Archive licensed MaleCNS core data as verified LFS chunks

2026-10-01 03:24:21 +08:00
parent 7dc85baea9
commit 13cd0e0be7
17 changed files with 225 additions and 0 deletions
@@ -0,0 +1,120 @@
+{
+  "archive_bytes": 834266158,
+  "archive_format": "tar.pax+zstd",
+  "archive_sha256": "feebf3fe3f3c2c9fea3db96fab8267330de49af7ab37008b84caeeea8dc272ed",
+  "chunk_bytes": 67108864,
+  "chunks": [
+    {
+      "bytes": 67108864,
+      "index": 0,
+      "path": "payload-000000.bin",
+      "sha256": "5527fc251d23c23209cf16c8831aedefcceb6d1e927a4eaf9ebed182fd5481ff"
+    },
+    {
+      "bytes": 67108864,
+      "index": 1,
+      "path": "payload-000001.bin",
+      "sha256": "4793d00b3d6b3506d16e21f3f3775bc70c23c70cd5be03b6733350328519a3c0"
+    },
+    {
+      "bytes": 67108864,
+      "index": 2,
+      "path": "payload-000002.bin",
+      "sha256": "a78930db08134f72e97306df7256bd8b0b533611fe9a08459f1c6289eb47624e"
+    },
+    {
+      "bytes": 67108864,
+      "index": 3,
+      "path": "payload-000003.bin",
+      "sha256": "54fc4943c3d644e1765a7cbdacf0629db1ddefde4f17035729417242930064a9"
+    },
+    {
+      "bytes": 67108864,
+      "index": 4,
+      "path": "payload-000004.bin",
+      "sha256": "7bb2deb3dd7d3f7064c096c8915bb3eff7f880a009628f6ee6c5e14dce939668"
+    },
+    {
+      "bytes": 67108864,
+      "index": 5,
+      "path": "payload-000005.bin",
+      "sha256": "d1aac9ec93c77f901c98c7343fd3713c746faf855096e9d7e6da897491c513df"
+    },
+    {
+      "bytes": 67108864,
+      "index": 6,
+      "path": "payload-000006.bin",
+      "sha256": "29f40919b04405609643b3a5a2beb749aacbf5525cf90a60d75fa3f0a283435e"
+    },
+    {
+      "bytes": 67108864,
+      "index": 7,
+      "path": "payload-000007.bin",
+      "sha256": "b3936a86da8636e5ba6d7a25f4d8d3b34eadc769e74817d67c7aefe2e9879e68"
+    },
+    {
+      "bytes": 67108864,
+      "index": 8,
+      "path": "payload-000008.bin",
+      "sha256": "47e2e7cfde2bc01d41de53ba933683faf4fa4dc57c3d80f07d8edb75dc1916d3"
+    },
+    {
+      "bytes": 67108864,
+      "index": 9,
+      "path": "payload-000009.bin",
+      "sha256": "ab37af43abeeb3434b0660fb5bfb185e7c0db07916b2a2233a2db083f66ea2b9"
+    },
+    {
+      "bytes": 67108864,
+      "index": 10,
+      "path": "payload-000010.bin",
+      "sha256": "bdbf00683b8940fb513fef121559e8e449d84972e03df2d4698d06e0dcc28efa"
+    },
+    {
+      "bytes": 67108864,
+      "index": 11,
+      "path": "payload-000011.bin",
+      "sha256": "a3ee35cae393b29d0366aebcad7f63a8ad578b61e0a93e773595dfdfe6848bbe"
+    },
+    {
+      "bytes": 28959790,
+      "index": 12,
+      "path": "payload-000012.bin",
+      "sha256": "7fbe5733e328f5a989fec3ffd78819c62ac53a32e099579492cd82766322e82a"
+    }
+  ],
+  "exclusion_records": 1,
+  "exclusions": {
+    "bytes": 135,
+    "sha256": "887492a8f75af6be4e71b6f5aa12506cef3d8e3a7363b3c6a50064da93b9b4a1"
+  },
+  "group_id": "malecns-raw-core",
+  "license": {
+    "data": "CC-BY-4.0",
+    "local_manifests_scripts": "Project-authored provenance; no new blanket software license",
+    "url": "https://creativecommons.org/licenses/by/4.0/"
+  },
+  "members": {
+    "bytes": 1009,
+    "sha256": "e963adede9d937effbf5519ae9717938a2b3324aecc1c28338800007f7003404"
+  },
+  "plan_sha256": "a20a61821c504e8315171a5fd14afbac011b934709af344045175bdda9fcba71",
+  "provenance": {
+    "attribution": "Male CNS collaboration: FlyEM (HHMI Janelia), University of Cambridge Department of Zoology, MRC Laboratory of Molecular Biology, Google Research; retain original dataset author credits",
+    "changes": "Data file bytes unchanged; archival compression and path manifest only. Download logs excluded.",
+    "source_page": "https://male-cns.janelia.org/download/",
