integer_code",
910
+ "row_count": 491
911
+ },
912
+ {
913
+ "dataset_count": 160,
914
+ "dataset_ids": [
915
+ "Air-Quality",
916
+ "Bar-Crawl",
917
+ "Bird-migration",
918
+ "Comments",
919
+ "ETDataset-ett",
920
+ "IGlocations2",
921
+ "Metro-Traffic",
922
+ "NYC_Yellow_Taxi_Trip",
923
+ "RealEstate1",
924
+ "RealEstate2",
925
+ "Romance",
926
+ "SpatialEpiBench",
927
+ "Telco",
928
+ "TrainsUK2",
929
+ "Uberlandia",
930
+ "Wins",
931
+ "YaleLanguages",
932
+ "africa_senegal_mauritania_crops_spi",
933
+ "ahr999-dataset",
934
+ "ast_spacemobile_fleet_data",
935
+ "australia_solar",
936
+ "australian_electricity_demand",
937
+ "auto_production_sf",
938
+ "azure2019_u",
939
+ "bitcoin",
940
+ "bitcoin_price_timeseries",
941
+ "car_parts",
942
+ "coastal_t_s",
943
+ "commodity_import",
944
+ "commodity_production",
945
+ "covid_deaths-monash",
946
+ "cphl",
947
+ "crypto",
948
+ "crypto_data",
949
+ "current_velocity",
950
+ "deep-space-probes",
951
+ "dmi-aarhus-weather-data",
952
+ "dst-index",
953
+ "ecdc_covid",
954
+ "eea_pm25_forecasting",
955
+ "electricity_demand",
956
+ "electricity_load_2011_2014",
957
+ "electricity_production",
958
+ "enedis-with-holidays",
959
+ "epf_electricity_price",
960
+ "eweld_load",
961
+ "exchange_rate",
962
+ "faang_engineered_time_series_features_2013_2025",
963
+ "finland_traffic",
964
+ "forex_factory_calendar",
965
+ "fred_md",
966
+ "freshretailnet_50k",
967
+ "freshretailnet_lt",
968
+ "fulus_lyd_rates_2025",
969
+ "geomagnetic_kp_index",
970
+ "github_top_projects",
971
+ "global_influenza",
972
+ "global_price",
973
+ "globalstar_fleet_data",
974
+ "gluco_tsfm_benchmark",
975
+ "goes_omni_electron_flux_forecasting",
976
+ "greatplains_multisource_2000_2024",
977
+ "hospital-monash",
978
+ "hourly-stock-data-2023",
979
+ "hourly_electricity_demand_brazil",
980
+ "housing_inventory",
981
+ "indian_stock_hourly_2017_2021",
982
+ "job_claims",
983
+ "jolts",
984
+ "jovian_lightning",
985
+ "kaggle_web_traffic",
986
+ "kaggle_web_traffic_weekly",
987
+ "kdd_cup_2018",
988
+ "knowable",
989
+ "kraken-trading-data",
990
+ "kuiper_fleet_data",
991
+ "london_smart_meters",
992
+ "macroecon",
993
+ "magseven_ml_ready_high_frequency_anomaly",
994
+ "meteoblue",
995
+ "metropt_3",
996
+ "multi_model_trading_data",
997
+ "nasa_maven_kp_insitu",
998
+ "national_illness",
999
+ "ne_china_wind",
1000
+ "niederschlag_station_4091_bavaria_germany",
1001
+ "nifty50_market_regime",
1002
+ "nn5_daily",
1003
+ "nn5_weekly",
1004
+ "oikolab_weather",
1005
+ "oil_price",
1006
+ "omie_blockchain_study",
1007
+ "online_retail_2_uci",
1008
+ "ooni_censorship_historical",
1009
+ "openelectricity_nem",
1010
+ "orbital_chaos_nasa_ssc",
1011
+ "pedestrian_counts",
1012
+ "phenology_normal_hawaii",
1013
+ "polymarket_crypto_5m_15m",
1014
+ "port_activity",
1015
+ "quitobench",
1016
+ "rating",
1017
+ "reg_forecasting_v2",
1018
+ "rideshare",
1019
+ "salesforecastingwomartstore",
1020
+ "saugeenday-monash",
1021
+ "scaphandre_cpu_usage",
1022
+ "sg_carpark",
1023
+ "sg_pm25",
