{
  "dataset": "charite_mockdata",
  "version": "1",
  "generated_at": "2026-10-22T13:23:14Z",
  "generator": {
    "name": "charite_mockdata",
    "version": "1.0.0",
    "seed": 20261022,
    "n_icu_stays": 20000,
    "git_sha": "50d8bbf95477b571b53c22fd660865d608e6d0a4",
    "params": {
      "row_group_size": 100000,
      "row_group_size_overrides": {
        "vital_IBP": 500000
      },
      "compression": "zstd(9)",
      "polars": "2.0.0",
      "numpy": "2.5.4",
      "pyarrow": "26.0.0"
    },
    "build_seconds": 56.5
  },
  "reference_now": "2025-12-31T23:59:59",
  "timezone": "Europe/Berlin (naive local timestamps); hierarchy c_value timestamps are UTC strings",
  "file_naming": "<stem>-<sha256[:12]>.parquet (content-addressed; full sha256 and size in 'files')",
  "tables": {
    "it_ishmed_patient": {
      "files": [
        "charite_mockdata/it_ishmed_patient-362440425b31.parquet"
      ],
      "rows": 13591,
      "bytes": 168058,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_gender": "VARCHAR",
        "c_birthdate": "TIMESTAMP",
        "c_datetimeofdeath": "TIMESTAMP",
        "c_nationality": "VARCHAR",
        "c_countryofbirth": "VARCHAR",
        "c_country": "VARCHAR",
        "c_postcode": "VARCHAR"
      },
      "sorted_by": [
        "c_patnr"
      ]
    },
    "it_ishmed_fall": {
      "files": [
        "charite_mockdata/it_ishmed_fall-63bccdd0d8f5.parquet"
      ],
      "rows": 18653,
      "bytes": 296470,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_aufnahme": "TIMESTAMP",
        "c_entlassung": "TIMESTAMP",
        "c_age": "BIGINT",
        "c_entlassungsart": "VARCHAR",
        "c_admission_hospital": "VARCHAR",
        "c_discharge_hospital": "VARCHAR",
        "c_dod": "TIMESTAMP"
      },
      "sorted_by": [
        "c_falnr"
      ]
    },
    "it_ishmed_bewegung": {
      "files": [
        "charite_mockdata/it_ishmed_bewegung-8d9279b29789.parquet"
      ],
      "rows": 88557,
      "bytes": 1369018,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_laufende_nummer": "BIGINT",
        "c_bewegungstyp": "VARCHAR",
        "c_bewegungsart": "VARCHAR",
        "c_begin": "TIMESTAMP",
        "c_ende": "TIMESTAMP",
        "c_pflege_oe_id": "VARCHAR",
        "c_fachliche_oe_id": "VARCHAR",
        "c_pflege_oe": "VARCHAR",
        "c_fachliche_oe": "VARCHAR",
        "c_bewegungskategory": "VARCHAR",
        "c_zimmer": "VARCHAR",
        "c_bett": "VARCHAR"
      },
      "sorted_by": [
        "c_falnr",
        "c_laufende_nummer"
      ]
    },
    "it_ishmed_diagnose": {
      "files": [
        "charite_mockdata/it_ishmed_diagnose-6a73b5e43c3c.parquet"
      ],
      "rows": 115743,
      "bytes": 961590,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_laufende_nummer": "BIGINT",
        "c_diagnose_1": "VARCHAR",
        "c_diagnose_timestamp": "TIMESTAMP",
        "c_gewissheit": "VARCHAR",
        "c_flag_fachabteilungshauptdiagnose": "VARCHAR"
      },
      "sorted_by": [
        "c_falnr",
        "c_laufende_nummer"
      ]
    },
    "it_ishmed_procedure": {
