jzxiao commited on
Commit
c7aeab6
·
verified ·
1 Parent(s): f998934

Publish the main26 gzip packager source and correct its references

Browse files

Documentation/source-reference correction only. Publish the exact Main26 snapshot packager and bind its SHA in the manifest/integration receipt. Numerical data, UI, app, ranking, input selection and prior results are unchanged.

CPP135_MAIN26_SITE_INTEGRATION.json CHANGED
@@ -1,147 +1,60 @@
1
  {
2
- "candidate_revision": "v4_gzip_transport_manifest_closure",
3
- "created_at": "2026-10-15T10:29:23.734229+00:00",
4
  "files": {
5
- "CPP135_MAIN26_AGGREGATE_RECEIPT.json": {
6
- "bytes": 3683,
7
- "sha256": "f098925d8bd0b5718b102a8b6921b1234ced3baec80e2faeb47f2edb71c2d337"
8
- },
9
- "CPP135_MAIN26_INPUT_SHA256SUMS.txt": {
10
- "bytes": 355,
11
- "sha256": "24d6eec79a4e09cd0e8c9819dc23d9723812867158869d7214caf0f1b9a75c24"
12
- },
13
- "CPP135_MAIN26_SELECTED_SOURCES.json": {
14
- "bytes": 1938310,
15
- "sha256": "50cc9edd30e3d3a6c7314bf3f28bf16d0a56ce095f9849c2fccb4a7a470eebfc"
16
- },
17
- "CPP135_MAIN26_SITE_ACCEPTANCE.json": {
18
- "bytes": 2860,
19
- "sha256": "e99fdac1f870174c520a2a2fae643ca4259a33afb4feffd0e849a5a302ad91cd"
20
- },
21
- "README.md": {
22
- "bytes": 4188,
23
- "sha256": "c89a678703ff26d46f676a8bb807aff3da30c74961c21063ea277307c8e8af99"
24
- },
25
- "app.js": {
26
- "bytes": 69465,
27
- "sha256": "39ca6b54fb0dcc0b722f0a84ea7e5175151de0225bfb65d4e40b53cf54fc204a"
28
- },
29
- "build_gzip_storage_recovery.py": {
30
- "bytes": 17650,
31
- "sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401"
32
- },
33
- "build_main26_site.py": {
34
- "bytes": 59034,
35
- "sha256": "0112b3121303e361b319791c3fbf5d8c230e3636fd1f7ce5197e9ccacc4712d9"
36
- },
37
- "cpp-latest-view-main26.json.gz": {
38
- "bytes": 837481,
39
- "sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180"
40
- },
41
- "cpp135-main26-column-results.jsonl.gz": {
42
- "bytes": 15699577,
43
- "sha256": "6c3d693556fb58f8277ac201dfe217ea85aec65489a707260af85981faa21e9b"
44
- },
45
- "cpp135-main26-dataset-method-results.jsonl.gz": {
46
- "bytes": 457656,
47
- "sha256": "5ba82d79f07327d6a5b2e1405d3f58db7e72930dcd0284132764ff48a8b5859b"
48
- },
49
- "data-main26.json.gz": {
50
- "bytes": 10041708,
51
- "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8"
52
- },
53
- "index.html": {
54
- "bytes": 17814,
55
- "sha256": "3a788a52e1ff441a3782aef8b34d3aaf77cc24424a7a3286c659f46a9717d2e8"
56
  },
57
  "manifest.json": {
58
- "bytes": 95687,
59
- "sha256": "15d2d18dd65f2c811a88149dd12c8ca3dd3b1089d7b4b8723f6767c823734ba0"
60
- },
61
- "ui-data.json": {
62
- "bytes": 9697244,
63
- "sha256": "841b15cbef0c346b43d72ab3c9530065abe4d24c45aef64d5e75d8ec49996f8f"
64
  }
65
  },
66
- "final_dataset_result_count": 99008,
67
- "historical_dataset_results_canonical_sha256": "213ac4e2c2d53801095316040d633cfd9541055ffc939b62a5b46ab95f442547",
68
- "new_dataset_result_count": 4037,
69
- "old_dataset_result_count": 94971,
70
- "page_checks_required_after_publication": [
71
- "C++ Overall uses the latest main26 decision for all exact 135 x 26 pairs",
72
- "full-support rows show server-192 provenance and one W1/R3/T1 timing contract",
73
- "partial, unsupported and not-applicable pairs do not fall back to old numeric rows",
74
- "CSV retains source host, binary/support identity, measurement status and timing status"
75
- ],
76
- "parent_revision": "963f2ff216fd95ffba42d625a12765169eb4d850",
 