1024
+ "sg_weather",
1025
+ "sleep_score_fitbit",
1026
+ "solar_10_minutes",
1027
+ "solar_4_seconds",
1028
+ "solar_weekly",
1029
+ "solusdt_enhanced_180",
1030
+ "spx",
1031
+ "stock_dataset",
1032
+ "substorm_onsets",
1033
+ "sunspot",
1034
+ "telangana_weather",
1035
+ "temperature_rain",
1036
+ "timeseries-1m-QQQ-10y",
1037
+ "timeseries-finance-ETF",
1038
+ "timeseries_1mn_sp500",
1039
+ "timeseries_1mn_stocks",
1040
+ "timeseries_finance_etf_missing",
1041
+ "tourism_monthly",
1042
+ "tourism_monthly-zaai-ai",
1043
+ "tourism_quarterly",
1044
+ "tourism_residuals",
1045
+ "tourism_yearly",
1046
+ "traffic",
1047
+ "traffic_hourly",
1048
+ "traffic_weekly",
1049
+ "traqq_weekly_activity",
1050
+ "trending_stocks_yahoo_finance",
1051
+ "trxusdt_spot_1m_05_2021_to_03_2026",
1052
+ "uk_electricity_generation_mix_2019_2026",
1053
+ "uncertainty_1m",
1054
+ "us_births-monash",
1055
+ "us_labor",
1056
+ "us_stock_financial_ratios",
1057
+ "us_term_structure",
1058
+ "vehicle_sales",
1059
+ "vehicle_supply",
1060
+ "vehicle_trips",
1061
+ "water_quality_darwin",
1062
+ "weather_data_NC",
1063
+ "weather_data_bavaria",
1064
+ "wids2023_competition_weather_forecasting",
1065
+ "wind_4_seconds",
1066
+ "wind_farms_minutely",
1067
+ "wordle_mcm_dataset",
1068
+ "wui_global",
1069
+ "xauusd",
1070
+ "xauusd_1m",
1071
+ "xinyi_public_gym",
1072
+ "xrpusdt_spot_1m_05_2021_to_03_2026",
1073
+ "yongchun_public_gym",
1074
+ "zillow_viewer"
1075
+ ],
1076
+ "mean_baseline_to_original_ratio": 10.796656930248938,
1077
+ "mean_byte_change_percent": 49.98352756875184,
1078
+ "mean_omission_to_baseline_ratio": 1.4998352756875184,
1079
+ "mean_omission_to_original_ratio": 7.540059345033453,
1080
+ "operator": "match_token_format",
1081
+ "row_count": 3611
1082
+ },
1083
+ {
1084
+ "dataset_count": 160,
1085
+ "dataset_ids": [
1086
+ "Air-Quality",
1087
+ "Bar-Crawl",
1088
+ "Bird-migration",
1089
+ "Comments",
1090
+ "ETDataset-ett",
1091
+ "IGlocations2",
1092
+ "Metro-Traffic",
1093
+ "NYC_Yellow_Taxi_Trip",
1094
+ "RealEstate1",
1095
+ "RealEstate2",
1096
+ "Romance",
1097
+ "SpatialEpiBench",
1098
+ "Telco",
1099
+ "TrainsUK2",
1100
+ "Uberlandia",
1101
+ "Wins",
1102
+ "YaleLanguages",
1103
+ "africa_senegal_mauritania_crops_spi",
1104
+ "ahr999-dataset",
1105
+ "ast_spacemobile_fleet_data",
1106
+ "australia_solar",
1107
+ "australian_electricity_demand",
1108
+ "auto_production_sf",
1109
+ "azure2019_u",
1110
+ "bitcoin",
1111
+ "bitcoin_price_timeseries",
1112
+ "car_parts",
1113
+ "coastal_t_s",
1114
+ "commodity_import",
1115
+ "commodity_production",
1116
+ "covid_deaths-monash",
1117
+ "cphl",
1118
+ "crypto",
1119
+ "crypto_data",
1120
+ "current_velocity",
1121
+ "deep-space-probes",
1122
+ "dmi-aarhus-weather-data",
1123
+ "dst-index",
1124
+ "ecdc_covid",
1125
+ "eea_pm25_forecasting",
1126
+ "electricity_demand",
1127
+ "electricity_load_2011_2014",
1128
+ "electricity_production",
1129
+ "enedis-with-holidays",
1130
+ "epf_electricity_price",
1131
+ "eweld_load",
1132
+ "exchange_rate",
1133
