{
  "profile": "tabular-data-package",
  "name": "basisdesk-longitudinal-corpus-2026",
  "title": "Basis Desk Longitudinal Primary-Source Crypto News, Regulatory Actions, and On-Chain Whale Flow Dataset (2026)",
  "version": "2026.10",
  "created": "2026-10-01T00:00:00Z",
  "updated": "2026-10-27T06:28:30.518Z",
  "homepage": "https://basisdesk.news/research",
  "description": "Machine-readable longitudinal corpus of source-verified cryptocurrency news articles, regulatory actions (SEC, CFTC, ESMA, FCA, DOJ, Federal Reserve, EU MiCA), automated grounding-audit scores, and labelled on-chain whale transfers (>= $5M USD) produced by the Basis Desk autonomous newsroom.",
  "keywords": [
    "cryptocurrency news dataset",
    "primary-source verification",
    "financial NLP benchmark",
    "regulatory filings corpus",
    "on-chain whale transfers",
    "automated fact-checking",
    "Basis Desk"
  ],
  "licenses": [
    {
      "name": "CC-BY-4.0",
      "title": "Creative Commons Attribution 4.0 International",
      "path": "https://creativecommons.org/licenses/by/4.0/"
    }
  ],
  "contributors": [
    {
      "title": "Julian Mercer",
      "role": "author",
      "organization": "Basis Desk",
      "path": "https://basisdesk.news/about/julian-mercer",
      "orcid": "0009-0003-1162-170X"
    },
    {
      "title": "Basis Desk Research Desk",
      "role": "publisher",
      "organization": "Basis Desk",
      "path": "https://basisdesk.news/research"
    }
  ],
  "stats": {
    "published_articles": 1321,
    "active_primary_sources": 70,
    "tracked_whale_transfers": 31353,
    "technical_reports": 3
  },
  "resources": [
    {
      "name": "verified-crypto-news-csv",
      "title": "Basis Desk Verified Crypto News & Audit Corpus (CSV)",
      "path": "https://basisdesk.news/api/research/dataset.csv",
      "mediatype": "text/csv",
      "format": "csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "id",
            "type": "string",
            "description": "Unique Basis Desk article identifier"
          },
          {
            "name": "kind",
            "type": "string",
            "description": "Article class: news | analysis | explainer"
          },
          {
            "name": "published_iso",
            "type": "datetime",
            "description": "Publication timestamp (ISO 8601 UTC)"
          },
          {
            "name": "category",
            "type": "string",
            "description": "Primary newsroom desk category"
          },
          {
            "name": "sentiment",
            "type": "string",
            "description": "Assessed story tone: bullish | bearish | neutral"
          },
          {
            "name": "tickers",
            "type": "string",
            "description": "Pipe-delimited asset symbols"
          },
          {
            "name": "word_count",
            "type": "integer",
            "description": "Verified article body word count"
          },
          {
            "name": "audit_score",
            "type": "number",
            "description": "Second-pass grounding audit score (0-100)"
          },
          {
            "name": "hero_score",
            "type": "number",
            "description": "Composite impact and source-authority score (0-1)"
          },
          {
            "name": "regulatory_status",
            "type": "string",
            "description": "Action status when applicable (proposed, final, enforcement, etc.)"
          },
          {
            "name": "headline",
            "type": "string",
            "description": "Verified article headline"
          },
          {
            "name": "canonical_url",
            "type": "string",
            "format": "uri",
            "description": "Canonical article URL on basisdesk.news"
          }
        ]
      }
    },
    {
      "name": "verified-crypto-news-jsonl",
      "title": "Basis Desk Verified Crypto News & At-a-Glance Corpus (JSONL)",
      "path": "https://basisdesk.news/api/research/dataset.jsonl",
      "mediatype": "application/x-ndjson",
      "format": "jsonl",
      "encoding": "utf-8"
    },
    {
      "name": "bibtex-citations",
      "title": "BibTeX Citations for Basis Desk Technical Reports & Datasets",
      "path": "https://basisdesk.news/api/research/cite.bib",
      "mediatype": "application/x-bibtex",
      "format": "bib"
    },
    {
      "name": "bd-tr-2026-01",
      "title": "BD-TR-2026-01: Primary-Source Grounding and Automated Claim Verification in Real-Time Cryptocurrency Newsrooms",
      "path": "https://basisdesk.news/papers/BasisDesk-2026-Primary-Source-Verification-and-Grounding-Audit-Architecture.pdf",
      "landingPage": "https://basisdesk.news/research/bd-tr-2026-01",
      "mediatype": "application/pdf",
      "format": "pdf",
      "published": "2026-10-01"
    },
    {
      "name": "bd-tr-2026-02",
      "title": "BD-TR-2026-02: Cross-Venue Entity Resolution, Regulatory Filing Ingestion, and On-Chain Whale Flow Attribution at the Edge",
      "path": "https://basisdesk.news/papers/BasisDesk-2026-Cross-Venue-Entity-Resolution-and-Onchain-Whale-Attribution-Study.pdf",
      "landingPage": "https://basisdesk.news/research/bd-tr-2026-02",
      "mediatype": "application/pdf",
      "format": "pdf",
      "published": "2026-10-10"
    },
    {
      "name": "bd-tr-2026-03",
      "title": "BD-TR-2026-03: Client-Triggered Claim Verification and Smart-Contract Risk Heuristics: Architecture of the Basis Desk Verify Benchmark",
      "path": "https://basisdesk.news/papers/BasisDesk-2026-Browser-Level-Claim-Verification-and-Token-Security-Benchmark.pdf",
      "landingPage": "https://basisdesk.news/research/bd-tr-2026-03",
      "mediatype": "application/pdf",
      "format": "pdf",
      "published": "2026-10-18"
    }
  ]
}