{
  "registry": "SIMARC data commons",
  "version": "v1",
  "updated": "2026-08-21",
  "policy": {
    "cost": "free, no account, no data-use agreement, no fee",
    "bundling": "nothing is bundled; every byte re-downloads from a primary source",
    "rationale": "A dataset you cannot re-fetch is a dataset whose provenance you are asserting rather than demonstrating.",
    "redistributable": "mirrored with SHA-256 manifests",
    "encumbered": "shipped as a re-download script plus checksums - equally reproducible, free of redistribution constraints",
    "nomination": "request_data(name, source_url, why) over MCP, or https://simarc.org/contact.html"
  },
  "datasets": [
    {
      "id": "tcga-pancancer-rnaseq",
      "name": "TCGA pan-cancer RNA-seq",
      "program": "P-03",
      "scale": "33 projects, ~11,500 patients",
      "rung_reachable": "OBSERVATIONAL",
      "access": "fetch + hash",
      "source_url": "https://portal.gdc.cancer.gov/",
      "license": "open access tier"
    },
    {
      "id": "depmap-crispr",
      "name": "DepMap CRISPR gene effect",
      "program": "P-03",
      "scale": "1,208 cell lines x 18,531 genes",
      "rung_reachable": "PERTURBATIONAL",
      "access": "fetch + hash",
      "source_url": "https://depmap.org/portal/download/",
      "license": "CC BY 4.0"
    },
    {
      "id": "dose-response",
      "name": "Dose-response compendium (CTRPv2, GDSC and others)",
      "program": "P-03",
      "scale": "5,450,000 measurements",
      "rung_reachable": "PHARMACOLOGICAL",
      "access": "fetch + hash",
      "source_url": "https://depmap.org/portal/download/",
      "license": "varies by source, all open"
    },
    {
      "id": "clinicaltrials-oncology",
      "name": "ClinicalTrials.gov - oncology interventional",
      "program": "P-03",
      "scale": "97,623 interventional cancer trials",
      "rung_reachable": "CLINICAL",
      "access": "live query, timestamped",
      "source_url": "https://clinicaltrials.gov/data-api/api",
      "license": "public domain"
    },
    {
      "id": "clinicaltrials-dementia",
      "name": "ClinicalTrials.gov - dementia interventional",
      "program": "P-04",
      "scale": "8,224 interventional trials",
      "rung_reachable": "CLINICAL",
      "access": "live query, timestamped",
      "source_url": "https://clinicaltrials.gov/data-api/api",
      "license": "public domain"
    },
    {
      "id": "bellenguez-2022-gwas",
      "name": "Bellenguez 2022 Alzheimer's disease GWAS",
      "program": "P-04",
      "scale": "21,101,114 variants, n = 487,511",
      "rung_reachable": "GENETIC",
      "access": "fetch + md5 verified on every run",
      "source_url": "https://www.ebi.ac.uk/gwas/",
      "license": "open, no data-use agreement",
      "checksum_policy": "md5 verified against the EBI published checksum each load"
    },
    {
      "id": "europepmc-dementia",
      "name": "Europe PMC - dementia literature corpus",
      "program": "P-04",
      "scale": "227,231 records on 'Alzheimer disease', with retraction metadata",
      "rung_reachable": "prior art",
      "access": "live query",
      "source_url": "https://europepmc.org/RestfulWebService",
      "license": "open"
    },
    {
      "id": "open-targets-gnomad",
      "name": "Open Targets and gnomAD",
      "program": "P-03, P-04",
      "scale": "associations, drugs, mechanisms, constraint, allele frequencies",
      "rung_reachable": "prior art",
      "access": "fetch + hash",
      "source_url": "https://platform.opentargets.org/",
      "license": "CC0 / open"
    },
    {
      "id": "cmb-skymaps",
      "name": "Planck and WMAP CMB sky maps",
      "program": "P-01",
      "scale": "4 independent sky-cleanings across two missions",
      "rung_reachable": "OBSERVATIONAL",
      "access": "fetch + hash",
      "source_url": "https://pla.esac.esa.int/",
      "license": "open"
    },
    {
      "id": "quasar-catalog",
      "name": "Quasar catalogs",
      "program": "P-01",
      "scale": "756,000 objects",
      "rung_reachable": "OBSERVATIONAL",
      "access": "fetch + hash",
      "source_url": "https://www.sdss.org/dr17/",
      "license": "open"
    },
    {
      "id": "butson-corpus-6",
      "name": "The Butson corpus at order 6",
      "program": "P-01",
      "scale": "27 inequivalent classes",
      "rung_reachable": "reference",
      "access": "mirrored",
      "license": "redistributable"
    }
  ],
  "blocked": [
    {
      "name": "ADNI, NACC, ROSMAP, UK Biobank",
      "program": "P-04",
      "why_blocked": "All require data-use applications. They are where individual-level longitudinal data lives.",
      "consequence": "The lag gate and the competing-risk gate are built, tested in both directions, and currently pointed at no data.",
      "status": "named as blocked rather than worked around; collaboration sought"
    }
  ],
  "cosmology": {