      "files": [
        "charite_mockdata/it_ishmed_procedure-04fd238c28a3.parquet"
      ],
      "rows": 96816,
      "bytes": 1163807,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_prozedur_code": "VARCHAR",
        "c_prozedur_begin": "TIMESTAMP",
        "c_prozedur_ende": "TIMESTAMP",
        "c_lfd_bewegung": "BIGINT"
      },
      "sorted_by": [
        "c_falnr",
        "c_prozedur_begin"
      ]
    },
    "it_copra6_hierarchy_v2": {
      "files": [
        "charite_mockdata/it_copra6_hierarchy_v2/part-000-vital_IBP-c2ef0ecd8d0a.parquet",
        "charite_mockdata/it_copra6_hierarchy_v2/part-001-vital_NBP-c6a32042e87e.parquet",
        "charite_mockdata/it_copra6_hierarchy_v2/part-002-urine-9a5b61ff21fe.parquet",
        "charite_mockdata/it_copra6_hierarchy_v2/part-003-ventilation-4531c026913b.parquet",
        "charite_mockdata/it_copra6_hierarchy_v2/part-004-other-e449853eb84b.parquet"
      ],
      "rows": 22163651,
      "bytes": 100583584,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_id": "BIGINT",
        "c_parent_id": "BIGINT",
        "c_var_id": "BIGINT",
        "c_var_name": "VARCHAR",
        "c_var_timestamp": "TIMESTAMP",
        "c_value": "VARCHAR",
        "c_mean": "VARCHAR",
        "c_systolic": "VARCHAR",
        "c_diastolic": "VARCHAR"
      },
      "sorted_by": [
        "c_var_name",
        "c_falnr",
        "c_var_timestamp",
        "c_id"
      ],
      "partitions": {
        "charite_mockdata/it_copra6_hierarchy_v2/part-000-vital_IBP-c2ef0ecd8d0a.parquet": [
          "vital_IBP"
        ],
        "charite_mockdata/it_copra6_hierarchy_v2/part-001-vital_NBP-c6a32042e87e.parquet": [
          "vital_NBP"
        ],
        "charite_mockdata/it_copra6_hierarchy_v2/part-002-urine-9a5b61ff21fe.parquet": [
          "CO_Bilanz_Ausfuhr_Spontanurin",
          "FALL_ANAE_VERL_AUSFUHR_URIN",
          "Fall_Urinableitung_Verlauf_Menge",
          "Fall_Urinableitung_Verlauf_Zulauf"
        ],
        "charite_mockdata/it_copra6_hierarchy_v2/part-003-ventilation-4531c026913b.parquet": [
          "beat_einstell_FiO2",
          "beat_einstell_modus",
          "beat_mess_FiO2"
        ],
        "charite_mockdata/it_copra6_hierarchy_v2/part-004-other-e449853eb84b.parquet": [
          "BEH_ANAE_ASA_STATUS",
          "BEH_ANAE_OP_DRINGL",
          "Behandlung",
          "Behandlung_Beginn",
          "Behandlung_Ende",
          "Behandlung_Gewicht_Aufnahme",
          "CO_Patient_Aufnahme_Gewicht",
          "CO_klinStatus_Behandlung_Patient_Aufnahme_Gewicht_",
          "Fall_AWZ",
          "Fall_AWZ_Anlage",
          "Fall_AWZ_Anlageart",
          "Fall_AWZ_Applika",
          "Fall_AWZ_Entfernung",
          "Fall_AWZ_Typ",
          "OP_Zeiten",
          "OP_Zeiten_Ereignis",
          "OP_Zeiten_Zeitpunkt",
          "Patient_Gewicht",
          "Praemedikation_ASA_Status",
          "Praemedikation_Gewicht",
          "Score_SOFA",
          "Score_SOFA_Date",
          "Score_SOFA_Wert"
        ]
      }
    },
    "it_copra6_therapy": {
      "files": [