 
 
 
 
 
 
 
 
 
 
 
 
77
  "publication_file_list": [
78
- "data-main26.json.gz",
79
- "ui-data.json",
80
- "cpp-latest-view-main26.json.gz",
81
- "app.js",
82
- "index.html",
83
- "README.md",
84
  "manifest.json",
85
- "build_gzip_storage_recovery.py",
86
- "cpp135-main26-column-results.jsonl.gz",
87
- "cpp135-main26-dataset-method-results.jsonl.gz",
88
- "CPP135_MAIN26_SELECTED_SOURCES.json",
89
- "CPP135_MAIN26_AGGREGATE_RECEIPT.json",
90
- "CPP135_MAIN26_INPUT_SHA256SUMS.txt",
91
- "CPP135_MAIN26_SITE_ACCEPTANCE.json",
92
- "build_main26_site.py",
93
  "CPP135_MAIN26_SITE_INTEGRATION.json"
94
  ],
95
- "schema": "compressionbenchmark-cpp135-main26-site-integration-v1",
 
96
  "scope": {
97
- "measured_datasets": 135,
98
- "methods": 26,
99
- "pair_count": 3510,
100
- "pair_status_counts": {
101
- "numeric": 1529,
102
- "partial_numeric": 629,
103
- "unsupported": 1352
104
- }
105
  },
106
  "semantic_checks": {
107
- "all_3510_latest_pair_decisions_replaced": true,
108
- "app_javascript_syntax": "pass",
109
- "compressed_bytes_include_NA_frames_once": true,
110
- "data_ui_sidecar_hash_closure": true,
111
- "gzip_packager_source_published": true,
112
- "gzip_transport_decompresses_byte_exact_to_canonical_v2_payload": true,
113
- "historical_rows_retained_byte_for_byte_in_canonical_order": true,
114
- "large_uncompressed_data_and_sidecar_excluded_from_publication_delta": true,
115
- "latest_page_never_reads_legacy_large_files": true,
116
- "manifest_exact_file_transport_and_legacy_closure": true,
117
- "numeric_rows_only_for_full_valid_support_within_exact_dtype_scope": true,
118
- "partial_overall_never_published_but_full_dtype_scope_retained": true,
119
- "partial_unsupported_not_applicable_numeric_fallback_count": 0,
120
- "ranking_js_unchanged": true,
121
- "readme_main26_scope_and_measurement_contract_updated": true
122
  },
123
  "status": "passed_not_published",
124
- "storage_plan": {
125
- "estimated_remaining_after_files_before_integration": 77713466,
126
- "excluded_uncompressed_bytes": 185591944,
127
- "official_limit_bytes": 1000000000,
128
- "official_remaining_bytes_before": 116656178,
129
- "official_used_bytes_before": 883343822,
130
- "publication_delta_bytes": 38942712,
131
- "transport_files": {
132
- "cpp_latest_view": {
133
- "encoding": "gzip",
134
- "file": "cpp-latest-view-main26.json.gz",
135
- "sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180",
136
- "uncompressed_sha256": "f1aef2f23a0374e43ddde18d5ab2b29095ff344cf9ef4d591cd8037e55958a6e"
137
- },
138
- "data": {
139
- "encoding": "gzip",
140
- "file": "data-main26.json.gz",
141
- "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
142
- "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
143
- }
144
- }
145
- },
146
- "supersedes_candidate": "candidate_main26_v3"
147
  }
 
