{
  "kind": "protein_material_aggregates",
  "title": "Protein / material generated-candidate aggregates — hashes + integer N",
  "look": "GET only. credentials omit. No visitor data. Generated rows without a PDB/ICD/InChI/COD key are not playable.",
  "claim": "DARK on generated labels. Play proteins on catalog.json PDB ids (game pdb). Play chemistry/material/disease on industry STD.",
  "label_kind": "GENERATED_CANDIDATE",
  "pdb_id": null,
  "n_proteins": 78680,
  "n_materials": 46622,
  "index_n": 125302,
  "fetched_at": "2026-08-24T18:28:07Z",
  "source_package": "steward-disk generated-candidate CSVs (not a public study name)",
  "c007": "C-007 arms not ingested. SOP JSON, manufacturing cookbooks, advanced-application protocols, and generation engines are refused.",
  "shear": "Using something that is not accurate (because it shears) may not be useless — it may be dangerous.",
  "not_known": "Unbound generated mass: not known. Win is the verified bond.",
  "instructions_mean": "Hosted surface is counts + integer descriptors + hashes only. No public named PDB / PubChem / ChEMBL / DailyMed ids in this aggregate. Playable protein set is discoveries/catalog.json N=258616.",
  "dropped_columns": [
    "confidence",
    "logp",
    "molecular_weight",
    "combined_score",
    "coherence",
    "overall_score",
    "tpsa",
    "drug_likeness_score",
    "safety_score",
    "synthetic_accessibility",
    "smiles",
    "sequence",
    "generated disease-target strings"
  ],
  "sources": [
    {
      "filename": "proteins_validated.csv",
      "source": "steward-disk generated-candidate CSV · proteins_validated.csv",
      "sha256": "bb3691b332fb15cdd54c43bc42905478e53c4f4b01862885a7304260498cf3f7",
      "n_rows": 78680,
      "role": "primary_protein",
      "integer_columns": {
        "length": {
          "min": 42,
          "max": 90,
          "sum": 5165782
        },
        "passes_safety": {
          "min": 0,
          "max": 1,
          "sum": 41391
        },
        "validation_passed": {
          "min": 1,
          "max": 1,
          "sum": 78680
        }
      }
    },
    {
      "filename": "proteins_validated_safe.csv",
      "source": "steward-disk generated-candidate CSV · proteins_validated_safe.csv",
      "sha256": "a2ca4777949d77d68acafb60e8c281d06a894e83c72f6e836cad45ac75e71def",
      "n_rows": 41391,
      "role": "subset_of_primary_protein",
      "integer_columns": {
        "length": {
          "min": 42,
          "max": 90,
          "sum": 2628907
        },
        "passes_safety": {
          "min": 1,
          "max": 1,
          "sum": 41391
        },
        "validation_passed": {
          "min": 1,
          "max": 1,
          "sum": 41391
        }
      }
    },
    {
      "filename": "proteins_by_disease.csv",
      "source": "steward-disk generated-candidate CSV · proteins_by_disease.csv",
      "sha256": "24cdbf96621e6c38fa046c7a203fcc3ea09e31fad410d9c1cb51f6d192a04204",
      "n_rows": 1400,
      "role": "sidecar_not_in_index_n",
      "integer_columns": {
        "length": {
          "min": 20,
          "max": 100,
          "sum": 78694
        }
      }
    },
    {
      "filename": "materials_bivqbit_validated.csv",
      "source": "steward-disk generated-candidate CSV · materials_bivqbit_validated.csv",
      "sha256": "eba20edffd6aecd8fd00d547deb217828be2ae82ff5e2bb1b16f990cbea17a66",
      "n_rows": 37910,
      "role": "primary_material",
      "integer_columns": {
        "num_atoms": {
          "min": 10,
          "max": 18,
          "sum": 553896
        },
        "hbd": {
          "min": 0,
          "max": 1,
          "sum": 7598
        },
        "hba": {
          "min": 0,
          "max": 2,
          "sum": 22790
        }
      }
    },
    {
      "filename": "materials_chemistry_validated.csv",
      "source": "steward-disk generated-candidate CSV · materials_chemistry_validated.csv",
      "sha256": "38fcd2c6048b361a0131843da549cfbbca84eefe921d1f575d28a010f09d6de4",
      "n_rows": 8712,
      "role": "primary_material",
      "integer_columns": {
        "lipinski_violations": {
          "min": 0,
          "max": 0,
          "sum": 0
        }
      }
    }
  ],
  "examples": [
    {
      "row_index": 0,
      "generated_label_hash": "e0baa708e2466b0a5aa786e70fdeb5e03310648bd6129bcbe14cac9edf8b7eea",
      "length": 88,
      "passes_safety": 1,
      "validation_passed": 1
    },
    {
      "row_index": 1,
      "generated_label_hash": "126e736d20205785aa3a188895113bedd7b8877f062062cbd4726569d6507a70",
      "length": 82,
      "passes_safety": 1,
      "validation_passed": 1
    },
    {
      "row_index": 2,
      "generated_label_hash": "23d2256ca5cc1a9b1ff20f6865614ba72c07202d36b8583d8bdf17ee691b5b9f",
      "length": 87,
      "passes_safety": 1,
      "validation_passed": 1
    },
    {
      "row_index": 0,
      "generated_label_hash": "4e7168f599c4ee9ccafc739657797953a5717cce52d07811d3cb4ac742209dfd",
      "num_atoms": 18,
      "hbd": 0,
      "hba": 0
    },
    {
      "row_index": 1,
      "generated_label_hash": "239215855b067a2b239b16f460daac390a98618f48747c819e2d4f2850d3a190",
      "num_atoms": 18,
      "hbd": 0,
      "hba": 0
    }
  ],
  "refused": [
    "C-007 SOP JSON directory (100 files) — not hosted",
    "C-007 manufacturing cookbooks (50 + index) — not hosted",
    "C-007 advanced-application protocols — not hosted",
    "generation engines under 05_TECHNICAL_CODE — MOCK/SIM, not court facts",
    "float score columns — Affine REFUSED_FLOAT",
    "generated disease-target labels — not hosted on the public apex"
  ],
  "play_via": [
    "#pdb-holdings",
    "#chemistry-inchi",
    "#material-std",
    "#disease-icd"
  ]
}