+ "faang_engineered_time_series_features_2013_2025",
1134
+ "finland_traffic",
1135
+ "forex_factory_calendar",
1136
+ "fred_md",
1137
+ "freshretailnet_50k",
1138
+ "freshretailnet_lt",
1139
+ "fulus_lyd_rates_2025",
1140
+ "geomagnetic_kp_index",
1141
+ "github_top_projects",
1142
+ "global_influenza",
1143
+ "global_price",
1144
+ "globalstar_fleet_data",
1145
+ "gluco_tsfm_benchmark",
1146
+ "goes_omni_electron_flux_forecasting",
1147
+ "greatplains_multisource_2000_2024",
1148
+ "hospital-monash",
1149
+ "hourly-stock-data-2023",
1150
+ "hourly_electricity_demand_brazil",
1151
+ "housing_inventory",
1152
+ "indian_stock_hourly_2017_2021",
1153
+ "job_claims",
1154
+ "jolts",
1155
+ "jovian_lightning",
1156
+ "kaggle_web_traffic",
1157
+ "kaggle_web_traffic_weekly",
1158
+ "kdd_cup_2018",
1159
+ "knowable",
1160
+ "kraken-trading-data",
1161
+ "kuiper_fleet_data",
1162
+ "london_smart_meters",
1163
+ "macroecon",
1164
+ "magseven_ml_ready_high_frequency_anomaly",
1165
+ "meteoblue",
1166
+ "metropt_3",
1167
+ "multi_model_trading_data",
1168
+ "nasa_maven_kp_insitu",
1169
+ "national_illness",
1170
+ "ne_china_wind",
1171
+ "niederschlag_station_4091_bavaria_germany",
1172
+ "nifty50_market_regime",
1173
+ "nn5_daily",
1174
+ "nn5_weekly",
1175
+ "oikolab_weather",
1176
+ "oil_price",
1177
+ "omie_blockchain_study",
1178
+ "online_retail_2_uci",
1179
+ "ooni_censorship_historical",
1180
+ "openelectricity_nem",
1181
+ "orbital_chaos_nasa_ssc",
1182
+ "pedestrian_counts",
1183
+ "phenology_normal_hawaii",
1184
+ "polymarket_crypto_5m_15m",
1185
+ "port_activity",
1186
+ "quitobench",
1187
+ "rating",
1188
+ "reg_forecasting_v2",
1189
+ "rideshare",
1190
+ "salesforecastingwomartstore",
1191
+ "saugeenday-monash",
1192
+ "scaphandre_cpu_usage",
1193
+ "sg_carpark",
1194
+ "sg_pm25",
1195
+ "sg_weather",
1196
+ "sleep_score_fitbit",
1197
+ "solar_10_minutes",
1198
+ "solar_4_seconds",
1199
+ "solar_weekly",
1200
+ "solusdt_enhanced_180",
1201
+ "spx",
1202
+ "stock_dataset",
1203
+ "substorm_onsets",
1204
+ "sunspot",
1205
+ "telangana_weather",
1206
+ "temperature_rain",
1207
+ "timeseries-1m-QQQ-10y",
1208
+ "timeseries-finance-ETF",
1209
+ "timeseries_1mn_sp500",
1210
+ "timeseries_1mn_stocks",
1211
+ "timeseries_finance_etf_missing",
1212
+ "tourism_monthly",
1213
+ "tourism_monthly-zaai-ai",
1214
+ "tourism_quarterly",
1215
+ "tourism_residuals",
1216
+ "tourism_yearly",
1217
+ "traffic",
1218
+ "traffic_hourly",
1219
+ "traffic_weekly",
1220
+ "traqq_weekly_activity",
1221
+ "trending_stocks_yahoo_finance",
1222
+ "trxusdt_spot_1m_05_2021_to_03_2026",
1223
+ "uk_electricity_generation_mix_2019_2026",
1224
+ "uncertainty_1m",
1225
+ "us_births-monash",
1226
+ "us_labor",
1227
+ "us_stock_financial_ratios",
1228
+ "us_term_structure",
1229
+ "vehicle_sales",
1230
+ "vehicle_supply",
1231
+ "vehicle_trips",
1232
+ "water_quality_darwin",
1233
+ "weather_data_NC",
1234
+ "weather_data_bavaria",
1235
+ "wids2023_competition_weather_forecasting",
1236
+ "wind_4_seconds",
1237
+ "wind_farms_minutely",