+    "source_prefix": "gs://flyem-male-cns/v1.0/connectome-data/flat-connectome/",
+    "version": "male-cns:v1.0"
+  },
+  "schema": "lfs-publication-group-v1",
+  "secret_scan": "UTF-8 files <=2 MiB, known binary suffixes excluded; fail closed on matching rules",
+  "source_bytes": 1207032031,
+  "source_files": 17,
+  "source_paths": [
+    "datasets/male-cns-v1.0/raw/annotations",
+    "datasets/male-cns-v1.0/raw/connectivity",
+    "datasets/male-cns-v1.0/raw/_manifests"
+  ],
+  "source_root": "/data/digital-drosophila",
+  "verification_scope": "content snapshot, not a license grant or nested-archive secret audit"
+}
@@ -0,0 +1,60 @@
+{
+  "schema": "lfs-publication-plan-v1",
+  "source_root": "/data/digital-drosophila",
+  "groups": [
+    {
+      "id": "malecns-raw-core",
+      "paths": ["datasets/male-cns-v1.0/raw/annotations", "datasets/male-cns-v1.0/raw/connectivity", "datasets/male-cns-v1.0/raw/_manifests"],
+      "license": {"data": "CC-BY-4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "local_manifests_scripts": "Project-authored provenance; no new blanket software license"},
+      "provenance": {"version": "male-cns:v1.0", "source_page": "https://male-cns.janelia.org/download/", "source_prefix": "gs://flyem-male-cns/v1.0/connectome-data/flat-connectome/", "attribution": "Male CNS collaboration: FlyEM (HHMI Janelia), University of Cambridge Department of Zoology, MRC Laboratory of Molecular Biology, Google Research; retain original dataset author credits", "changes": "Data file bytes unchanged; archival compression and path manifest only. Download logs excluded."}
+    },
+    {
+      "id": "malecns-swc",
+      "paths": ["datasets/male-cns-v1.0/raw/skeletons"],
+      "license": {"data": "CC-BY-4.0", "url": "https://creativecommons.org/licenses/by/4.0/"},
+      "provenance": {"version": "male-cns:v1.0", "source_page": "https://male-cns.janelia.org/download/", "source_prefix": "gs://flyem-male-cns/v1.0/segmentation/skeletons-malecns/skeletons-swc/", "attribution": "Male CNS collaboration: FlyEM (HHMI Janelia), University of Cambridge Department of Zoology, MRC Laboratory of Molecular Biology, Google Research", "changes": "Unchanged downloaded SWC bytes; not restricted to the later neuron-only canonical set. No EM images."}
+    },
+    {
+      "id": "malecns-processed",
+      "paths": ["datasets/male-cns-v1.0/processed"],
+      "license": {"derived_data": "CC-BY-4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "local_scripts_reports": "Project-authored processing and provenance; no new blanket software license"},
+      "provenance": {"dataset": "male-cns:v1.0", "source_page": "https://male-cns.janelia.org/download/", "attribution": "Original Male CNS collaboration; Digital Drosophila project for local processing", "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.", "canonical_neurons": 166700, "canonical_edges": 25582938, "canonical_synaptic_weight_sum": 124177617}
+    },
+    {
+      "id": "malecns-synaptic-partners",
+      "paths": ["experiments/phase4aa-apl-pn-scope/external-resources"],
+      "license": {"data": "CC-BY-4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "local_provenance": "Project-authored"},
+      "provenance": {"source_page": "https://male-cns.janelia.org/download/", "source_url": "https://storage.googleapis.com/flyem-male-cns/v1.0/connectome-data/flat-connectome/syn-partners-male-cns-v1.0-minconf-0.5.feather?generation=1780494942562468", "registered_file_sha256": "959d8ef4173b35382a3e6acfaf5167c795b6d10b877572d146af04e1b487bc07", "attribution": "Male CNS collaboration: FlyEM (HHMI Janelia), University of Cambridge Department of Zoology, MRC Laboratory of Molecular Biology, Google Research", "changes": "Unchanged downloaded paired-synapse file and provenance; syn-points and EM were not downloaded."}