        "charite_mockdata/it_copra6_therapy-d12f1e8c2830.parquet"
      ],
      "rows": 122589,
      "bytes": 1455197,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_start": "TIMESTAMP",
        "c_end": "TIMESTAMP",
        "c_apparat_mode": "VARCHAR",
        "c_apparat_name": "VARCHAR",
        "c_apparat_type": "VARCHAR",
        "c_therapy_type": "VARCHAR"
      },
      "sorted_by": [
        "c_falnr",
        "c_start"
      ]
    },
    "it_copra6_medication": {
      "files": [
        "charite_mockdata/it_copra6_medication-85bed48ddb77.parquet"
      ],
      "rows": 650347,
      "bytes": 3912283,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_application_start": "TIMESTAMP",
        "c_application_end": "TIMESTAMP",
        "c_drug_name": "VARCHAR",
        "c_drug_id": "VARCHAR",
        "c_generic_name": "VARCHAR",
        "c_amount_total": "VARCHAR",
        "c_amount_unit": "VARCHAR",
        "c_rate": "VARCHAR",
        "c_rate_unit": "VARCHAR",
        "c_application_location": "VARCHAR",
        "c_volume_mixture": "VARCHAR",
        "c_volume_unit": "VARCHAR",
        "c_concentration": "VARCHAR"
      },
      "sorted_by": [
        "c_falnr",
        "c_application_start",
        "c_drug_name"
      ]
    },
    "it_ishmed_labor": {
      "files": [
        "charite_mockdata/it_ishmed_labor-615f23f5cede.parquet"
      ],
      "rows": 7366869,
      "bytes": 84218813,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_dokument_timestamp": "TIMESTAMP",
        "c_wert_timestamp": "TIMESTAMP",
        "c_katalog_leistungtext": "VARCHAR",
        "c_leistungnr": "VARCHAR",
        "c_wert": "VARCHAR",
        "c_wert_einheit": "VARCHAR"
      },
      "sorted_by": [
        "c_katalog_leistungtext",
        "c_falnr",
        "c_dokument_timestamp"
      ]
    },
    "it_ishmed_observation": {
      "files": [
        "charite_mockdata/it_ishmed_observation-18c9d6d14182.parquet"
      ],
      "rows": 18504,
      "bytes": 190299,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "c_type": "VARCHAR",
        "c_value": "VARCHAR",
        "c_unit": "VARCHAR",
        "c_valtimestamp": "TIMESTAMP"
      },
      "sorted_by": [
        "c_falnr",
        "c_valtimestamp"
      ]
    }
  },
  "total_bytes": 194319119,
  "validation": {
    "description": "Generator parameters per ICU stay and hospital case (archetype, severity, planned organ support, outcomes) for validating concept implementations. Fully synthetic — no patient data. Not part of the HDP-style tables, see docs/GENERATION.md 'Validation set'.",
    "stays": {
      "files": [
        "validation/stays-5b8cdc50ba65.parquet"
      ],
      "rows": 20000,
      "bytes": 1175692,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "stay_index": "BIGINT",
        "n_stays_in_case": "BIGINT",
        "icu_movement_ids": "BIGINT[]",
        "icu_wards": "VARCHAR[]",
        "icu_admission": "TIMESTAMP",
        "icu_discharge": "TIMESTAMP",
        "open_at_reference_now": "BOOLEAN",
        "readmission": "BOOLEAN",
        "admitted_from_or": "BOOLEAN",
