{
  "schema_version": "2.0",
  "record_type": "dataset",
  "tier": "verified",
  "slug": "chempile-lift",
  "name": "jablonkagroup/chempile-lift",
  "summary": {
    "en": "License: restricted (CC-BY-NC-SA-4.0); Mdexa hosting: link-only. restrictions are read broadly: CC-BY-NC-SA-4.0",
    "zh": "许可证声明：受限（CC-BY-NC-SA-4.0）；本站处理：只链接原出处。限制从宽认定。"
  },
  "systems": [
    "modern-medicine"
  ],
  "domains": [
    "pharmacy-drugs"
  ],
  "content_types": [
    "database",
    "annotated-corpus"
  ],
  "content_description": {
    "en": "Chemical dataset with configurations such as BACE, BBBP, MUV, RedDB and SIDER, stored as text; primarily English, reflecting biases in chemical databases and scientific literature.",
    "zh": "包含 BACE、BBBP、MUV、RedDB、SIDER 等配置的化学数据集，以文本形式存储，主要为英文内容，反映化学数据库和科学文献中的偏差。"
  },
  "languages": [
    "en"
  ],
  "modalities": [
    "text"
  ],
  "size": {
    "raw": null,
    "measures": []
  },
  "publisher": "jablonkagroup",
  "year": {
    "value": null,
    "raw": null
  },
  "license": {
    "legacy_status": "pending",
    "spdx": "CC-BY-NC-SA-4.0",
    "commercial_use": "no",
    "derivatives": "unstated",
    "redistribution": "unstated",
    "rationale": {
      "en": "restrictions are read broadly: CC-BY-NC-SA-4.0",
      "zh": "限制从宽认定"
    },
    "evidence": [
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s03 (api-hf)",
          "zh": "在快照 s03（api-hf）中找到的声明"
        },
        "excerpt": "\"cc-by-nc-sa-4.0\"",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s03",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "hf-card-metadata",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "license:\n- cc-by-nc-sa-4.0",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "hf-card-text",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "All content is made open-source under the **CC BY-NC-SA 4.0** license, allowing for:",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "hf-card-text",
        "location_detail": {
          "en": "Statement found in snapshot s01 (readme)",
          "zh": "在快照 s01（readme）中找到的声明"
        },
        "excerpt": "- **License**: Non-commercial use only under CC BY-NC-SA 4.0",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s01",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "dataset-page",
        "location_detail": {
          "en": "Statement found in snapshot s02 (page)",
          "zh": "在快照 s02（page）中找到的声明"
        },
        "excerpt": "License: cc-by-nc-sa-4.0",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "captured_by": "pipeline"
      },
      {
        "location": "dataset-page",
        "location_detail": {
          "en": "Statement found in snapshot s02 (page)",
          "zh": "在快照 s02（page）中找到的声明"
        },
        "excerpt": "License : Non-commercial use only under CC BY-NC-SA 4.0",
        "spdx": "CC-BY-NC-SA-4.0",
        "url": "https://huggingface.co/datasets/jablonkagroup/chempile-lift",
        "verified_on": "2026-11-12",
        "snapshot_id": "s02",
        "observed": "page",
        "captured_by": "pipeline"
      }
    ],
    "license_conditions": [
      "attribution",
      "share-alike"
    ]
  },
  "license_status": "restricted",
  "hosting": "link-only",
  "hosting_reason": {
    "en": "License restricted: restrictions are read broadly: CC-BY-NC-SA-4.0. Link only.",
    "zh": "许可证受限：限制从宽认定。只链接原出处。"
  },
  "signoff": null,
  "risk_flags": [],
  "provenance": {
    "source_description": null,
    "upstream": []
  },
  "known_issues": [
    {
      "en": "The dataset reflects biases present in chemical databases and scientific literature.",
      "zh": "该数据集反映了化学数据库和科学文献中存在的偏差。"
    }
  ],
  "preflight": {
    "status": "not-run"
  },
  "access": {
    "mdexa_download": null,
    "external_urls": [
      "https://huggingface.co/datasets/jablonkagroup/chempile-lift"
    ],
    "notes": null
  },
  "citation": {
    "text": null,
    "references": [
      "arXiv:2505.12534"
    ]
  },
  "verification_level": "verified",
  "last_verified": "2026-11-14",
  "tags": [
    {
      "facet": "intended_use",