1
  {
2
+ "created_at": "2026-10-15T10:41:11.575667+00:00",
 
3
  "files": {
4
+ "build_main26_gzip_storage.py": {
5
+ "bytes": 3877,
6
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  },
8
  "manifest.json": {
9
+ "bytes": 96829,
10
+ "sha256": "d9ba49d31279996b9601beb84cb74584b7f4218adf68a120b29b06a50ee6800d"
 
 
 
 
11
  }
12
  },
13
+ "frozen_transports": {
14
+ "cpp_latest_view": {
15
+ "file": "cpp-latest-view-main26.json.gz",
16
+ "sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180",
17
+ "uncompressed_sha256": "f1aef2f23a0374e43ddde18d5ab2b29095ff344cf9ef4d591cd8037e55958a6e"
18
+ },
19
+ "data": {
20
+ "file": "data-main26.json.gz",
21
+ "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
22
+ "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
23
+ }
24
+ },
25
+ "parent_closure": {
26
+ "final_qa_sha256": "8526e827367dbf171813ca084a3837de9200bc55c695e6671f8a2bc5ad4c5772",
27
+ "integration_sha256": "de7c96c013fc98d87f6ebdb078d7c97b3727c4dbe30c060525e2170abd1cd0e2",
28
+ "manifest_sha256": "15d2d18dd65f2c811a88149dd12c8ca3dd3b1089d7b4b8723f6767c823734ba0"
29
+ },
30
+ "parent_revision": "f9989349b67cd1b86f018346ae94f23056f6e997",
31
+ "public_packager": {
32
+ "file": "build_main26_gzip_storage.py",
33
+ "role": "main26_canonical_json_gzip_packager",
34
+ "schema": "cpp135-main26-gzip-storage-build-v1",
35
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
36
+ },
37
  "publication_file_list": [
38
+ "build_main26_gzip_storage.py",
 
 
 
 
 
39
  "manifest.json",
 
 
 
 
 
 
 
 
40
  "CPP135_MAIN26_SITE_INTEGRATION.json"
41
  ],
42
+ "reason": "Replace the incorrectly cited historical operator CSV packager with the actual deterministic Main26 JSON gzip packager.",
43
+ "schema": "compressionbenchmark-cpp135-main26-packager-correction-v1",
44
  "scope": {
45
+ "changed_public_files": 3,
46
+ "result_selection_changed": false,
47
+ "scientific_payload_changed": false,
48
+ "ui_payload_changed": false
 
 
 
 
49
  },
50
  "semantic_checks": {
51
+ "actual_main26_gzip_packager_source_published": true,
52
+ "historical_operator_csv_packager_provenance_preserved_and_distinguished": true,
53
+ "manifest_public_packager_file_and_sha_match": true,
54
+ "no_experiment_or_result_rebuild": true,
55
+ "packager_reproduces_both_frozen_transports_byte_for_byte": true,
56
+ "scientific_data_ui_app_index_and_readme_unchanged": true
 
 
 
 
 
 
 
 
 
