Publish licensed data snapshots with LAN LFS transfer and content audits

2026-10-01 03:42:51 +08:00
parent 13cd0e0be7
commit 6e33e05ede
173 changed files with 3614 additions and 0 deletions
@@ -0,0 +1,102 @@
+{
+  "archive_bytes": 635332131,
+  "archive_format": "tar.pax+zstd",
+  "archive_sha256": "a5d8ac0e6eebd5c6235078e9a9ac5a5c224bc86185bb77dd38248833c6b946f1",
+  "chunk_bytes": 67108864,
+  "chunks": [
+    {
+      "bytes": 67108864,
+      "index": 0,
+      "path": "payload-000000.bin",
+      "sha256": "a65619004cdc36e594bdca344d1fe51ac86fb719159f70a2ba0fb21c763f9c04"
+    },
+    {
+      "bytes": 67108864,
+      "index": 1,
+      "path": "payload-000001.bin",
+      "sha256": "cca9eedbc44b20be736317745ee12e8c06bf0e1aafc7815b74bc6aa27cef5be5"
+    },
+    {
+      "bytes": 67108864,
+      "index": 2,
+      "path": "payload-000002.bin",
+      "sha256": "e395b23867e74b7579aed8eeb927e373c86d77433962a0f89ac198aeca4f8470"
+    },
+    {
+      "bytes": 67108864,
+      "index": 3,
+      "path": "payload-000003.bin",
+      "sha256": "e47d83eba2875f963add02ab697cb6386dd8fe4a5f33b96db5a321986a276774"
+    },
+    {
+      "bytes": 67108864,
+      "index": 4,
+      "path": "payload-000004.bin",
+      "sha256": "4d4bdff46071f05c29ac34cd9081204739317bef5ab862d612d2c7a82c3d5bca"
+    },
+    {
+      "bytes": 67108864,
+      "index": 5,
+      "path": "payload-000005.bin",
+      "sha256": "4f82611c41e868faa6ea06d7bd275df90f712e3f5eb14296117e39c3bf6c95c0"
+    },
+    {
+      "bytes": 67108864,
+      "index": 6,
+      "path": "payload-000006.bin",
+      "sha256": "4cbfb164c194db8c54eadef4d039240d98b0f5be8e20e4005be08bd2d2f6ab5d"
+    },
+    {
+      "bytes": 67108864,
+      "index": 7,
+      "path": "payload-000007.bin",
+      "sha256": "9ba4adfe64d73d0ceb249ab25215734f58b0d8b38d11f22676fd93f68e83df68"
+    },
+    {
+      "bytes": 67108864,
+      "index": 8,
+      "path": "payload-000008.bin",
+      "sha256": "8f388376c6e9d3b7abaff219b00d669ea88db1bf5cd48381db9354598102b345"
+    },
+    {
+      "bytes": 31352355,
+      "index": 9,
+      "path": "payload-000009.bin",
+      "sha256": "e1ac638f1d640de9e85b82d9526d6f729f78239e66c5c024e0037144adf7f003"
+    }
+  ],
+  "exclusion_records": 6,
+  "exclusions": {
+    "bytes": 219,
+    "sha256": "0909f401f73ca15301ea2be92a5e7c66cf79d9d4f8bbe5449f82c2980d6d3e80"
+  },
+  "group_id": "malecns-processed",
+  "license": {
+    "derived_data": "CC-BY-4.0",
+    "local_scripts_reports": "Project-authored processing and provenance; no new blanket software license",
+    "url": "https://creativecommons.org/licenses/by/4.0/"
+  },
+  "members": {
+    "bytes": 3639,
+    "sha256": "fe399bea661cdd018e53a5ea58bc46a64d2f94fb09d1dec40f8a956789204627"
+  },
+  "plan_sha256": "a20a61821c504e8315171a5fd14afbac011b934709af344045175bdda9fcba71",
+  "provenance": {
+    "attribution": "Original Male CNS collaboration; Digital Drosophila project for local processing",
+    "canonical_edges": 25582938,
+    "canonical_neurons": 166700,
+    "canonical_synaptic_weight_sum": 124177617,
+    "changes": "Existing Phase 3 all-body and Phase 3B neuron-only tables, index mappings, CSR and audit reports, copied byte-for-byte. These were previously derived by filtering/reindexing official data, not new preprocessing. Phase 3 historical outputs are not the approved SNN input; use neuron-only for current runtime.",
+    "dataset": "male-cns:v1.0",
+    "source_page": "https://male-cns.janelia.org/download/"
+  },
+  "schema": "lfs-publication-group-v1",
+  "secret_scan": "UTF-8 files <=2 MiB, known binary suffixes excluded; fail closed on matching rules",
+  "source_bytes": 1140025370,
+  "source_files": 64,
+  "source_paths": [
+    "datasets/male-cns-v1.0/processed"
+  ],
+  "source_root": "/data/digital-drosophila",
+  "verification_scope": "content snapshot, not a license grant or nested-archive secret audit"
+}