      "value": "fine-tuning",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - name: train",
      "snapshot_id": "s01"
    },
    {
      "facet": "intended_use",
      "value": "evaluation",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - name: test",
      "snapshot_id": "s01"
    },
    {
      "facet": "official_split",
      "value": "full-split",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - name: train",
      "snapshot_id": "s01"
    },
    {
      "facet": "data_format",
      "value": "parquet",
      "basis": "inferred",
      "inferred_from": "snapshot-structure",
      "excerpt": "  - name: text",
      "snapshot_id": "s01"
    }
  ],
  "changelog": [
    {
      "date": "2026-11-13",
      "change": {
        "en": "Added via the automated pipeline and passed all checks (gates, verbatim quotes, rule engine, two independent extractions).",
        "zh": "经自动流水线收录并通过全部校验（门禁、逐字引用、判定引擎、两轮独立抽取）。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-13",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    },
    {
      "date": "2026-11-14",
      "change": {
        "en": "Re-adjudicated under the current rules; all machine checks still pass.",
        "zh": "按当前规则重新判定；机器检查仍全部通过。"
      }
    }
  ],
  "access_recipe": {
    "verified_on": "2026-11-14",
    "platform": "huggingface",
    "repo_id": "jablonkagroup/chempile-lift",
    "source": {
      "api_url": "https://huggingface.co/api/datasets/jablonkagroup/chempile-lift",
      "fetched_on": "2026-11-14"
    },
    "access_state": "open",
    "files": [],
    "files_truncated": false,
    "commands": [
      {
        "command": "hf download jablonkagroup/chempile-lift --repo-type dataset",
        "evidence": {
          "excerpt": "You can use the hf download command from the terminal to directly download files from the Hub.",
          "doc": "hf-download",
          "url": "https://huggingface.co/docs/huggingface_hub/guides/download",
          "fetched_on": "2026-11-14"
        }
      }
    ],
    "registration": null,
    "version": {
      "commit": "ec8e0efe144d6a05c98ef55c0f136b25f5cb5658",
      "last_modified": "2026-01-12T05:37:34.000Z"
    },
    "license_note": {
      "license_status": "restricted",
      "text": "Use according to the terms of the official source; this recipe does not say the data can be used freely."
    },
    "gaps": [
      "the platform publishes no checksum for these files; none was computed (we do not download data files)"
    ]
  },
  "_links": {
    "text": "Continue in this database. This record is one of 109 processed and verified records (datasets, data resources and open models). To find others, call `https://mcp.mdexa.com/v1/datasets?q=<words>` or connect the MCP server at `https://mcp.mdexa.com/mcp`; no key is needed for 20 calls per minute. Rows are under 1 KB; an empty result means \"not listed\". For a list of items, one batch check (free account) returns a report. Guide: /agents.md. Similar records: TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening (https://mdexa.com/datasets/topu-lbvs/); ClinPGx/PharmGKB (https://mdexa.com/datasets/pharmgkb/); Therapeutics Data Commons (https://mdexa.com/datasets/tdc/).",
    "records": 109,
    "search": {
      "template": "https://mcp.mdexa.com/v1/datasets?q={words}",
      "example": "https://mcp.mdexa.com/v1/datasets?q=binding%20affinity"
    },
    "mcp": "https://mcp.mdexa.com/mcp",
    "anonymous_calls_per_minute": 20,
    "guide": "https://mdexa.com/agents.md",
    "faq": "https://mdexa.com/developers/faq/",
    "similar": [
      {
        "name": "TopU-LBVS: Multi-Target Benchmark for Ligand-Based Virtual Screening",
        "url": "https://mdexa.com/datasets/topu-lbvs/",
        "json": "https://mdexa.com/datasets/topu-lbvs.json"
      },
      {
        "name": "ClinPGx/PharmGKB",
        "url": "https://mdexa.com/datasets/pharmgkb/",
        "json": "https://mdexa.com/datasets/pharmgkb.json"
      },
      {
        "name": "Therapeutics Data Commons",
        "url": "https://mdexa.com/datasets/tdc/",
        "json": "https://mdexa.com/datasets/tdc.json"
      }
    ]
  }
}