        "archetype_key": "VARCHAR",
        "archetype_label": "VARCHAR",
        "severity": "DOUBLE",
        "stay_severity": "DOUBLE",
        "ventilated": "BOOLEAN",
        "intubation_time": "TIMESTAMP",
        "extubation_time": "TIMESTAMP",
        "reintubated": "BOOLEAN",
        "mv_start": "TIMESTAMP",
        "mv_end": "TIMESTAMP",
        "mv_hours": "DOUBLE",
        "tracheostomy": "BOOLEAN",
        "tracheostomy_time": "TIMESTAMP",
        "norepinephrine_planned": "BOOLEAN",
        "norepinephrine": "BOOLEAN",
        "norepinephrine_start": "TIMESTAMP",
        "norepinephrine_end": "TIMESTAMP",
        "shock_peak": "DOUBLE",
        "aki_stage_planned": "BIGINT",
        "rrt": "BOOLEAN",
        "rrt_start": "TIMESTAMP",
        "rrt_end": "TIMESTAMP",
        "rrt_modes": "VARCHAR[]",
        "chronic_dialysis": "BOOLEAN",
        "surgery": "BOOLEAN",
        "surgery_time": "TIMESTAMP",
        "surgery_ops": "VARCHAR[]",
        "surgery_elective": "BOOLEAN",
        "death_in_stay": "BOOLEAN",
        "hospital_death": "BOOLEAN",
        "death_time": "TIMESTAMP"
      },
      "description": "one row per ICU stay as the generator defines it (= merged ICU stay of the cohort loader): archetype, latent severity and the planned organ support / outcome"
    },
    "cases": {
      "files": [
        "validation/cases-2c8fbef0bb32.parquet"
      ],
      "rows": 18653,
      "bytes": 464774,
      "columns": {
        "c_patnr": "VARCHAR",
        "c_falnr": "VARCHAR",
        "case_kind": "VARCHAR",
        "archetype_key": "VARCHAR",
        "archetype_label": "VARCHAR",
        "severity": "DOUBLE",
        "admission_route": "VARCHAR",
        "n_icu_stays": "BIGINT",
        "main_dx": "VARCHAR",
        "surgery": "BOOLEAN",
        "surgery_ops": "VARCHAR[]",
        "open_at_reference_now": "BOOLEAN",
        "hospital_death": "BOOLEAN",
        "death_time": "TIMESTAMP",
        "chronic_dialysis": "BOOLEAN",
        "comorbidities": "VARCHAR[]",
        "cm_chf": "BOOLEAN",
        "cm_arrhythmia": "BOOLEAN",
        "cm_valvular": "BOOLEAN",
        "cm_pulm_circ": "BOOLEAN",
        "cm_pvd": "BOOLEAN",
        "cm_htn_unc": "BOOLEAN",
        "cm_htn_comp": "BOOLEAN",
        "cm_paralysis": "BOOLEAN",
        "cm_neuro_other": "BOOLEAN",
        "cm_copd": "BOOLEAN",
        "cm_dm_unc": "BOOLEAN",
        "cm_dm_comp": "BOOLEAN",
        "cm_hypothyroid": "BOOLEAN",
        "cm_renal": "BOOLEAN",
        "cm_liver": "BOOLEAN",
        "cm_pud": "BOOLEAN",
        "cm_hiv": "BOOLEAN",
        "cm_lymphoma": "BOOLEAN",
        "cm_metastatic": "BOOLEAN",
        "cm_tumor": "BOOLEAN",
        "cm_ra": "BOOLEAN",
        "cm_coag": "BOOLEAN",
        "cm_obesity": "BOOLEAN",
        "cm_weight_loss": "BOOLEAN",
        "cm_fluid": "BOOLEAN",
        "cm_anemia_bl": "BOOLEAN",
        "cm_anemia_def": "BOOLEAN",
        "cm_alcohol": "BOOLEAN",
        "cm_drugs": "BOOLEAN",
        "cm_psychoses": "BOOLEAN",
        "cm_depression": "BOOLEAN"
      },
