Adding Research Papers

scripts/Readme.md

@@ -22,6 +22,15 @@ Generates `website/lib/generated/memberOrganizationsOutput.json`, the list of or
 - Walks each group's participations and collects the participating organizations (excluding individual participants).
 - Orders groups according to a predefined list and sorts organizations alphabetically.
 
+### `research-papers`
+
+Generates `website/lib/generated/researchPapers.json`, the list of research papers related to the Web of Things.
+
+- Reads the curated paper list (title → DOI) from [research-papers/researchPapersInput.ts](research-papers/researchPapersInput.ts).
+- For each DOI, fetches publication metadata from the [Crossref API](https://api.crossref.org/works).
+
+> Unlike `dev-tools` and `member-organizations`, this script is **not** run periodically/automatically. The relevant research papers change infrequently, so the list is maintained by hand and the script is run manually only when new papers need to be added. To add a paper, insert a new entry in [research-papers/researchPapersInput.ts](research-papers/researchPapersInput.ts) and run `npm run research-papers`.
+
 ## Setup
 
 ```bash
@@ -48,13 +57,16 @@ npm run dev-tools
 
 # Generate member organizations data
 npm run member-organizations
+
+# Generate research papers data (run manually, on demand)
+npm run research-papers
 ```
 
-Both scripts are run via [tsx](https://github.com/privatenumber/tsx), so no build step is required.
+The scripts are run via [tsx](https://github.com/privatenumber/tsx), so no build step is required.
 
 ## Automation
 
-These scripts run automatically through the [Weekly Script Updates](../.github/workflows/scripts.yml) GitHub workflow (scheduled weekly, or triggered manually via `workflow_dispatch`). The workflow:
+The `dev-tools` and `member-organizations` scripts run automatically through the [Weekly Script Updates](../.github/workflows/scripts.yml) GitHub workflow (scheduled weekly, or triggered manually via `workflow_dispatch`). The `research-papers` script is excluded from this automation and is run manually on demand. The workflow:
 
 1. Runs both scripts.
 2. Commits directly to `main` if only `lastUpdated` fields changed.

scripts/member-organizations/index.ts

@@ -16,6 +16,8 @@ async function fetchMemberOrganizations() {
     const result: Result = {};
 
     for (const groupLink of groups._links.groups) {
+      // Skip Web of Things Interest Group
+      if (groupLink.href === 'https://api.w3.org/groups/ig/wot') continue;
       const groupRes = await fetch(groupLink.href);
       const group = (await groupRes.json()) as Group;
       let participationsLink: string | undefined = group._links.participations.href;
@@ -45,7 +47,6 @@ async function fetchMemberOrganizations() {
       'Web of Things Community Group',
       'Web Thing Protocol Community Group',
       'Web of Things Japanese Community Group',
-      'Web of Things Interest Group',
     ];
 
     for (const groupName of groupOrder) {

scripts/package.json

@@ -7,7 +7,8 @@
   "type": "module",
   "scripts": {
     "dev-tools": "npx tsx dev-tools/index.ts",
-    "member-organizations": "npx tsx member-organizations/index.ts"
+    "member-organizations": "npx tsx member-organizations/index.ts",
+    "research-papers": "npx tsx research-papers/index.ts"
   },
   "devDependencies": {
     "@types/node": "^25.2.1",

scripts/research-papers/index.ts

@@ -0,0 +1,87 @@
+import { dirname, resolve } from 'path';
+import { fileURLToPath } from 'url';
+import { RESEARCH_PAPERS } from './researchPapersInput.ts';
+import { mkdirSync, writeFileSync } from 'fs';
+import { CrossrefDate, ResearchPaperFetchOutput } from './types.ts';
+
+const __dirname = dirname(fileURLToPath(import.meta.url));
+
+// Crossref asks callers to identify themselves; this also grants access to the
+// faster "polite" pool and reduces the chance of throttled/empty responses.
+const HEADERS = {
+  'User-Agent': 'wot-marketing/1.0 (https://github.com/w3c/wot-marketing; mailto:bobur.khayitov@siemens.com)',
+};
+
+(async () => {
+  const researchPapers: ResearchPaperFetchOutput[] = [];
+  // Fetch sequentially to stay well within Crossref's rate limits; firing all
+  for (const [title, doi] of Object.entries(RESEARCH_PAPERS)) {
+    try {
+      const result = await fetchWork(doi);
+      researchPapers.push(result);
+    } catch (err) {
+      console.error(`Could not fetch ${title} \n ${err}`);
+    }
+  }
+  // Save the fetched data in devToolsOutput.json
+  try {
+    const outputPath = resolve(__dirname, '../../website/lib/generated/researchPapers.json');
+    mkdirSync(dirname(outputPath), { recursive: true });
+    writeFileSync(outputPath, JSON.stringify(researchPapers, null, 2));
+    console.log('website/lib/generated/researchPapers.json successfully generated');
+  } catch (error) {
+    console.error('Could not save the output file:', error);
+  }
+})();
+
+async function fetchWork(doi: string, retries = 3): Promise<ResearchPaperFetchOutput> {
+  for (let attempt = 0; attempt <= retries; attempt++) {
+    try {
+      const response = await fetch(`https://api.crossref.org/works/${doi}`, {
+        headers: HEADERS,
+      });
+      if (!response.ok) {
+        throw new Error(`HTTP ${response.status} ${response.statusText}`);
+      }
+      // Read the body as text first so an empty/truncated response gives a clear error
+      const body = await response.text();
+      if (!body.trim()) {
+        throw new Error('Empty response body');
+      }
+      const message = JSON.parse(body).message;
+      return {
+        authors: message.author
+          .sort((a: any, b: any) => {
+            if (a.sequence === b.sequence) return 0;
+            return a.sequence === 'first' ? -1 : 1;
+          })
+          .map((author: any) => author.given + ' ' + author.family),
+        date: crossrefDateToLocaleString(message.published),
+        link: message.URL,
+        publisher: message.publisher,
+        title: message.title.join('. '),
+        type: message.type.replace(/[._-]+/g, ' ').replace(/\b\w/g, (char: string) => char.toUpperCase()),
+      };
+    } catch (err) {
+      if (attempt === retries) throw err;
+      // Exponential backoff before retrying (500ms, 1s, 2s, ...).
+      await sleep(500 * 2 ** attempt);
+    }
+  }
+  throw new Error('Could not fetch: ' + doi);
+}
+
+export function crossrefDateToLocaleString(date?: CrossrefDate): string {
+  const parts = date?.['date-parts']?.[0];
+
+  if (!parts?.[0]) throw new Error('Could not extract publish date');
+
+  const [year, month = 1, day = 1] = parts;
+
+  const dateObj = new Date(Date.UTC(year, month - 1, day));
+  return dateObj.toISOString();
+}
+
+function sleep(ms: number) {
+  return new Promise((res) => setTimeout(res, ms));
+}