+    },
+    {
+      "id": "celltype-explorer",
+      "paths": ["experiments/phase4f-retinotopic-vision/external-resources/celltype-explorer"],
+      "license": {"upstream": "CC-BY-4.0", "url": "https://creativecommons.org/licenses/by/4.0/", "evidence_file": "LICENSE", "evidence_sha256": "9ba9550ad48438d0836ddab3da480b3b69ffa0aac7b7878b5a0039e7ab429411"},
+      "provenance": {"repository": "https://github.com/reiserlab/celltype-explorer-drosophila-male-cns", "commit": "789cc6c105798ce2fd70ba85dab394f90899616b", "attribution": "Reiser Lab and Male CNS Cell Type Explorer contributors; retain upstream notices", "changes": "Unchanged pinned working-tree file bytes; .git, environments, caches and credentials excluded. A source snapshot, not a full Git clone."}
+    },
+    {
+      "id": "visualpathways",
+      "paths": ["experiments/phase4f-retinotopic-vision/external-resources/visualpathways"],
+      "license": {"upstream": "GPL-3.0 as supplied in upstream LICENSE; no assertion of only/or-later option", "evidence_file": "LICENSE", "evidence_sha256": "3972dc9744f6499f0f9b2dbf76696f2ae7ad8af9b23dde66d6af86c9dfb36986", "third_party_notices": "Retained; no relicensing of third-party components"},
+      "provenance": {"repository": "https://github.com/reiserlab/visualpathways", "commit": "23f6ac131529b5f56894c6eeb9b88b17894fc00d", "attribution": "Reiser Lab and visualpathways contributors; original copyright notices and source retained", "changes": "Unchanged source/resource file bytes from pinned checkout; .git, credentials, environments and caches omitted; explicit exclusions recorded. No software execution or model alteration."}
+    },
+    {
+      "id": "door-data",
+      "paths": ["experiments/phase4l-olfactory-grounding/external-resources/DoOR.data"],
+      "license": {"upstream": "CC-BY-SA-4.0", "url": "https://creativecommons.org/licenses/by-sa/4.0/", "evidence_file": "DESCRIPTION", "evidence_sha256": "27db2a92eb651d67969de94959990d51668a5857a33c4750a3b6ef49c5880504"},
+      "provenance": {"repository": "https://github.com/ropensci/DoOR.data", "commit": "eea72d64b42a4e91dafe822cf0b5204de33f8d34", "version": "2.0.1", "attribution": "Daniel Münch, C. Giovanni Galizia, Shouwen Ma, Martin Strauch, Anja Nissler; see upstream DESCRIPTION and data-source references", "papers": ["https://doi.org/10.1038/srep21841", "https://doi.org/10.1093/chemse/bjq042"], "changes": "Unchanged pinned data package; .git omitted. ShareAlike terms remain attached to this package, not asserted over unrelated repository content."}
+    },
+    {
+      "id": "shiu-author-model-source",
+      "paths": ["experiments/phase4ac-lif-semantics/external-resources"],
+      "license": {"upstream": "MIT", "evidence_file": "LICENSE", "evidence_sha256": "3621f6d6476189190e2960fa43f11b275ba4eca848fdac50a1ba2925de6223e8"},
+      "provenance": {"repository": "https://github.com/philshiu/Drosophila_brain_model", "commit": "91bdd1e7dcf193f3e7ca5a8933497fcef63b7960", "attribution": "Philip Shiu and Drosophila_brain_model contributors; original MIT copyright and permission notice retained", "paper": "https://www.nature.com/articles/s41586-024-07763-9", "changes": "The previously downloaded model.py, environment_full.yml, LICENSE and local provenance only. This is model source, not pretrained weights, and not a strict original-model reproduction claim."}
+    }
+  ],
+  "exclude_paths": [
+    "datasets/male-cns-v1.0/processed/_staging",
+    "experiments/phase4f-retinotopic-vision/external-resources/visualpathways/.env_sample",
+    "experiments/phase4f-retinotopic-vision/external-resources/visualpathways/pdfversion",
+    "experiments/phase4f-retinotopic-vision/external-resources/visualpathways/docs/column_coord.pdf"
+  ]
+}