      "description": "one row per hospital case: archetype of the ICU case ('non_icu' otherwise), admission route, comorbidity flags, outcome"
    }
  },
  "files": {
    "charite_mockdata/it_copra6_hierarchy_v2/part-000-vital_IBP-c2ef0ecd8d0a.parquet": {
      "sha256": "c2ef0ecd8d0a782614f7ee5e994366943fbd53a7d63a03ce88bf96459cd78ccb",
      "bytes": 79285513
    },
    "charite_mockdata/it_copra6_hierarchy_v2/part-001-vital_NBP-c6a32042e87e.parquet": {
      "sha256": "c6a32042e87eefe35183f7762ef397c7d2f5c1c072004c246d01789e2b044d3d",
      "bytes": 4528559
    },
    "charite_mockdata/it_copra6_hierarchy_v2/part-002-urine-9a5b61ff21fe.parquet": {
      "sha256": "9a5b61ff21fe0a3a5ff8a7e7a6e01e96c34642163c7881d824295c808e334970",
      "bytes": 5703539
    },
    "charite_mockdata/it_copra6_hierarchy_v2/part-003-ventilation-4531c026913b.parquet": {
      "sha256": "4531c026913b48bbf050e0363357505973bb36af08173ae2fdd4115f1334816c",
      "bytes": 4510126
    },
    "charite_mockdata/it_copra6_hierarchy_v2/part-004-other-e449853eb84b.parquet": {
      "sha256": "e449853eb84b162fd09db101c355af9e76f21ac3d41319a48b67ca9f1ed47efd",
      "bytes": 6555847
    },
    "charite_mockdata/it_copra6_medication-85bed48ddb77.parquet": {
      "sha256": "85bed48ddb77c14aa1a6c1360f75f044cb98172663bbb9a526ca8f66acbab176",
      "bytes": 3912283
    },
    "charite_mockdata/it_copra6_therapy-d12f1e8c2830.parquet": {
      "sha256": "d12f1e8c28300355fbb9125eaa8278bc18257d3ddb8256ebd3e588a6100193e2",
      "bytes": 1455197
    },
    "charite_mockdata/it_ishmed_bewegung-8d9279b29789.parquet": {
      "sha256": "8d9279b29789650fcf5737ccbbc168f770836c347d1ec33f75ce66f686d8326e",
      "bytes": 1369018
    },
    "charite_mockdata/it_ishmed_diagnose-6a73b5e43c3c.parquet": {
      "sha256": "6a73b5e43c3cbbaac0336d531c3f44e147d9ecb71c9e9b1c97767c1362e40911",
      "bytes": 961590
    },
    "charite_mockdata/it_ishmed_fall-63bccdd0d8f5.parquet": {
      "sha256": "63bccdd0d8f571ce8d8e9d68620e1aa5852b9a0b12d37e6f52b2fd4fe6a93914",
      "bytes": 296470
    },
    "charite_mockdata/it_ishmed_labor-615f23f5cede.parquet": {
      "sha256": "615f23f5cedec684f5594ea01a06d951563d5de4c0fe2d6d1b8289654e93d15b",
      "bytes": 84218813
    },
    "charite_mockdata/it_ishmed_observation-18c9d6d14182.parquet": {
      "sha256": "18c9d6d14182c6c6965171f215bace5397428ed89bcee39a603ca8f4ac6835b1",
      "bytes": 190299
    },
    "charite_mockdata/it_ishmed_patient-362440425b31.parquet": {
      "sha256": "362440425b31d260d9a0ecaf14a75be08dbbe2d7dfe74a7e7d334b996d1c151a",
      "bytes": 168058
    },
    "charite_mockdata/it_ishmed_procedure-04fd238c28a3.parquet": {
      "sha256": "04fd238c28a373111fa7848e53b56580a4a29ad20c7f3f07d8ecbd2bffbced83",
      "bytes": 1163807
    },
    "validation/cases-2c8fbef0bb32.parquet": {
      "sha256": "2c8fbef0bb3216e30a9fd344cf7a236504d74a4b836c9b0879f72b7ec51c1f12",
      "bytes": 464774
    },
    "validation/stays-5b8cdc50ba65.parquet": {
      "sha256": "5b8cdc50ba654c4f4c424f0df6fe0571efb2d76841c57ac1ad9c04e4d1bdd740",
      "bytes": 1175692
    }
  }
}
