From 75fe386ef650a96fb2ed59ae761c9f06f9e4c281 Mon Sep 17 00:00:00 2001
From: deeddy <deeddy@users.noreply.github.com>
Date: Sun, 28 Jun 2026 08:54:18 +0200
Subject: [PATCH 1/3] Add CITATION.cff (enables GitHub 'Cite this repository')

---
 CITATION.cff | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 CITATION.cff

diff --git a/CITATION.cff b/CITATION.cff
new file mode 100644
index 0000000..623a6a4
--- /dev/null
+++ b/CITATION.cff
@@ -0,0 +1,17 @@
+cff-version: 1.2.0
+title: NASdisks NAS Drive Data
+message: "If you use this dataset, please cite it and link to nasdisks.com."
+type: dataset
+authors:
+  - name: NASdisks
+url: "https://www.nasdisks.com/data/"
+repository-code: "https://github.com/deeddy/nas-drive-data"
+license: CC-BY-4.0
+keywords:
+  - NAS
+  - hard drives
+  - CMR
+  - SMR
+  - Backblaze
+  - reliability
+  - storage

From 673651a810105a50f09eec3f579dc1f6cc48c81e Mon Sep 17 00:00:00 2001
From: deeddy <deeddy@users.noreply.github.com>
Date: Sun, 28 Jun 2026 11:08:39 +0200
Subject: [PATCH 2/3] Add Frictionless datapackage.json (DataHub/Frictionless
 ingestable)

---
 datapackage.json | 50 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 datapackage.json

diff --git a/datapackage.json b/datapackage.json
new file mode 100644
index 0000000..f71a718
--- /dev/null
+++ b/datapackage.json
@@ -0,0 +1,50 @@
+{
+  "name": "nas-drive-data",
+  "title": "NASdisks NAS Drive Data",
+  "description": "Open dataset of currently-sold NAS and enterprise hard drives: full specs (capacity, RPM, cache, interface, form factor), verified CMR vs SMR, idle/seek acoustic noise, helium/air fill, drive class, and real-world annualized failure rates (AFR) computed from Backblaze Drive Stats. Drive specs and CMR/SMR are CC BY 4.0; AFR fields are cited to Backblaze Drive Stats, not relicensed.",
+  "homepage": "https://www.nasdisks.com/data/",
+  "licenses": [
+    { "name": "CC-BY-4.0", "title": "Creative Commons Attribution 4.0 International", "path": "https://creativecommons.org/licenses/by/4.0/" }
+  ],
+  "keywords": ["nas", "hard drives", "hdd", "cmr", "smr", "backblaze", "reliability", "annualized failure rate", "storage", "price per tb"],
+  "resources": [
+    {
+      "name": "drives",
+      "title": "NAS & enterprise hard drives (full dataset)",
+      "path": "https://www.nasdisks.com/data/drives.csv",
+      "format": "csv",
+      "mediatype": "text/csv",
+      "schema": {
+        "fields": [
+          { "name": "model", "type": "string" },
+          { "name": "brand", "type": "string" },
+          { "name": "line", "type": "string" },
+          { "name": "capacity_tb", "type": "number" },
+          { "name": "rpm", "type": "integer" },
+          { "name": "cache_mb", "type": "integer" },
+          { "name": "interface", "type": "string" },
+          { "name": "form_factor", "type": "string" },
+          { "name": "recording_tech", "type": "string", "description": "cmr or smr" },
+          { "name": "acoustic_idle_db", "type": "number" },
+          { "name": "acoustic_seek_db", "type": "number" },
+          { "name": "is_helium", "type": "boolean" },
+          { "name": "drive_class", "type": "string" },
+          { "name": "in_production", "type": "boolean" },
+          { "name": "also_sold_as", "type": "string" },
+          { "name": "afr_pct", "type": "number", "description": "Backblaze annualized failure rate (%)" },
+          { "name": "reliability_drive_count", "type": "integer", "description": "Backblaze" },
+          { "name": "reliability_drive_days", "type": "integer", "description": "Backblaze" },
+          { "name": "reliability_failures", "type": "integer", "description": "Backblaze" },
+          { "name": "reliability_source", "type": "string" }
+        ]
+      }
+    },
+    {
+      "name": "drives-json",
+      "title": "Full dataset (JSON, with license + reliability metadata)",
+      "path": "https://www.nasdisks.com/data/drives.json",
+      "format": "json",
+      "mediatype": "application/json"
+    }
+  ]
+}

From 2ab1f089c9642725c237b3c7ae97ffa5a6da5d14 Mon Sep 17 00:00:00 2001
From: deeddy <deeddy@users.noreply.github.com>
Date: Mon, 6 Jul 2026 19:53:59 +0200
Subject: [PATCH 3/3] Add Zenodo DOI badge + citation (10.5281/zenodo.21225049)

---
 README.md | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/README.md b/README.md
index c583370..8e79ee4 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,9 @@
 # NAS drive dataset
 
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.21225049.svg)](https://doi.org/10.5281/zenodo.21225049)
+
+**Cite:** NASdisks (2026), *NAS Drive Dataset*, Zenodo. doi:[10.5281/zenodo.21225049](https://doi.org/10.5281/zenodo.21225049)
+
 An original dataset of NAS and enterprise hard drives: full specs, **CMR vs SMR classification**, and **annualized failure rates** derived from Backblaze Drive Stats. 149 drives.
 
 The core of this dataset - the CMR/SMR classification and drive specs - is our own original research, compiled from manufacturer datasheets and model-number analysis. Manufacturers do not publish a unified CMR/SMR list; we built one. The failure-rate column enriches it with rates derived from Backblaze's raw Drive Stats data (our computation, their underlying counts).