1238
+ "wordle_mcm_dataset",
1239
+ "wui_global",
1240
+ "xauusd",
1241
+ "xauusd_1m",
1242
+ "xinyi_public_gym",
1243
+ "xrpusdt_spot_1m_05_2021_to_03_2026",
1244
+ "yongchun_public_gym",
1245
+ "zillow_viewer"
1246
+ ],
1247
+ "mean_baseline_to_original_ratio": 7.399231685234153,
1248
+ "mean_byte_change_percent": 234.28062077509267,
1249
+ "mean_omission_to_baseline_ratio": 3.3428062077509266,
1250
+ "mean_omission_to_original_ratio": 3.5127479764942295,
1251
+ "operator": "run_length",
1252
+ "row_count": 3611
1253
+ },
1254
+ {
1255
+ "dataset_count": 105,
1256
+ "dataset_ids": [
1257
+ "Air-Quality",
1258
+ "Bar-Crawl",
1259
+ "Bird-migration",
1260
+ "Comments",
1261
+ "IGlocations2",
1262
+ "Metro-Traffic",
1263
+ "NYC_Yellow_Taxi_Trip",
1264
+ "RealEstate1",
1265
+ "RealEstate2",
1266
+ "Romance",
1267
+ "SpatialEpiBench",
1268
+ "Telco",
1269
+ "TrainsUK2",
1270
+ "Uberlandia",
1271
+ "Wins",
1272
+ "YaleLanguages",
1273
+ "africa_senegal_mauritania_crops_spi",
1274
+ "ahr999-dataset",
1275
+ "ast_spacemobile_fleet_data",
1276
+ "australian_electricity_demand",
1277
+ "bitcoin",
1278
+ "bitcoin_price_timeseries",
1279
+ "car_parts",
1280
+ "covid_deaths-monash",
1281
+ "crypto_data",
1282
+ "deep-space-probes",
1283
+ "dmi-aarhus-weather-data",
1284
+ "dst-index",
1285
+ "eea_pm25_forecasting",
1286
+ "electricity_demand",
1287
+ "faang_engineered_time_series_features_2013_2025",
1288
+ "forex_factory_calendar",
1289
+ "fred_md",
1290
+ "freshretailnet_50k",
1291
+ "freshretailnet_lt",
1292
+ "fulus_lyd_rates_2025",
1293
+ "geomagnetic_kp_index",
1294
+ "github_top_projects",
1295
+ "globalstar_fleet_data",
1296
+ "gluco_tsfm_benchmark",
1297
+ "goes_omni_electron_flux_forecasting",
1298
+ "hospital-monash",
1299
+ "hourly-stock-data-2023",
1300
+ "indian_stock_hourly_2017_2021",
1301
+ "jovian_lightning",
1302
+ "kaggle_web_traffic_weekly",
1303
+ "kdd_cup_2018",
1304
+ "knowable",
1305
+ "kraken-trading-data",
1306
+ "kuiper_fleet_data",
1307
+ "meteoblue",
1308
+ "multi_model_trading_data",
1309
+ "nasa_maven_kp_insitu",
1310
+ "niederschlag_station_4091_bavaria_germany",
1311
+ "nifty50_market_regime",
1312
+ "nn5_daily",
1313
+ "nn5_weekly",
1314
+ "oikolab_weather",
1315
+ "omie_blockchain_study",
1316
+ "ooni_censorship_historical",
1317
+ "orbital_chaos_nasa_ssc",
1318
+ "pedestrian_counts",
1319
+ "phenology_normal_hawaii",
1320
+ "polymarket_crypto_5m_15m",
1321
+ "quitobench",
1322
+ "rating",
1323
+ "reg_forecasting_v2",
1324
+ "rideshare",
1325
+ "salesforecastingwomartstore",
1326
+ "saugeenday-monash",
1327
+ "sleep_score_fitbit",
1328
+ "solar_10_minutes",
1329
+ "solar_4_seconds",
1330
+ "solar_weekly",
1331
+ "solusdt_enhanced_180",
1332
+ "spx",
1333
+ "stock_dataset",
1334
+ "substorm_onsets",
1335
+ "sunspot",
1336
+ "timeseries-1m-QQQ-10y",
1337
+ "timeseries-finance-ETF",
1338
+ "timeseries_1mn_sp500",
1339
+ "timeseries_1mn_stocks",
1340
+ "timeseries_finance_etf_missing",
1341
+ "tourism_monthly",
1342
+ "tourism_monthly-zaai-ai",
1343