scripts/research-papers/researchPapersInput.ts

@@ -0,0 +1,35 @@
+export const RESEARCH_PAPERS = {
+  'Methodologies in digital twin for manufacturing industry: A systematic literature review':
+    '10.1016/j.future.2025.107997',
+  'Increasing interoperability between digital twin standards and specifications: transformation of DTDL to AAS':
+    '10.3390/s23187742',
+  'Internet of Things: A comprehensive survey on syntactic and semantic interoperability for effective inter-entity communication':
+    '10.1016/j.array.2026.100942',
+  'Overview and comparison of asset information model standards': '10.1109/access.2023.3312286',
+  'DTAG: A methodology for aggregating digital twins using the WoTDT ontology': '10.3390/app14135960',
+  'Machine component monitoring in data and service ecosystems enabled by the asset administration shell':
+    '10.1016/j.procir.2024.10.269',
+  'Decentralized authentication for web of things: a self-sovereign identity (SSI)-based solution':
+    '10.1109/icnc59896.2024.10556086',
+  'Cyberlogic: A Foundational Framework for Cross-Space Logic in the Cyber-Physical-Social-Thinking Hyperspace':
+    '10.1109/jiot.2026.3698940',
+  'HoloWoT: a first step towards mixed reality digital twins for the industrial internet of things':
+    '10.1145/3652620.3688243',
+  'WoT2Pod: an architecture enabling an edge-to-cloud continuum': '10.1145/3627050.3627063',
+  'Proximity-based service discovery for distributed digital twin systems': '10.1007/s43926-025-00103-x',
+  'The Arrowhead Framework Ontology': '10.1109/ojies.2026.3693084',
+  'WoT-Server: Combining the Web-Of-Things and SensorThings standards to build an IoT platform': '10.21105/joss.09470',
+  'RobWoT: Generating Real-Time Digital Twin Simulations for the Robotic Web of Things':
+    '10.1109/wf-iot58464.2023.10539381',
+  'From Fragmentation to Integration: A Framework for Heterogeneous IoT-based Smart City Systems':
+    '10.1109/etfa65518.2025.11205783',
+  'RobWoTAR: Web of Things Approach to Universally Control Robots in Augmented Reality': '10.1145/3770501.3770526',
+  'Skill-Based Multi-Agent Systems for Building Control Using KNX IoT and Web of Things':
+    '10.1109/etfa65518.2025.11205736',
+  'Asynchronous Thing Descriptions for Crafting Applications in the Web of Things': '10.1109/ictai66417.2025.00197',
+  'RetroWoT: A Method to Integrate Brownfield Devices in the Web of Things': '10.1145/3703790.3703799',
+  'Vendor-Independent Data Platform Architecture in Smart Buildings': '10.1109/ccnc65079.2026.11366376',
+  'Stateful-WoT: Capturing the Behavior of Highly Dynamic Cyber-Physical Systems': '10.1109/coins61597.2024.10622288',
+  'Leveraging Information-Centric Edge Computing in Private 5G Cellular Networks via the W3C Web of Things':
+    '10.1109/ccnc54725.2025.10976001',
+};

scripts/research-papers/types.ts

@@ -0,0 +1,12 @@
+export interface ResearchPaperFetchOutput {
+  title: string;
+  type: string;
+  publisher: string;
+  authors: string[];
+  date: string;
+  link: string;
+}
+
+export type CrossrefDate = {
+  'date-parts'?: number[][];
+};