    "note": "Cosmology and galaxy-dynamics holdings. Redistribution differs by source, so it is recorded per dataset: only entries marked mirrored are copied onto our servers, and everything else is published as a pointer, a fetch route and a checksum. Journal PDFs in the source tree are excluded — they are reading, not data, and they are not ours to redistribute.",
    "datasets": [
      {
        "id": "cosmo-act-cmb-lensing",
        "name": "act cmb lensing",
        "program": "P-01",
        "files": 10,
        "bytes": 362673284,
        "sources": [
          "https://arxiv.org/abs/2206.07773"
        ],
        "license": "ACT via NASA LAMBDA — public, attribution",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-cosmic-chronometers",
        "name": "cosmic chronometers",
        "program": "P-01",
        "files": 5,
        "bytes": 6493,
        "sources": [
          "https://cluster.difa.unibo.it/astro/CC_data/data_CC.dat",
          "https://arxiv.org/abs/2201.07241"
        ],
        "license": "compilation of published tables — attribution",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-desi-bao",
        "name": "desi bao",
        "program": "P-01",
        "files": 26,
        "bytes": 32761146,
        "sources": [
          "https://arxiv.org/e-print/2503.14738",
          "https://arxiv.org/abs/2503.14738"
        ],
        "license": "DESI DR1 — CC BY 4.0",
        "mirrored": true,
        "access": "mirrored with SHA-256 manifest",
        "pdfs_excluded": 48
      },
      {
        "id": "cosmo-dsph-member-stars",
        "name": "dsph member stars",
        "program": "P-01",
        "files": 6,
        "bytes": 1638633,
        "sources": [
          "https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/AJ/137/3100&amp",
          "https://cdsarc.cds.unistra.fr/viz-bin/cat/J/AJ/137/3100",
          "https://cds.unistra.fr/vizier-org/licences_vizier.html",
          "https://doi.org/10.26093/cds/vizier.51373100"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-early-type-rar",
        "name": "early type rar",
        "program": "P-01",
        "files": 8,
        "bytes": 7766512,
        "sources": [
          "https://arxiv.org/e-print/1208.3522",
          "https://tapvizier.cds.unistra.fr/TAPVizieR/tap/sync"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 35
      },
      {
        "id": "cosmo-erosita-clusters",
        "name": "erosita clusters",
        "program": "P-01",
        "files": 7,
        "bytes": 4295832,
        "sources": [
          "https://cdsarc.cds.unistra.fr/ftp/J/A+A/685/A106/",
          "https://arxiv.org/abs/2402.08458"
        ],
        "license": "eROSITA DR1 — check terms before mirroring",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-frb-foreground",
        "name": "frb foreground",
        "program": "P-01",
        "files": 14,
        "bytes": 586162213,
        "sources": [
          "https://tapvizier.cds.unistra.fr/TAPVizieR/tap/sync"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-highz-rar",
        "name": "highz rar",
        "program": "P-01",
        "files": 433,
        "bytes": 29362495,
        "sources": [
          "https://arxiv.org/abs/2504.20857",
          "https://arxiv.org/abs/1703.04321",
          "https://arxiv.org/abs/2604.22613",
          "https://arxiv.org/abs/1512.04543"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 10
      },
      {
        "id": "cosmo-local-group-dwarfs",
        "name": "local group dwarfs",
        "program": "P-01",
        "files": 6,
        "bytes": 56349,
        "sources": [
          "https://vizier.cds.unistra.fr/viz-bin/votable?-source=J/AJ/144/4&amp",
          "https://cdsarc.cds.unistra.fr/viz-bin/cat/J/AJ/144/4",
          "https://cds.unistra.fr/vizier-org/licences_vizier.html",
          "http://vizier.cds.unistra.fr/doc/asu.html"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-more-frbs",
        "name": "more frbs",
        "program": "P-01",
        "files": 9,
        "bytes": 195888,
        "sources": [
          "https://arxiv.org/e-print/2511.01195",
          "https://arxiv.org/abs/2511.01195"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 9
      },
      {
        "id": "cosmo-mw-vertical-kz",
        "name": "mw vertical kz",
        "program": "P-01",
        "files": 7,
        "bytes": 258906,
        "sources": [
          "https://arxiv.org/e-print/1309.0809",
          "https://doi.org/10.1088/0004-637X/779/2/115"
        ],
        "license": "not yet established — fetch-only until checked",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      },
      {
        "id": "cosmo-tidal-streams",
        "name": "tidal streams",
        "program": "P-01",
        "files": 15,
        "bytes": 308872417,
        "sources": [
          "https://arxiv.org/abs/1805.00425"
        ],
        "license": "Gaia-derived tracks via galstreams — check per track",
        "mirrored": false,
        "access": "fetch + hash",
        "pdfs_excluded": 0
      }
    ]
  }
}