+ "tourism_quarterly",
1344
+ "tourism_residuals",
1345
+ "tourism_yearly",
1346
+ "traffic_hourly",
1347
+ "traffic_weekly",
1348
+ "traqq_weekly_activity",
1349
+ "trending_stocks_yahoo_finance",
1350
+ "uk_electricity_generation_mix_2019_2026",
1351
+ "us_births-monash",
1352
+ "us_stock_financial_ratios",
1353
+ "vehicle_trips",
1354
+ "weather_data_NC",
1355
+ "weather_data_bavaria",
1356
+ "wids2023_competition_weather_forecasting",
1357
+ "wind_4_seconds",
1358
+ "wordle_mcm_dataset",
1359
+ "xauusd",
1360
+ "xauusd_1m",
1361
+ "zillow_viewer"
1362
+ ],
1363
+ "mean_baseline_to_original_ratio": 7.345386448946594,
1364
+ "mean_byte_change_percent": 312.99513486080724,
1365
+ "mean_omission_to_baseline_ratio": 4.129951348608072,
1366
+ "mean_omission_to_original_ratio": 5.201818911054927,
1367
+ "operator": "trailing_zero_pack",
1368
+ "row_count": 1895
1369
+ }
1370
+ ],
1371
+ "schema": "compressionbenchmark-operator-byte-effect-summary-v1",
1372
+ "status": "accepted",
1373
+ "storage_packaging": {
1374
+ "logical_csv_sha256_preserved": true,
1375
+ "lossless": true,
1376
+ "receipt_file": "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json",
1377
+ "schema": "compressionbenchmark-operator-csv-gzip-packaging-v1"
1378
+ },
1379
+ "timing": {
1380
+ "admission": "none_all_fields_null_cross_host_timing_forbidden",
1381
+ "field_count": 18,
1382
+ "fields": [
1383
+ "compression_time_ns",
1384
+ "decompression_time_ns",
1385
+ "baseline_compression_ns",
1386
+ "baseline_decompression_ns",
1387
+ "omission_compression_ns",
1388
+ "omission_decompression_ns",
1389
+ "baseline_compression_ns_samples",
1390
+ "baseline_decompression_ns_samples",
1391
+ "omission_compression_ns_samples",
1392
+ "omission_decompression_ns_samples",
1393
+ "baseline_compression_ns_per_byte",
1394
+ "baseline_decompression_ns_per_byte",
1395
+ "omission_compression_ns_per_byte",
1396
+ "omission_decompression_ns_per_byte",
1397
+ "baseline_compression_ns_per_point",
1398
+ "baseline_decompression_ns_per_point",
1399
+ "omission_compression_ns_per_point",
1400
+ "omission_decompression_ns_per_point"
1401
+ ],
1402
+ "status": "unavailable"
1403
+ }
1404
+ }
style.css CHANGED
@@ -15,3 +15,7 @@
15
  @media(max-width:1000px){.operator-summary{grid-template-columns:repeat(3,1fr)}.dataset-list{grid-template-columns:repeat(2,minmax(0,1fr))}.dataset-catalog-head{align-items:stretch;flex-direction:column;gap:12px}.dataset-catalog-controls{width:100%;grid-template-columns:1fr 1.5fr}}
16
  @media(max-width:768px){.operator-summary{grid-template-columns:repeat(2,1fr)}.implementation-entry dl>div{grid-template-columns:1fr;gap:1px}.dataset-catalog-panel{padding:14px}.dataset-catalog-controls,.dataset-list{grid-template-columns:1fr}.dataset-catalog{max-height:520px}}
17