57
  },
58
  "status": "passed_not_published",
59
+ "supersedes_candidate": "candidate_main26_v4"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
  }
build_main26_gzip_storage.py ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python3
2
+ """Rebuild the two deterministic gzip transports used by the Main26 release.
3
+
4
+ This tool only packages the already accepted canonical JSON payloads. It does
5
+ not select results, alter metrics, or rebuild the benchmark. Both the source
6
+ JSON and resulting gzip bytes are checked against the frozen Main26 release.
7
+ """
8
+
9
+ from __future__ import annotations
10
+
11
+ import argparse
12
+ import gzip
13
+ import hashlib
14
+ import json
15
+ import os
16
+ import shutil
17
+ from pathlib import Path
18
+
19
+
20
+ SPECS = {
21
+ "data": {
22
+ "source": "data.json",
23
+ "target": "data-main26.json.gz",
24
+ "source_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2",
25
+ "target_sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
26
+ "target_bytes": 10041708,
27
+ },
28
+ "cpp_latest_view": {
29
+ "source": "cpp-latest-view.json",
30
+ "target": "cpp-latest-view-main26.json.gz",
31
+ "source_sha256": "f1aef2f23a0374e43ddde18d5ab2b29095ff344cf9ef4d591cd8037e55958a6e",
32
+ "target_sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180",
33
+ "target_bytes": 837481,
34
+ },
35
+ }
36
+
37
+
38
+ def sha256(path: Path) -> str:
39
+ digest = hashlib.sha256()
40
+ with path.open("rb") as stream:
41
+ for block in iter(lambda: stream.read(8 << 20), b""):
42
+ digest.update(block)
43
+ return digest.hexdigest()
44
+
45
+
46
+ def deterministic_gzip(source: Path, target: Path) -> None:
47
+ target.parent.mkdir(parents=True, exist_ok=True)
48
+ temporary = target.with_name(f".{target.name}.{os.getpid()}.tmp")
49
+ try:
50
+ with source.open("rb") as src, temporary.open("wb") as raw:
51
+ with gzip.GzipFile(
52
+ filename="", mode="wb", fileobj=raw, compresslevel=9, mtime=0
53
+ ) as zipped:
54
+ shutil.copyfileobj(src, zipped, length=8 << 20)
55
+ temporary.replace(target)
56
+ finally:
57
+ if temporary.exists():
58
+ temporary.unlink()
59
+
60
+
61
+ def main() -> None:
62
+ parser = argparse.ArgumentParser(
63
+ description="Rebuild and verify the frozen Main26 gzip transports."
64
+ )
65
+ parser.add_argument(
66
+ "--source-dir", type=Path, required=True,
67
+ help="Directory containing canonical data.json and cpp-latest-view.json",
68
+ )
69
+ parser.add_argument(
70
+ "--output-dir", type=Path, required=True,
71
+ help="Directory receiving the two deterministic .json.gz files",
72
+ )
73
+ args = parser.parse_args()
74
+
75
+ outputs = {}
76
+ for name, spec in SPECS.items():
77
+ source = args.source_dir / spec["source"]
78
+ target = args.output_dir / spec["target"]
79
+ if not source.is_file():
80
+ raise SystemExit(f"missing canonical source: {source}")
81
+ source_sha = sha256(source)
82
+ if source_sha != spec["source_sha256"]:
83
+ raise SystemExit(
84
+ f"canonical source SHA mismatch for {source}: "
85
+ f"expected {spec['source_sha256']}, got {source_sha}"
86
+ )
87
+ deterministic_gzip(source, target)
88
+ target_sha = sha256(target)
89
+ target_bytes = target.stat().st_size
90
+ if target_sha != spec["target_sha256"] or target_bytes != spec["target_bytes"]:
91
+ raise SystemExit(
92
+ f"gzip output mismatch for {target}: expected "
93
+ f"{spec['target_sha256']} / {spec['target_bytes']} bytes, got "
94
+ f"{target_sha} / {target_bytes} bytes"
95
+ )
96
+ outputs[name] = {
97
+ "source": spec["source"],
98
+ "source_sha256": source_sha,
99
+ "target": spec["target"],
100
+ "target_sha256": target_sha,
101
+ "target_bytes": target_bytes,
102
+ }
103
+
104
+ print(json.dumps({
105
+ "schema": "cpp135-main26-gzip-storage-build-v1",
106
+ "status": "verified",
107
+ "outputs": outputs,
108
+ }, ensure_ascii=False, indent=2, sort_keys=True))
109
+
110
+
111
+ if __name__ == "__main__":
112
+ main()
manifest.json CHANGED
@@ -546,6 +546,12 @@
546
  "file": "data-main26.json.gz",
547
  "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
548
  "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
 
 
 
 
 
 
549
  }
550
  },
551
  "schema": "cpp135-main26-site-import-v1",
@@ -558,6 +564,12 @@
558
  "cpp_latest_view": {
559
  "encoding": "gzip",
560
  "file": "cpp-latest-view-main26.json.gz",
 
 
 
 
 