  .dataset-badge-legend{display:flex;align-items:center;flex-wrap:wrap;gap:6px;margin:8px 0 0;color:var(--muted);font-size:10px;line-height:1.45}.thulab-dataset-badge{display:inline-flex;align-items:center;gap:4px;width:max-content;padding:2px 7px;border:1px solid #d7a92880;border-radius:999px;background:#f4c84b24;color:#8a6410;font-size:9px;font-weight:700;line-height:1.4;white-space:nowrap}.thulab-dataset-badge:hover{border-color:#d7a928;background:#f4c84b38;color:#6f4f08;text-decoration:none}:root[data-theme=dark] .thulab-dataset-badge{border-color:#d9b84c80;background:#d9b84c1c;color:#efd46f}:root[data-theme=dark] .thulab-dataset-badge:hover{border-color:#efd46f;background:#d9b84c30;color:#ffe89b}.dataset-affiliations{display:flex;flex-wrap:wrap;gap:5px;margin-top:7px}.toolbar-title-row{display:flex;align-items:center;flex-wrap:wrap;gap:8px}.toolbar-title-row h2{margin:0}
 
 
 
 
 
15
  @media(max-width:1000px){.operator-summary{grid-template-columns:repeat(3,1fr)}.dataset-list{grid-template-columns:repeat(2,minmax(0,1fr))}.dataset-catalog-head{align-items:stretch;flex-direction:column;gap:12px}.dataset-catalog-controls{width:100%;grid-template-columns:1fr 1.5fr}}
16
  @media(max-width:768px){.operator-summary{grid-template-columns:repeat(2,1fr)}.implementation-entry dl>div{grid-template-columns:1fr;gap:1px}.dataset-catalog-panel{padding:14px}.dataset-catalog-controls,.dataset-list{grid-template-columns:1fr}.dataset-catalog{max-height:520px}}
17
  .dataset-badge-legend{display:flex;align-items:center;flex-wrap:wrap;gap:6px;margin:8px 0 0;color:var(--muted);font-size:10px;line-height:1.45}.thulab-dataset-badge{display:inline-flex;align-items:center;gap:4px;width:max-content;padding:2px 7px;border:1px solid #d7a92880;border-radius:999px;background:#f4c84b24;color:#8a6410;font-size:9px;font-weight:700;line-height:1.4;white-space:nowrap}.thulab-dataset-badge:hover{border-color:#d7a928;background:#f4c84b38;color:#6f4f08;text-decoration:none}:root[data-theme=dark] .thulab-dataset-badge{border-color:#d9b84c80;background:#d9b84c1c;color:#efd46f}:root[data-theme=dark] .thulab-dataset-badge:hover{border-color:#efd46f;background:#d9b84c30;color:#ffe89b}.dataset-affiliations{display:flex;flex-wrap:wrap;gap:5px;margin-top:7px}.toolbar-title-row{display:flex;align-items:center;flex-wrap:wrap;gap:8px}.toolbar-title-row h2{margin:0}
18
+
19
+ .snapshot-notice{margin:0 0 1.5rem;padding:1rem 1.25rem;border:1px solid var(--border,#cbd5e1);border-radius:12px}.snapshot-notice p{margin:.5rem 0;line-height:1.5}
20
+
21
+ .operator-effect-results{margin:18px 0 26px;padding:18px;border:1px solid var(--line);border-radius:var(--radius);background:var(--surface)}.operator-effect-head{display:flex;align-items:start;justify-content:space-between;gap:20px}.operator-effect-head h3{margin:0 0 4px}.operator-effect-table-wrap{max-height:430px}.operator-effect-table-wrap th:first-child,.operator-effect-table-wrap td:first-child{text-align:left}.operator-effect-cost{color:#a34832}.operator-effect-saving{color:var(--accent)}@media(max-width:768px){.operator-effect-head{flex-direction:column}.operator-effect-head .quiet-button{width:100%;text-align:center}.operator-effect-table-wrap{max-height:520px}}
ui-data.json CHANGED
The diff for this file is too large to render. See raw diff