 
561
  "schema": "compressionbenchmark-cpp-latest-view-v1",
562
  "sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180",
563
  "status": "built_from_verified_live_float9_baseline_and_completed_main26",
@@ -568,6 +580,12 @@
568
  "data_transport": {
569
  "encoding": "gzip",
570
  "file": "data-main26.json.gz",
 
 
 
 
 
 
571
  "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
572
  "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
573
  },
@@ -1612,6 +1630,12 @@
1612
  },
1613
  "timing_admission": "none_all_fields_null_cross_host_timing_forbidden"
1614
  },
 
 
 
 
 
 
1615
  "reference_catalog_sha256": "15fc0b3931c87bc7f3012b2cbd72b200fcbae811f159d200568af6fb45a10e88",
1616
  "result_csv_files": [
1617
  {
@@ -2180,6 +2204,7 @@
2180
  "derived_packaging_receipt_file": "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json",
2181
  "public_packager": {
2182
  "file": "build_gzip_storage_recovery.py",
 
2183
  "sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401"
2184
  },
2185
  "receipt_binding": "derived receipt binds this manifest; its own SHA is frozen by the external publication plan and review",
 
546
  "file": "data-main26.json.gz",
547
  "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
548
  "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
549
+ },
550
+ "public_packager": {
551
+ "file": "build_main26_gzip_storage.py",
552
+ "role": "main26_canonical_json_gzip_packager",
553
+ "schema": "cpp135-main26-gzip-storage-build-v1",
554
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
555
  }
556
  },
557
  "schema": "cpp135-main26-site-import-v1",
 
564
  "cpp_latest_view": {
565
  "encoding": "gzip",
566
  "file": "cpp-latest-view-main26.json.gz",
567
+ "public_packager": {
568
+ "file": "build_main26_gzip_storage.py",
569
+ "role": "main26_canonical_json_gzip_packager",
570
+ "schema": "cpp135-main26-gzip-storage-build-v1",
571
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
572
+ },
573
  "schema": "compressionbenchmark-cpp-latest-view-v1",
574
  "sha256": "818f9390fbbfe49e3afc1f44330cb612e32848376f158202413ad60097672180",
575
  "status": "built_from_verified_live_float9_baseline_and_completed_main26",
 
580
  "data_transport": {
581
  "encoding": "gzip",
582
  "file": "data-main26.json.gz",
583
+ "public_packager": {
584
+ "file": "build_main26_gzip_storage.py",
585
+ "role": "main26_canonical_json_gzip_packager",
586
+ "schema": "cpp135-main26-gzip-storage-build-v1",
587
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
588
+ },
589
  "sha256": "7a00869fc545f1f2cb7a6c7bd2a6f72e12eddc7361edc68925d3b4bd04ac28a8",
590
  "uncompressed_sha256": "e7f7a9f294c1a94aec0e8271c62308f499286cbe9bd2333a6fe685f0839cabb2"
591
  },
 
1630
  },
1631
  "timing_admission": "none_all_fields_null_cross_host_timing_forbidden"
1632
  },
1633
+ "public_packager": {
1634
+ "file": "build_main26_gzip_storage.py",
1635
+ "role": "main26_canonical_json_gzip_packager",
1636
+ "schema": "cpp135-main26-gzip-storage-build-v1",
1637
+ "sha256": "eff8a5fa67dc094e6d85e4d6d7ac54cb6e5643678a23751f1df68545c054549e"
1638
+ },
1639
  "reference_catalog_sha256": "15fc0b3931c87bc7f3012b2cbd72b200fcbae811f159d200568af6fb45a10e88",
1640
  "result_csv_files": [
1641
  {
 
2204
  "derived_packaging_receipt_file": "OPERATOR970_BYTE_EFFECT_GZIP_PACKAGING_V1.json",
2205
  "public_packager": {
2206
  "file": "build_gzip_storage_recovery.py",
2207
+ "role": "historical_operator_csv_gzip_packager_not_main26",
2208
  "sha256": "5ae7e125c6aab30f95cd6c05681111dfec9a94832ec44181491134a0d33ae401"
2209
  },
2210
  "receipt_binding": "derived receipt binds this manifest; its own SHA is frozen by the external publication plan and review",